Radiomics Based on the Tumor–Parenchyma Invasive Interface Predicts Major Pathological Response to Neoadjuvant Immunochemotherapy in Non-small Cell Lung Cancer

Radiomics Based on the Tumor–Parenchyma Invasive Interface Predicts Major Pathological Response to Neoadjuvant Immunochemotherapy in Non-small Cell Lung Cancer | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Radiomics Based on the Tumor–Parenchyma Invasive Interface Predicts Major Pathological Response to Neoadjuvant Immunochemotherapy in Non-small Cell Lung Cancer Yisong Wang, Xiaoying Li, Youlan Shang, Xiangru Song, Xiaohuang Yang, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7531855/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Background Accurate prediction of tumor response to neoadjuvant immunochemotherapy (NAIC) enables personalized perioperative therapy for resectable non-small cell lung cancer (NSCLC). Objective The present aimed to evaluate the predictive value of radiomics derived from the tumor-parenchyma invasive zone for response to NAIC in resectable NSCLC, with the goal of developing a more accurate and clinically applicable model. Methods Patients with pathologically proven NSCLC from August 2019 and March 2025 were retrospectively included from two medical centers. In the training set, radiomics features were extracted from the whole tumor region and tumor margin region (6mm) respectively. Following feature selection via intraclass correlation coefficient and least absolute shrinkage and selection operator, the Whole Tumor Model (WTM) and Tumor Margin model (TMM) were developed to non-invasively predict major pathological response (MPR) following NAIC. The performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value, and negative predictive value in the internal validation and external test sets. The optimal radiomics model and clinical characteristics were combined to build the hybrid model (HM). Results A total of 169 patients (median age, 60 years; 154 men) were divided into training, internal validation and external test sets, with 104 patients (61.5%) achieving MPR. In the test dataset, WTM and TMM achieved AUCs of 0.71 (95% CI: 0.54–0.89) and 0.84 (95% CI: 0.71–0.97), respectively. After incorporating tumor margin radiomics features and clinical predictors(pathology), the HM demonstrated satisfactory performance in the training set (AUC: 0.88, 95% CI: 0.81–0.95) and internal validation set (AUC: 0.86, 95% CI: 0.74–0.98). In the independent external test set, the HM obtained satisfactory performance (AUC = 0.87, 95% CI: 0.76–0.98). Decision curves analysis indicated that the radiomics-clinical combined nomogram provided significant clinical utility. Conclusion A radiomics model based on the tumor margin region outperformed the whole-tumor model in predicting MPR in NSCLC. Our study developed a novel tool to predict the response of NSCLC to NAIC, which demonstrated excellent performance. Radiomics Neoadjuvant immunochemotherapy Major pathological response Non-small cell lung cancer nomogram Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Introduction Lung cancer remains the leading cause of cancer-related mortality worldwide and is among the most frequently diagnosed malignancies[ 1 ]. Non-small cell lung cancer (NSCLC) accounts for approximately 85% of all cases[ 2 ]. Surgical resection remains the cornerstone of curative treatment for NSCLC in both early and locally advanced stages[ 3 ]. The extent of residual tumor cells after surgery is a key prognostic factor influencing long-term survival. Studies have shown that NSCLC patients whose resected specimens demonstrate a major pathologic response (MPR) after neoadjuvant treatment experience significantly improved survival outcomes[ 4 ]. Compared to chemotherapy alone, neoadjuvant immunochemotherapy (NAIC) improves the MPR rate and long-term survival, making it a promising strategy for resectable NSCLC[ 5 ]. However, a substantial proportion of patients fail to achieve MPR and may even experience immune-related adverse effects after NAIC[ 6 ], underscoring the urgent need for reliable methods to identify those most likely to benefit from this approach. Tumor mutational burden (TMB) and PD-L1 expression are widely used biomarkers for predicting responses to immune checkpoint inhibitors[ 7 , 8 ]. However, their assessment relies on invasive tissue sampling, and tumor heterogeneity poses challenges to the consistency and reliability of test results. Radiomics and deep learning can analyze a broad spectrum of quantifiable features from medical imaging and have emerged as promising approaches in lung cancer precision medicine[ 9 , 10 ]. Numerous studies have leveraged CT image features to predict MPR in NSCLC following NAIC, but they primarily analyzed the entire tumor as a whole, thereby overlooking the tumoral heterogeneity. Tumor heterogeneity is increasingly recognized as a critical factor reflecting distinct biological properties[ 11 , 12 ]. This may be attributed to central necrosis and increased cellular proliferation at the tumor periphery[ 13 ]. The tumor-stroma interface is the most biologically diverse and heterogeneous region within the tumor microenvironment, serving as a crucial hub for tumor-host interactions. Studies have demonstrated that tumor margin region is a hotspot for key biological processes, including angiogenesis, immune cell infiltration, and tumor invasion[ 14 – 16 ]. To the best of our knowledge, no previous studies have explored the predictive value of tumor margin region features for assessing NAIC response in NSCLC. This study aimed to evaluate these features and develop a preoperative model to predict NAIC response in NSCLC. Materials and Method Patients The study was approved by the Ethics Committee (retrospective study approval 2023 − 121) and the requirement for informed consent was waived. We retrospectively screened patients with NSCLC who underwent surgery following NAIC at two medical centers between August 2019 and March 2025. Inclusion criteria included: (1) NSCLC diagnosis confirmed by biopsy pathology; (2) clinically staged II to III; (3) completion of at least two cycles of NAIC; (4) postoperative pathological evaluation of tumor and lymph nodes as per International Association for the Study of Lung Cancer (IASLC) guidelines. Exclusion criteria included: (1) prior immunotherapy; (2) absence of pre-NAIC contrasted-enhanced CT images; (3) CT images with insufficient quality for radiomic analysis; and (4) time interval between chest CT and treatment initiation exceeds one month. We collected baseline clinical information and contrasted-enhanced CT images acquired within one month prior to the initiation of NAIC. NAIC regimens usually consist of 2 to 5 cycles of pembrolizumab or nivolumab administered in combination with platinum-based chemotherapy. Finally, 169 patients were included in the study. For model development, patients from the Second Xiangya Hospital were randomly assigned to training and internal validation sets in a 7:3 ratio, while the cohort from Hunan Cancer Hospital served as an external test set to evaluate model performance. The patient selection process and distribution flowchart are depicted in Fig. 1 , and the overall study design is illustrated in Fig. 2 . Histopathological assessment and definition of MPR According to the multidisciplinary recommendations from the IASLC regarding pathological assessment of lung cancer excision specimens after neoadjuvant therapy[ 17 ], all pathologic information were independently performed by two pathologists, each with over 10 years of experience. MPR was defined as 0–10% of viable tumor cells remaining in the residual tumor. In cases of disagreement, discussions were held until a consensus was reached. CT image acquisition and ROI segmentation All patients underwent baseline CT scans within one month prior to NAIC treatment, with the following CT imaging using: Somatom Definition Flash (Siemens, Germany), uCT780 (United Imaging, Shanghai, China), Somatom Perspective 128 (Siemens, Germany), and Somatom Definition Force (Siemens, Germany). Scanning parameters were standardized as follows: 120 kVp, 100–200 mAs, and a pitch of 0.75–1.5. CT images were acquired with patients in the supine position at full inspiration. Iodine contrast agent agent (e.g., Omnipaque, 300mgI/ml, GE Healthcare) was administered by power injector at a flow rate of 3.0 to 3.5 mL/s and the contrasted images were acquired after the injection of iodine contrast agent at 30–40 second. No adverse reactions occurred after the injection of contrast agent in all patients. Then, contrasted-enhanced CT images were retained in DICOM format and resampled to a uniform resolution of 1 × 1 × 1 mm to mitigate the impact of variations in acquisition equipment. Region of interest (ROI) was manually segmented slice by slice using 3D Slicer software[ 18 ] (version 5.6.2, Brigham and Women’s Hospital) by one junior radiologists with over 10 years of experience. A senior radiologist then reviewed the segmented ROIs and made necessary adjustments. Image dilation expanded the tumor areas to generate outer peritumor areas, while image erosion shrank the tumor areas to yield inner peritumor areas. The tumor margin region was generated by the “ROI operation” module of the RIAS software[ 19 ]. Annular 6 mm (defined as the tumor margin region) wide areas at a radial distance of − 3 mm (inside) to 3 mm (outside) from the edge of the segmented region were created finally. Feature extraction and selection Radiomic features were extracted from the whole tumor region and tumor margin region using the open-source PyRadiomics package in Python[ 20 ]. To evaluate robustness, 50 cases were randomly selected for intraclass correlation coefficient (ICC) analysis, with an ICC ≥ 0.75 indicating satisfactory reproducibility. The Minimum Redundancy Maximum Relevance algorithm was employed to select the top 20 most valuable features. Following this, Least Absolute Shrinkage and Selection Operator (LASSO) regression was applied using a tenfold cross-validation to retain the most important features. A radiomics score (Rad-score) for each patient was then calculated by taking a linear combination of the selected features, weighted according to their respective coefficients. Model construction and comparison The dataset was randomly split into training and internal validation sets at a 7:3 ratio. Three models were constructed: the Whole Tumor Model (WTM), based on radiomic features extracted from the whole tumor region; the Tumor Margin Model (TMM), based on radiomic features derived from the tumor margin region; and the Clinical model (CM). The hybrid model (HM) was developed by integrating the optimized radiomics signature with clinically predictors to enhance predictive performance. Model performance was subsequently evaluated by plotting receiver operating characteristic (ROC) curves and calculating the corresponding area under the receiver operating characteristic curve (AUC). Nomogram Development and Evaluation Clinically significant predictors were combined with the Rad-Score in a multivariate logistic regression model. The resulting model coefficients were then used to build the nomogram. A calibration curve displayed the agreement between actual clinical outcomes and model predictions. The AUC was used to measure the discrimination performance. Decision curves analysis (DCA) was used to evaluate and compare the net benefit of the constructed models. Statistical Analysis All statistical analysis was conducted with R software (version 4.1.0, Vienna, Austria). Continuous variables were presented as mean ± standard deviation, and categorical variables as frequency (percentage). Univariate and multivariate logistic regression analyses were conducted to identify risk factors, with odds ratios and 95% confidence intervals provided. The model's performance was evaluated using AUC, accuracy (ACC), sensitivity, specificity, positive predictive value, and negative predictive value. The DeLong test was used to assess the statistical significance of differences between models. The "glmnet" package in R was used to perform LASSO logistic regression. The "rms" package was used for nomogram construction and calibration plotting. ROC plots were constructed using the "pROC" package. The "rmda" package was used to construct the DCA curve plots. The "rms" package in R was used to calibrate the radiomic signature using the calibration curve. Statistical significance was accepted at P < 0.05. Results Patient Characteristics A total of 169 patients were divided into training set (n = 93), internal validation set (n = 39) and external test set (n = 37). Table 1 presents the characteristics across different cohorts. The overall cohort had a mean age of 60 years, with 91.1% (n = 154) being male. Histologically, 130 patients (76.9%) had squamous cell carcinoma, while 39 (23.1%) had adenocarcinoma. Most patients were staged as clinical stage T2 (n = 72, 42.6%) and clinical stage N2 (n = 90, 53.3%), with clinical stage III (n = 126, 74.6%) being the most common. Pathologic response assessment showed that 61.5% (n = 104) achieved MPR. The primary immune checkpoint inhibitors administered across the two centers included tislelizumab (30.2%), pembrolizumab (27.8%), sintilimab (13.6%), and toripalimab (13.0%). No statistically significant differences in the neoadjuvant treatment regimens were observed between the MPR and non-MPR groups across all three cohorts. After conducting univariable and multivariable logistic regression analyses, pathology was confirmed as an independent risk factor and subsequently included in the CM (p = 0.006; OR = 4.26, 95% CI: 1.52,11.98) (Table 2 ). Table 1 Clinical characteristics of the entire dataset. Clinical factors Train set (n = 93) Internal validation set (n = 39) External test set (n = 37) Total MPR (n = 56) NMPR (n = 37) p-value MPR (n = 24) NMPR (n = 15) p-value MPR (n = 24) NMPR (n = 13) p-value Gender 1.00 *0.02 1.00 Male 53 (94.6) 35 (94.6) 23 (95.8) 9 (60.0) 22 (91.7) 12 (92.3) 154 (91.1) Female 3 (5.4) 2 (5.4) 1 (4.2) 6 (40.0) 2 (8.3) 1 (7.7) 15 (8.9) Age (mean ± SD) 59.5 (6.6) 61.7 (7.1) 0.13 61.4 (6) 55.8 (8.2) *0.01 59.8 (7.7) 62.7 (6.3) 0.24 Age group 0.39 0.21 0.35 < 65 41 (73.2) 24 (64.9) 15 (62.5) 13 (86.7) 18 (75.0) 7 (53.8) 118 (69.8) ≥ 65 15 (26.8) 13 (35.1) 9 (37.5) 2 (13.3) 6 (25.0) 6 (46.2) 51 (30.2) Smoking history 0.26 *0.02 0.57 Yes 45 (80.4) 26 (70.3) 21 (87.5) 7 (46.7) 23 (95.8) 11 (84.6) 133 (78.7) No 11 (19.6) 11 (29.7) 3 (12.5) 8 (53.3) 1 (4.2) 2 (15.4) 36 (21.3) Lung lobe 0.64 0.13 0.96 Right 29 (51.8) 21 (56.8) 10 (41.7) 10 (66.7) 15 (62.5) 9 (69.2) 93 (55.0) Left 27 (48.2) 16 (43.2) 14 (58.3) 5 (33.3) 9 (37.5) 4 (30.8) 76 (45.0) Clinical T Stage 0.65 0.09 0.19 1 3 (5.4) 3 (8.1) 2 (8.3) 0 (0.0) 1 2 11 (6.5) 2 25 (44.6) 15 (40.5) 12 (50.0) 4 (26.7) 10 6 72 (42.6) 3 15 (26.8) 7 (18.9) 4 (16.7) 8 (53.3) 9 5 48 (28.4) 4 13 (23.2) 12 (32.4) 6 (25.0) 3 (20.0) 4 0 38 (22.5) Clinical N Stage 0.35 0.16 0.73 0 6 (10.7) 9 (24.3) 1 (4.2) 3 (20.0) 1 0 20 (11.8) 1 15 (26.8) 7 (18.9) 7 (29.2) 1 (6.7) 10 5 45 (26.6) 2 31 (55.4) 19 (51.4) 11 (45.8) 9 (60.0) 12 8 90 (53.3) 3 4 (7.1) 2 (5.4) 5 (20.8) 2 (13.3) 1 0 14 (8.3) Clinical Stage 0.84 0.51 1.00 II 7 (12.5) 6 (16.2) 2 (8.3) 0 (0.0) 18 10 43 (25.4) III 49 (87.5) 31 (83.8) 22 (91.7) 15 (100.0) 6 3 126 (74.6) Pathology *0.004 0.42 0.28 Squamous carcinoma 49 (87.5) 23 (62.2) 20 (83.3) 10 (66.7) 20 (83.3) 8 (61.5) 130 (76.9) Adenocarcinoma 7 (12.5) 14 (37.8) 4 (16.7) 5 (33.3) 4 (16.7) 5 (38.5) 39 (23.1) NAIC cycle 0.22 0.86 0.24 2 13 (23.2) 6 (16.2) 5 (20.8) 4 (26.7) 6 (25.0) 6 (46.2) 40 (23.7) 3 22 (39.3) 10 (27.0) 11 (45.8) 5 (33.3) 15 (62.5) 7 (53.8) 70 (41.4) 4 21 (37.5) 20 (54.1) 6 (25.0) 5 (33.3) 3 (12.5) 0 (0.0) 55 (32.5) 5 0 (0.0) 1 (2.7) 2 (8.3) 1 (6.7) 0 0 4 (2.4) Immunotherapy agent 0.51 0.38 0.60 Tislelizumab 23 (41.1) 12 (32.4) 7 (29.2) 6 (40.0) 1 (4.2) 2 (15.4) 51 (30.2) Pembrolizumab 21 (37.5) 12 (32.4) 7 (29.2) 7 (46.7) 0 0 47 (27.8) Sintilimab 7 (12.5) 5 (13.5) 6 (25.0) 2 (13.3) 2 (8.3) 1 (7.7) 23 (13.6) Toripalimab 3 (5.4) 4 (10.8) 3 (12.5) 0 (0.0) 9 (37.5) 3 (23.1) 22 (13.0) Other 2 (3.6) 4 (10.8) 1 (4.2) 0 (0.0) 12 (50.0) 7 (53.8) 26 (15.4) PD-L1_1 0.50 1.00 1.00 ≤ 50% 9 (16.1) 8 (21.6) 22 (91.7) 13 (86.7) 23 (95.8) 13 (100.0) 125 (74.0) >50% 47 (83.9) 29 (78.4) 2 (8.3) 2 (13.3) 1 (4.2) 0 (0.0) 44 (26.0) PD-L1_2 0.95 0.88 1.00 ≤ 1% 39 (69.6) 26 (70.3) 15 (62.5) 9 (60.0) 23 (95.8) 13 (100.0) 125 (74.0) >1% 17 (30.4) 11 (29.7) 9 (37.5) 6 (40.0) 1 (4.2) 0 (0.0) 44 (26.0) Ki 67 0.35 0.59 0.78 >40% 16 (28.6) 14 (37.8) 8 (33.3) 3 (20.0) 16 (66.7) 10 (76.9) 67 (39.6) ≤ 40% 40 (71.4) 23 (62.2) 16 (66.7) 12 (80.0) 8 (33.3) 3 (23.1) 102 (60.4) NLR 0.58 0.72 0.37 ≤ 2.75 24 (42.9) 18 (48.6) 11 (45.8) 6 (40.0) 11 (45.8) 4 (30.8) 74 (43.8) >2.75 32 (57.1) 19 (51.4) 13 (54.2) 9 (60.0) 13 (54.2) 9 (69.2) 95 (56.2) Data in parentheses are percentages; MPR, major pathological response; NMPR, non-MPR; NAIC, neoadjuvant immunochemotherapy; PD-L1, Programmed Death-Ligand 1; NLR, neutrophil to lymphocyte ratioNLR, neutrophil to lymphocyte ratio. *p < 0.05 Table 2 Univariate and multivariate analysis of clinical data in the training set. Variable Univariate analysis Multivariate analysis OR (95%CI) P-value OR (95%CI) P-value Gender 1.01 (0.16, 6.35) 0.99 Age 1.05 (0.99, 1.12) 0.13 Age group 1.48 (0.60, 3.63) 0.39 Smoking history 0.58(0.22, 1.52) 0.27 Lung lobe 1.22 (0.53, 2.82) 0.64 Clinical T Stage 1.09 (0.70, 1.71) 0.69 Clinical N Stage 0.74 (0.45, 1.22) 0.24 Clinical Stage 0.74 (0.23, 2.40) 0.61 Pathology 4.26 (1.52, 11.98) *0.01 4.26 (1.52,11.98) *0.006 NAIC cycle 1.62 (0.93, 2.81) 0.09 Immunotherapy agent 1.36 (0.95, 1.94) 0.09 PD-L1_1 0.69 (0.24, 2.00) 0.50 PD-L1_2 0.97 (0.39, 2.40) 0.95 Ki-67 0.66 (0.27, 1.59) 0.35 NLR 0.79 (0.34, 1.82) 0.58 OR, odds ratio; CI, confidence interval; NAIC, neoadjuvant immunochemotherapy; NAIC, neoadjuvant immunochemotherapy; PD-L1, Programmed Death-Ligand 1; NLR, neutrophil to lymphocyte ratio. *p < 0.05 Development of the Radiomics Signature A total of 1410 radiomics features were extracted from two regions using Pyradiomics, of which 1340 (95.03%) features were retained after ICC analysis. After Z-score normalization, all extracted features underwent reproducibility assessment using ICC analysis, and 1,340 features with ICC ≥ 0.75 were retained. The retained features consisted of 258 first-order features describing voxel intensity distributions, 14 shape features quantifying tumor geometry, and 1,068 texture features characterizing spatial relationships and heterogeneity patterns. The texture category was further divided into 334 gray level co-occurrence matrix features, 233 gray level run length matrix features, 226 gray level size zone matrix features, 205 gray level dependence matrix features, and 70 neighboring gray tone difference matrix features. These features were derived from multiple image transformation filters, including original, wavelet, logarithm, square, exponential, square root, and local binary pattern, to enhance specific signal properties and capture multi-scale information. To reduce dimensionality and avoid overfitting, the LASSO regression method was applied to the extracted radiomic features (Figure S1 -2). As a result, 10 features from the tumor margin region and 6 features from the whole tumor region were retained as the most predictive for constructing the TMM and WTM models, respectively (Fig. 3 A, 3 B). The Wilcoxon rank-sum test showed that the Rad-scores derived from above two region features differed significantly between MPR and NMPR patients in both cohorts (p < 0.05) (Fig. 3 C, 3 D). Performance Comparison of Model The evaluation performance of the three model was assessed using ROC curves (Fig. 4 ). The CM exhibited limited predictive performance, with AUCs of 0.63 (95% CI: 0.54–0.72), 0.58 (95% CI: 0.44–0.73) and 0.61 (95% CI: 0.45–0.77) in the training and internal validation sets, respectively. The TMM achieved AUCs of 0.84 (95% CI: 0.76–0.92) and 0.84 (95% CI: 0.71–0.97) in the respective datasets, exceeding the WTM (AUC = 0.74 [95% CI: 0.64–0.85] in training set, 0.71 [95% CI: 0.54–0.89] in the internal validation set (Fig. 4 A, 4 B). The HM, integrating tumor margin radiomic features with clinicopathological data, further improved predictive performance, achieving AUCs of 0.88 (95% CI: 0.81–0.95) and 0.86 (95% CI: 0.74–0.98) in the training and internal validation sets, respectively. The HM achieved the highest ACC of 0.79 (95% CI: 0.64–0.91), surpassing the CM (ACC = 0.64, 95% CI: 0.47–0.79), TMM (ACC = 0.62, 95% CI: 0.45–0.77) and WTM (ACC = 0.69, 95% CI: 0.52–0.83) in the internal validation set. Additional diagnostic metrics are summarized in Table 3 . Table 3 Model predictive performance. Training set Internal validation set External test set Model ACC (95% CI) SEN SPE PPV NPV ACC (95% CI) SEN SPE PPV NPV ACC (95% CI) SEN SPE PPV NPV TMM 0.71 (0.61–0.80) 1.00 0.52 0.58 1.00 0.62 (0.45–0.77) 0.87 0.46 0.50 0.85 0.76 (0.59–0.88) 0.38 0.96 0.83 0.74 WTM 0.74 (0.64–0.83) 0.70 0.77 0.67 0.80 0.69 (0.52–0.83) 0.47 0.83 0.64 0.71 0.73 (0.56–0.86) 0.23 1.00 1.00 0.71 CM 0.68 (0.57–0.77) 0.38 0.88 0.678 0.68 0.64 (0.47–0.79) 0.33 0.83 0.56 0.67 0.68 (0.50–0.82)- 0.38 0.83 0.56 0.72 HM 0.83 (0.74–0.90) 0.76 0.88 0.80 0.84 0.79 (0.64–0.91) 0.67 0.88 0.77 0.81 0.76 (0.59–0.88) 0.31 1.00 1.00 0.73 ACC, Accuracy; CI, Confidence Interval; TMM, Tumor Margin Model; WTM, Whole Tumor Model; CM, Clinical Model; HM, Hybrid Model; SPE, Specificity; SEN, Sensitivity; PPV, Positive Predictive Value; NPV, Negative Predictive Value. In the external test set, the HM maintained favorable performance (AUC 0.87; 95% CI, 0.76–0.98) (Fig. 4 C), supporting its potential utility for preoperative risk stratification and patient selection. Nomogram Construction and Clinical Utility Assessment The variables included in the HM are presented as a nomogram to allow clinicians to intuitively and conveniently assess the likelihood of MPR using patient-specific information (Fig. 5 A). Each factor was assigned a weighted point value. Using the nomogram, these points were summed for each patient to yield a total score, which was then translated into an estimated probability of MPR. The calibration curves also indicated minimal overall deviation between the model-predicted and expected probabilities (Fig. 5 B). DCA showed that nomogram provided a larger net benefit across the range of reasonable threshold probabilities compared with the other models (Fig. 5 C). Discussion NAIC has revolutionized the treatment paradigm for NSCLC by reducing tumor burden prior to surgical resection, thereby decreasing the risk of recurrence[ 21 ]. However, a considerable proportion of NSCLC patients fail to achieve MPR after NAIC, identifying patients most likely to benefit from this advanced therapy is of considerable clinical significance. In the present study, a HM was developed to predict MPR in NSCLC following NAIC, achieving AUC of 0.88 in the training set and 0.86 in the internal validation set. Additionally, the DCA confirmed that HM provided the greatest clinical benefit. Finally, a nomogram based on HM was developed to assist clinicians in better assessing the likelihood of achieving MPR in NSCLC patients. Consistent with previous studies, pathology was identified as a clinical variable closely associated with MPR prediction in NSCLC patients[ 22 , 23 ]. MPR is more likely in patients with lung squamous cell carcinoma compared to those with non-squamous carcinoma, which may be attributable to higher PD-L1 expression, TMB, and functional tumor-infiltrating lymphocyte density in the tumor microenvironment of squamous cell carcinoma[ 24 ]. CT has been a standard imaging modality in clinical practice for evaluating treatment response in lung cancer. Due to immune cell infiltration, relying solely on conventional CT characteristics is insufficient for accurately predicting treatment response[ 25 ]. Radiomics enables the extraction of a vast array of imaging features from multimodal medical images and has played an increasingly pivotal role in lung cancer, encompassing screening, treatment decision-making, and survival prediction[ 26 ]. Liu et al.[ 23 ] were the first to develop a radiomics model integrating clinical features, achieving an AUC of 0.81 in the test set for MPR prediction in NSCLC patients who underwent NAIC. Han et al.[ 27 ] extracted radiomic features from pre- and post-treatment contrast-enhanced CT images to quantify feature changes, resulting in an AUC of 0.732 in the testing cohort. She et al.[ 28 ] utilized deep learning-derived features to construct a predictive model for MPR, yielding an AUC of 0.75 in an external test cohort. Recent studies have also demonstrated that peritumoral microenvironment can predict the response to NAIC. These studies have generally assumed tumor homogeneity, using features from the entire tumor or including the peritumoral area without addressing its heterogeneity. Indeed, increasing evidence suggests that the tumor stroma interface is where immune microenvironment alterations and metabolic changes in tumor cells are most pronounced. The tumor margin areas, where tumor cells invade surrounding tissues and interact with other cells, are the most active regions for cell infiltration and invasion[ 14 , 16 ]. Recently, Wu et al.[ 29 ] identified a region within 250 µm on both sides of the tumor border in patients with liver cancer. The zone is characterized by an immunosuppressive microenvironment, metabolic reprogramming of tumor cells, and significant damaged hepatocytes, all of which influence the risk of tumor invasion and patient prognosis. Similarly, in colorectal cancer, spatial transcriptomic analyses revealed that immune cell organization within a 300 µm tumor stroma boundary was highly predictive of response to immune checkpoint blockade[ 30 ]. These studies provide compelling biological justification for analyzing tumor margins as distinct and informative regions. Analogous findings have been reported in neuro-oncology. The interface between the brain parenchyma and the tumor, known as the brain-to-tumor interface (BTI), is recognized as the key region where brain tumors interact with intracranial cells and the immune system[ 31 ]. Previous studies have demonstrated that the BTI is critically associated with brain invasion status[ 32 , 33 ], tumor grading[ 34 ], and the differentiation of metastatic tumor types[ 35 ]. However, in NSCLC, prior studies have predominantly examined intratumoral region, whereas the significance of tumor margin region remains underexplored. Given that immune checkpoint inhibitors exert antitumor effects by modulating the tumor and peritumoral immune microenvironment[ 36 ], we investigated the potential of tumor margin characteristics in predicting the response to NAIC in NSCLC patients. While peritumoral regions in lung cancer research are commonly extended in 3 mm increments, there is no standardized definition for the optimal tumor margin. A margin that is too narrow (e.g., 1–2 mm) may fail to capture key edge features, whereas an overly wide margin (e.g., ≥ 10 mm) may introduce substantial normal tissue and background noise, diluting critical biological signals. To balance these factors, we defined the − 3 ~ + 3 mm region as the tumor margin, aiming to capture essential peritumoral information while minimizing extraneous interference. Notably, our HM yielded AUCs of 0.86 (internal validation) and 0.87 (external test), surpassing the performance of previously reported models—such as Ye et al.[ 37 ] (AUC = 0.78, habitat model) and Wang et al.[ 38 ] (AUC = 0.80, radiomics-clinical combined model). These findings support the hypothesis that explicitly modeling the tumor-lung interface may provide complementary and clinically meaningful information for NAIC response prediction. This finding aligns with prior research by Hu et al.[ 39 ], who divided tumors into marginal (S1) and internal (S2) subregions and found that features from S1 consistently outperformed those from S2 or the entire tumor in predicting response to anti-PD1 therapy. Notably, this margin-dominant predictive pattern has been validated across multiple cancer types and imaging modalities, including MRI-based cervical cancer radiomics[ 40 ] and PET/CT-driven nasopharyngeal carcinoma studies[ 41 ]. The enhanced performance of TMM may be attributed to its ability to capture critical tumor-host interactions[ 42 , 43 ], such as immune infiltration, angiogenesis, and invasive behavior, which are strongly associated with response to NAIC. In contrast, the whole tumor features may include both active and less informative areas (e.g., necrotic or hypoxic regions), potentially diluting predictive signals. This study has several limitations. First, the overall sample size is relatively small, which may constrain the generalizability of the findings. Although we have added an independent external test cohort to enhance validation, future prospective studies with larger and more diverse populations across multiple centers are warranted to confirm model robustness. Second, the proportion of female patients in our cohort is limited, which may reduce the precision of subgroup estimates for women. This gender imbalance reflects real-world treatment patterns in thoracic oncology, where male patients are more frequently diagnosed with smoking-related NSCLC, but nonetheless warrants caution when extrapolating the model’s performance to female populations. Future work should aim to recruit more gender-balanced cohorts to ensure broader applicability. Third, the biological underpinnings of tumor margin region characteristics in NSCLC remain to be directly validated. Future studies integrating imaging, pathology, and spatial transcriptomics will be essential to better understand the mechanistic basis of the radiomic signal captured at the tumor margin. Finally, due to the short follow-up period, we have not yet investigated the predictive value of tumor margin characteristics for survival outcomes. Therefore, further studies incorporating survival as the primary endpoint are necessary to comprehensively evaluate the prognostic value of the tumor marginal region. In conclusion, this study proposes a novel tumor margin radiomics approach to predict NAIC response in resectable NSCLC. By facilitating more precise clinical decision-making, the HM holds the potential to minimize overtreatment and optimize personalized therapeutic strategies for resectable NSCLC. Abbreviations NAIC, Neoadjuvant immunochemotherapy NSCLC, Non-small cell lung cancer WTM, Whole Tumor Model TMM, Tumor Margin model CM, Clinical model HM, Hybrid model MPR, Major pathological response AUC, Area under the receiver operating characteristic curve ROC, Receiver operating characteristic TMB, Tumor mutational burden ROI, Region of interest ICC, Intraclass correlation coefficient LASSO, Least Absolute Shrinkage and Selection Operator Rad-score, Radiomics score DCA, Decision curves analysis ACC, Accuracy Declarations Ethics approval and consent to participate All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and the 1964 Helsinki Declaration and its later amendments or comparable ethical standards. This study was approved by an Institutional Review Board approval from the Second Xiangya Hospital of Central South University prior to the commencement of this study (retrospective study approval 2023 − 121), and informed consent was waived because of the study design. Consent for publication Not applicable. Competing Interests The authors declare no competing interests Funding The study was supported by National Natural Science Foundation of China (62476291), Hunan Provincial Natural Science Foundation for Distinguished Young Scholars (2025JJ20097), Hunan Provincial Natural Science Foundation (2022JJ70139), the Research Foundation of Education Bureau of Hunan Province (24B0003), the Fundamental Research Funds for the central Universities of Central South University (2025ZZTS0873). Author Contribution Yisong Wang and Wei Zhao designed the study. Xiaohuang Yang, Feiping Li, Xiaoping Yu and Wei Han extracted, collected and analyzed data. Youlan Shang, Xiangru Song prepared tables and figures. Yisong Wang and Xiaoying Li reviewed the results, interpreted data, and wrote the manuscript. Wei Zhao and Jun Liu have accessed and verified all the data in the study. All authors have made an intellectual contribution to the manuscript and approved the submission. Acknowledgements Not applicable. Data Availability The datasets used and/or analyzed during the current study available from the corresponding author on reasonable request. References Ettinger DS, Wood DE, Aisner DL, Akerley W, Bauman JR, Bharat A, et al. NCCN Guidelines® Insights: Non-Small Cell Lung Cancer, Version 2.2023. J Natl Compr Canc Netw. 2023;21:340–50. https://doi.org/10.6004/jnccn.2023.0020 . Siegel RL, Giaquinto AN, Jemal A, Cancer statistics. 2024. CA: A Cancer Journal for Clinicians. 2024;74:12–49. https://doi.org/10.3322/caac.21820 Miller M, Hanna N. Advances in systemic therapy for non-small cell lung cancer. BMJ. 2021;375:n2363. https://doi.org/10.1136/bmj.n2363 . Travis WD, Dacic S, Wistuba I, Sholl L, Adusumilli P, Bubendorf L, et al. IASLC Multidisciplinary Recommendations for Pathologic Assessment of Lung Cancer Resection Specimens After Neoadjuvant Therapy. J Thorac Oncol. 2020;15:709–40. https://doi.org/10.1016/j.jtho.2020.01.005 . Provencio M, Nadal E, Insa A, García-Campelo MR, Casal-Rubio J, Dómine M, et al. Neoadjuvant chemotherapy and nivolumab in resectable non-small-cell lung cancer (NADIM): an open-label, multicentre, single-arm, phase 2 trial. Lancet Oncol. 2020;21:1413–22. https://doi.org/10.1016/S1470-2045(20)30453-8 . Forde PM, Spicer J, Lu S, Provencio M, Mitsudomi T, Awad MM, et al. Neoadjuvant Nivolumab plus Chemotherapy in Resectable Lung Cancer. N Engl J Med. 2022;386:1973–85. https://doi.org/10.1056/NEJMoa2202170 . Kluger HM, Zito CR, Turcu G, Baine MK, Zhang H, Adeniran A, et al. PD-L1 Studies Across Tumor Types, Its Differential Expression and Predictive Value in Patients Treated with Immune Checkpoint Inhibitors. Clin Cancer Res. 2017;23:4270–9. https://doi.org/10.1158/1078-0432.CCR-16-3146 . Shi W-J, Zhao W. Biomarkers or factors for predicting the efficacy and adverse effects of immune checkpoint inhibitors in lung cancer: achievements and prospective. Chin Med J (Engl). 2020;133:2466–75. https://doi.org/10.1097/CM9.0000000000001090 . Chen M, Copley SJ, Viola P, Lu H, Aboagye EO. Radiomics and artificial intelligence for precision medicine in lung cancer treatment. Semin Cancer Biol. 2023;93:97–113. https://doi.org/10.1016/j.semcancer.2023.05.004 . Tunali I, Gillies RJ, Schabath MB. Application of Radiomics and Artificial Intelligence for Lung Cancer Precision Medicine. Cold Spring Harb Perspect Med. 2021;11:a039537. https://doi.org/10.1101/cshperspect.a039537 . Xu H, Lv W, Feng H, Du D, Yuan Q, Wang Q, et al. Subregional Radiomics Analysis of PET/CT Imaging with Intratumor Partitioning: Application to Prognosis for Nasopharyngeal Carcinoma. Mol Imaging Biol. 2020;22:1414–26. https://doi.org/10.1007/s11307-019-01439-x . O’Connor JPB, Rose CJ, Waterton JC, Carano RAD, Parker GJM, Jackson A. Imaging intratumor heterogeneity: role in therapy response, resistance, and clinical outcome. Clin Cancer Res. 2015;21:249–57. https://doi.org/10.1158/1078-0432.CCR-14-0990 . Wu J, Gensheimer MF, Dong X, Rubin DL, Napel S, Diehn M, et al. Robust Intratumor Partitioning to Identify High-Risk Subregions in Lung Cancer: A Pilot Study. Int J Radiat Oncol Biol Phys. 2016;95:1504–12. https://doi.org/10.1016/j.ijrobp.2016.03.018 . Schürch CM, Bhate SS, Barlow GL, Phillips DJ, Noti L, Zlobec I, et al. Coordinated Cellular Neighborhoods Orchestrate Antitumoral Immunity at the Colorectal Cancer Invasive Front. Cell. 2020;182:1341–e135919. https://doi.org/10.1016/j.cell.2020.07.005 . Ji AL, Rubin AJ, Thrane K, Jiang S, Reynolds DL, Meyers RM, et al. Multimodal Analysis of Composition and Spatial Architecture in Human Squamous Cell Carcinoma. Cell. 2020;182:497–e51422. https://doi.org/10.1016/j.cell.2020.05.039 . Zheng L, Qin S, Si W, Wang A, Xing B, Gao R, et al. Pan-cancer single-cell landscape of tumor-infiltrating T cells. Science. 2021;374:abe6474. https://doi.org/10.1126/science.abe6474 . Travis WD, Dacic S, Wistuba I, Sholl L, Adusumilli P, Bubendorf L, et al. IASLC Multidisciplinary Recommendations for Pathologic Assessment of Lung Cancer Resection Specimens After Neoadjuvant Therapy. J Thorac Oncol. 2020;15:709–40. https://doi.org/10.1016/j.jtho.2020.01.005 . Fedorov A, Beichel R, Kalpathy-Cramer J, Finet J, Fillion-Robin J-C, Pujol S, et al. 3D Slicer as an image computing platform for the Quantitative Imaging Network. Magn Reson Imaging. 2012;30:1323–41. https://doi.org/10.1016/j.mri.2012.05.001 . Li M, Li X, Guo Y, Miao Z, Liu X, Guo S, et al. Development and assessment of an individualized nomogram to predict colorectal cancer liver metastases. Quant Imaging Med Surg. 2020;10:397–414. https://doi.org/10.21037/qims.2019.12.16 . van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, et al. Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res. 2017;77:e104–7. https://doi.org/10.1158/0008-5472.CAN-17-0339 . Lahiri A, Maji A, Potdar PD, Singh N, Parikh P, Bisht B, et al. Lung cancer immunotherapy: progress, pitfalls, and promises. Mol Cancer. 2023;22:40. https://doi.org/10.1186/s12943-023-01740-y . Li F, Zhai S, Lv Z, Yuan L, Wang S, Jin D, et al. Effect of histology on the efficacy of immune checkpoint inhibitors in advanced non-small cell lung cancer: A systematic review and meta-analysis. Front Oncol. 2022;12:968517. https://doi.org/10.3389/fonc.2022.968517 . Liu C, Zhao W, Xie J, Lin H, Hu X, Li C, et al. Development and validation of a radiomics-based nomogram for predicting a major pathological response to neoadjuvant immunochemotherapy for patients with potentially resectable non-small cell lung cancer. Front Immunol. 2023;14:1115291. https://doi.org/10.3389/fimmu.2023.1115291 . Tian Y, Zhai X, Yan W, Zhu H, Yu J. Clinical outcomes of immune checkpoint blockades and the underlying immune escape mechanisms in squamous and adenocarcinoma NSCLC. Cancer Med. 2021;10:3–14. https://doi.org/10.1002/cam4.3590 . Chiou VL, Burotto M. Pseudoprogression and Immune-Related Response in Solid Tumors. J Clin Oncol. 2015;33:3541–3. https://doi.org/10.1200/JCO.2015.61.6870 . Huang S, Yang J, Shen N, Xu Q, Zhao Q. Artificial intelligence in lung cancer diagnosis and prognosis: Current application and future perspective. Semin Cancer Biol. 2023;89:30–7. https://doi.org/10.1016/j.semcancer.2023.01.006 . Han X, Wang M, Zheng Y, Wang N, Wu Y, Ding C, et al. Delta-radiomics features for predicting the major pathological response to neoadjuvant chemoimmunotherapy in non-small cell lung cancer. Eur Radiol. 2024;34:2716–26. https://doi.org/10.1007/s00330-023-10241-x . She Y, He B, Wang F, Zhong Y, Wang T, Liu Z, et al. Deep learning for predicting major pathological response to neoadjuvant chemoimmunotherapy in non-small cell lung cancer: A multicentre study. EBioMedicine. 2022;86:104364. https://doi.org/10.1016/j.ebiom.2022.104364 . Wu L, Yan J, Bai Y, Chen F, Zou X, Xu J, et al. An invasive zone in human liver cancer identified by Stereo-seq promotes hepatocyte-tumor cell crosstalk, local immunosuppression and tumor progression. Cell Res. 2023;33:585–603. https://doi.org/10.1038/s41422-023-00831-1 . Feng Y, Ma W, Zang Y, Guo Y, Li Y, Zhang Y, et al. Spatially organized tumor-stroma boundary determines the efficacy of immunotherapy in colorectal cancer patients. Nat Commun. 2024;15:10259. https://doi.org/10.1038/s41467-024-54710-3 . Berghoff AS, Rajky O, Winkler F, Bartsch R, Furtner J, Hainfellner JA, et al. Invasion patterns in brain metastases of solid cancers. Neuro Oncol. 2013;15:1664–72. https://doi.org/10.1093/neuonc/not112 . Joo L, Park JE, Park SY, Nam SJ, Kim Y-H, Kim JH, et al. Extensive peritumoral edema and brain-to-tumor interface MRI features enable prediction of brain invasion in meningioma: development and validation. Neuro Oncol. 2021;23:324–33. https://doi.org/10.1093/neuonc/noaa190 . Li N, Mo Y, Huang C, Han K, He M, Wang X, et al. A Clinical Semantic and Radiomics Nomogram for Predicting Brain Invasion in WHO Grade II Meningioma Based on Tumor and Tumor-to-Brain Interface Features. Front Oncol. 2021;11:752158. https://doi.org/10.3389/fonc.2021.752158 . Zhao Z, Nie C, Zhao L, Xiao D, Zheng J, Zhang H, et al. Multi-parametric MRI-based machine learning model for prediction of WHO grading in patients with meningiomas. Eur Radiol. 2024;34:2468–79. https://doi.org/10.1007/s00330-023-10252-8 . Jiang M, Sun Y, Yang C, Wang Z, Xie M, Wang Y, et al. Radiomics based on brain-to-tumor interface enables prediction of metastatic tumor type of brain metastasis: a proof-of-concept study. Radiol Med. 2024. https://doi.org/10.1007/s11547-024-01934-4 . Zhou F, Qiao M, Zhou C. The cutting-edge progress of immune-checkpoint blockade in lung cancer. Cell Mol Immunol. 2021;18:279–93. https://doi.org/10.1038/s41423-020-00577-5 . Ye G, Wu G, Zhang C, Wang M, Liu H, Song E, et al. CT-based quantification of intratumoral heterogeneity for predicting pathologic complete response to neoadjuvant immunochemotherapy in non-small cell lung cancer. Front Immunol. 2024;15:1414954. https://doi.org/10.3389/fimmu.2024.1414954 . Wang F, Yang H, Chen W, Ruan L, Jiang T, Cheng L, et al. A combined model using pre-treatment CT radiomics and clinicopathological features of non-small cell lung cancer to predict major pathological responses after neoadjuvant chemoimmunotherapy. Curr Probl Cancer. 2024;50:101098. https://doi.org/10.1016/j.currproblcancer.2024.101098 . Hu Y, Jiang T, Wang H, Song J, Yang Z, Wang Y, et al. Ct-based subregional radiomics using hand-crafted and deep learning features for prediction of therapeutic response to anti-PD1 therapy in NSCLC. Phys Med. 2024;117:103200. https://doi.org/10.1016/j.ejmp.2023.103200 . Cui L, Yu T, Kan Y, Dong Y, Luo Y, Jiang X. Multi-parametric MRI-based peritumoral radiomics on prediction of lymph-vascular space invasion in early-stage cervical cancer. Diagn Interv Radiol. 2022;28:312–21. https://doi.org/10.5152/dir.2022.20657 . Xu H, Lv W, Feng H, Du D, Yuan Q, Wang Q, et al. Subregional Radiomics Analysis of PET/CT Imaging with Intratumor Partitioning: Application to Prognosis for Nasopharyngeal Carcinoma. Mol Imaging Biol. 2020;22:1414–26. https://doi.org/10.1007/s11307-019-01439-x . Pietras K, Ostman A. Hallmarks of cancer: interactions with the tumor stroma. Exp Cell Res. 2010;316:1324–31. https://doi.org/10.1016/j.yexcr.2010.02.045 . Joyce JA, Pollard JW. Microenvironmental regulation of metastasis. Nat Rev Cancer. 2009;9:239–52. https://doi.org/10.1038/nrc2618 . Additional Declarations No competing interests reported. Supplementary Files Supplementalmaterials.docx Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 14 Oct, 2025 Reviewers agreed at journal 07 Oct, 2025 Reviewers invited by journal 29 Sep, 2025 Editor assigned by journal 23 Sep, 2025 Editor invited by journal 05 Sep, 2025 Submission checks completed at journal 05 Sep, 2025 First submitted to journal 05 Sep, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7531855","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":527071868,"identity":"407a9cfe-49fe-4725-9834-4d7591ba583d","order_by":0,"name":"Yisong Wang","email":"","orcid":"","institution":"The Second Xiangya Hospital of Central South University","correspondingAuthor":false,"prefix":"","firstName":"Yisong","middleName":"","lastName":"Wang","suffix":""},{"id":527071869,"identity":"4f570874-e769-4ae9-bc04-f26c8f5a6dbb","order_by":1,"name":"Xiaoying Li","email":"","orcid":"","institution":"The Second Xiangya Hospital of Central South University","correspondingAuthor":false,"prefix":"","firstName":"Xiaoying","middleName":"","lastName":"Li","suffix":""},{"id":527071870,"identity":"448da26e-8350-47fd-9c92-739a00fffa98","order_by":2,"name":"Youlan Shang","email":"","orcid":"","institution":"The Second Xiangya Hospital of Central South University","correspondingAuthor":false,"prefix":"","firstName":"Youlan","middleName":"","lastName":"Shang","suffix":""},{"id":527071871,"identity":"fb810c1e-4905-4207-8b78-f33982961b20","order_by":3,"name":"Xiangru Song","email":"","orcid":"","institution":"The Second Xiangya Hospital of Central South University","correspondingAuthor":false,"prefix":"","firstName":"Xiangru","middleName":"","lastName":"Song","suffix":""},{"id":527071872,"identity":"00baef88-c316-49d9-951c-cefdee17eb51","order_by":4,"name":"Xiaohuang Yang","email":"","orcid":"","institution":"The Affiliated Cancer Hospital of Xiangya School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Xiaohuang","middleName":"","lastName":"Yang","suffix":""},{"id":527071873,"identity":"7541842b-0eb5-40ed-ad65-22d41a196013","order_by":5,"name":"Feiping Li","email":"","orcid":"","institution":"The Affiliated Cancer Hospital of Xiangya School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Feiping","middleName":"","lastName":"Li","suffix":""},{"id":527071874,"identity":"6a50ed8f-2fb2-4230-9906-84afae0d8903","order_by":6,"name":"Xiaoping Yu","email":"","orcid":"","institution":"The Second Xiangya Hospital of Central South University","correspondingAuthor":false,"prefix":"","firstName":"Xiaoping","middleName":"","lastName":"Yu","suffix":""},{"id":527071875,"identity":"648de239-981f-4ad3-8350-62a9d57b4107","order_by":7,"name":"Wei Han","email":"","orcid":"","institution":"The Second Xiangya Hospital of Central South University","correspondingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"Han","suffix":""},{"id":527071876,"identity":"18bbebcf-f5b2-4f65-83b4-7db62b55c827","order_by":8,"name":"Wei Zhao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1ElEQVRIie3PsQrCMBCA4QtCuxRc08E+QyVQhIK+SoNDl+IsKHgixNHVxxAEcWwRzBL3bNKls6uLGBEcY90c8pPABfIFAuBy/WUEXwu671PnBxJie/JWEJdtSSxXSO7HYcSkbChMU47+pbQTVSGEaswSVSQUVM4xmGRWkmiO0BcdftCBR4k4caRBbCfXGoGLBd9v/YaSRxuizd8r8/iOQkIJtiAjxbFaCsmoKtggO+dMBIWdhGtZ13cxi7pm0Ld52tv4yk5elZ8pM9v7et/lcrlcX3sCbqxE8B/ZJ1wAAAAASUVORK5CYII=","orcid":"","institution":"The Second Xiangya Hospital of Central South University","correspondingAuthor":true,"prefix":"","firstName":"Wei","middleName":"","lastName":"Zhao","suffix":""},{"id":527071877,"identity":"daf4f646-6baf-4e4f-9529-be3444d3af9f","order_by":9,"name":"Jun Liu","email":"","orcid":"","institution":"The Second Xiangya Hospital of Central South University","correspondingAuthor":false,"prefix":"","firstName":"Jun","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2025-09-04 04:08:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7531855/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7531855/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93337473,"identity":"655287c8-642a-4a34-9ade-e8fb7e0763fe","added_by":"auto","created_at":"2025-10-12 14:09:08","extension":"jpg","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":56332,"visible":true,"origin":"","legend":"","description":"","filename":"Figure1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/1cfd7f60a12e0e13945f264d.jpg"},{"id":93337482,"identity":"7329e903-6a78-4aa7-b385-59b7c7fc7327","added_by":"auto","created_at":"2025-10-12 14:09:08","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":92718,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/0f6abbeed8bd8dae450a3926.docx"},{"id":93338113,"identity":"846e15a8-4a1c-45b2-b0e5-0f7d7e6b1bc0","added_by":"auto","created_at":"2025-10-12 14:17:08","extension":"jpg","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":156755,"visible":true,"origin":"","legend":"","description":"","filename":"Figure2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/246689a29e15a00288a0d205.jpg"},{"id":93338118,"identity":"6f2b10f8-b1b5-4985-8784-3530e9e7348b","added_by":"auto","created_at":"2025-10-12 14:17:08","extension":"docx","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":46147,"visible":true,"origin":"","legend":"","description":"","filename":"Tables.docx","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/7d1e868fd0cfbb89b7c909c4.docx"},{"id":93338115,"identity":"69821eb1-f3b1-4853-8927-d8a91041ce74","added_by":"auto","created_at":"2025-10-12 14:17:08","extension":"jpg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":256160,"visible":true,"origin":"","legend":"","description":"","filename":"Figure3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/7bced40057fda07eae91e6fc.jpg"},{"id":93337492,"identity":"c05c2cfc-05cf-4895-831d-4e9319923329","added_by":"auto","created_at":"2025-10-12 14:09:08","extension":"jpg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2180196,"visible":true,"origin":"","legend":"","description":"","filename":"Figure4.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/1770283c5a34b9dcaae6b5cb.jpg"},{"id":93337487,"identity":"6cc07889-1f82-4f4d-9791-0b90eb8046e7","added_by":"auto","created_at":"2025-10-12 14:09:08","extension":"jpg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":206558,"visible":true,"origin":"","legend":"","description":"","filename":"Figure5.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/3734a891a7f6c31281f997a1.jpg"},{"id":93337491,"identity":"e2bc1029-2ffd-4b94-bf77-d09f149b1e21","added_by":"auto","created_at":"2025-10-12 14:09:08","extension":"json","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11287,"visible":true,"origin":"","legend":"","description":"","filename":"c68626d16c3c4155a5a8294064b4eea2.json","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/b70eca2ddf04e4ef11d5a141.json"},{"id":93337494,"identity":"507e48b4-2a95-4421-9789-0a05f566766e","added_by":"auto","created_at":"2025-10-12 14:09:08","extension":"docx","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":296351,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementalmaterials.docx","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/f9bc7e931a645d288fc10af0.docx"},{"id":93339230,"identity":"2020f4b6-2292-4699-a226-4b7c98d70f44","added_by":"auto","created_at":"2025-10-12 14:25:08","extension":"xml","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":176250,"visible":true,"origin":"","legend":"","description":"","filename":"c68626d16c3c4155a5a8294064b4eea21enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/55bf1c9c4153b8ee1ae48c7b.xml"},{"id":93337496,"identity":"ba229e35-c5c0-4db8-a931-603fd150489f","added_by":"auto","created_at":"2025-10-12 14:09:08","extension":"jpg","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":56332,"visible":true,"origin":"","legend":"","description":"","filename":"Figure1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/2c8e8db6d2091481028075a8.jpg"},{"id":93337486,"identity":"b2985312-b072-4cdb-9e2d-b044e96d5ce2","added_by":"auto","created_at":"2025-10-12 14:09:08","extension":"jpg","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":156755,"visible":true,"origin":"","legend":"","description":"","filename":"Figure2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/7351f0e87416d2a9a5e1c526.jpg"},{"id":93338120,"identity":"fbae04eb-51fc-4ff6-ae3d-17000526db51","added_by":"auto","created_at":"2025-10-12 14:17:08","extension":"jpg","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":256160,"visible":true,"origin":"","legend":"","description":"","filename":"Figure3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/3493a5f6b33cdccfdde46616.jpg"},{"id":93337500,"identity":"4d906e87-2400-4d28-a467-76cd6cad534a","added_by":"auto","created_at":"2025-10-12 14:09:08","extension":"jpg","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2180196,"visible":true,"origin":"","legend":"","description":"","filename":"Figure4.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/7b3647c78532e65fe8f4cae3.jpg"},{"id":93337498,"identity":"9becce8f-fa64-48cf-81d8-603ff048d31e","added_by":"auto","created_at":"2025-10-12 14:09:08","extension":"jpg","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":206558,"visible":true,"origin":"","legend":"","description":"","filename":"Figure5.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/529193d9964452c96a618c85.jpg"},{"id":93337484,"identity":"fc13e1eb-847d-4b43-a768-f8992556b92c","added_by":"auto","created_at":"2025-10-12 14:09:08","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30135,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure1.png","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/1dd528562bb56753ed72bb24.png"},{"id":93337485,"identity":"f3126287-f1d0-4714-b6fd-1038bbf4bfd4","added_by":"auto","created_at":"2025-10-12 14:09:08","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64844,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure2.png","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/ebb7d90b1d846ea5ac4a3401.png"},{"id":93337499,"identity":"3b60c22a-fd87-4bec-a597-966c955a5ad6","added_by":"auto","created_at":"2025-10-12 14:09:08","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":148250,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure3.png","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/a97b8022dd25cda6a14dcb2d.png"},{"id":93337495,"identity":"99e0bf5b-f2fc-499c-91a7-b74348fd3c86","added_by":"auto","created_at":"2025-10-12 14:09:08","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":354043,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure4.png","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/296dd7b89f3f6b46f74f5b07.png"},{"id":93340677,"identity":"258d6d42-a90f-4d45-ba7c-f82ee7d2d623","added_by":"auto","created_at":"2025-10-12 14:33:08","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":129677,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure5.png","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/eddc3b540979b66d6e0ac4e6.png"},{"id":93338123,"identity":"98b9c4b7-abb0-4913-9632-3f5715299dd4","added_by":"auto","created_at":"2025-10-12 14:17:08","extension":"xml","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":171969,"visible":true,"origin":"","legend":"","description":"","filename":"c68626d16c3c4155a5a8294064b4eea21structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/14e5f0e506a7ff4728121bc6.xml"},{"id":93337493,"identity":"c0d59c18-1243-450f-83e0-f90f6d53fa1c","added_by":"auto","created_at":"2025-10-12 14:09:08","extension":"html","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":184840,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/4e1b221c40bca2556bf122f2.html"},{"id":93339229,"identity":"82ad26bc-8791-4de6-b4b2-ccc7a4148b3c","added_by":"auto","created_at":"2025-10-12 14:25:08","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":56332,"visible":true,"origin":"","legend":"\u003cp\u003ePatient selection and distribution flowchart.\u003c/p\u003e","description":"","filename":"Figure1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/8e45a8b5324bf431669412a7.jpg"},{"id":93338117,"identity":"a3276c22-bacd-48b7-8058-62862c5ab0f4","added_by":"auto","created_at":"2025-10-12 14:17:08","extension":"jpg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":156755,"visible":true,"origin":"","legend":"\u003cp\u003eFlowchart illustrates the study design.\u003c/p\u003e","description":"","filename":"Figure2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/9a7aca7e0344655d2928e960.jpg"},{"id":93337474,"identity":"f635498c-c255-4b13-9948-2a78aa3c0dac","added_by":"auto","created_at":"2025-10-12 14:09:08","extension":"jpg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":256160,"visible":true,"origin":"","legend":"\u003cp\u003eRadiomic feature selection using a least absolute shrinkage and selection operator (LASSO) binary logistic regression model. Radiomic feature selection process via the LASSO binary logistic regression model (A, B). Comparison of the Rad-scores between the MPR and NMPR groups in the training and test cohorts. Red indicates the MPR group, and blue indicates the NMPR group (C, D).\u003c/p\u003e","description":"","filename":"Figure3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/30c05ccfffc97cc1453bdd32.jpg"},{"id":93337478,"identity":"e91376bf-fb3a-41ed-bfa4-8c3151b236ff","added_by":"auto","created_at":"2025-10-12 14:09:08","extension":"jpg","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":2180196,"visible":true,"origin":"","legend":"\u003cp\u003eConstruction and performance of the models for predicting Major Pathological Response with receiver operating characteristic curve analysis in the training set (A), internal validation set (B) and external test set (C). AUC, Area under the receiver operating characteristic curve; CM, Clinical Model; TMM, Tumor Margin Model; WTM, Whole Tumor Model; HM, Hybrid Model.\u003c/p\u003e","description":"","filename":"Figure4.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/9ca94a34cdc42e99c7723f33.jpg"},{"id":93338119,"identity":"94d5049f-87d3-4584-a021-553b8e6f9b12","added_by":"auto","created_at":"2025-10-12 14:17:08","extension":"jpg","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":206558,"visible":true,"origin":"","legend":"\u003cp\u003eNomogram, Calibration curve and Decision curve analysis. (A) Nomogram and (B) Calibration curve for Major Pathological Response in the training and validation groups. (C) Decision curve analysis for each model. CM, Clinical Model; TMM, Tumor Margin Model; WTM, Whole Tumor Model; HM, Hybrid Model.\u003c/p\u003e","description":"","filename":"Figure5.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/047a2eb9769270d23199ad63.jpg"},{"id":93342000,"identity":"0a2a14c0-20b3-4c81-ab1e-e595122c9337","added_by":"auto","created_at":"2025-10-12 14:41:09","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4326768,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/d83b4175-0e6e-4cf6-ae71-e8d6ca7c8ac5.pdf"},{"id":93339228,"identity":"e70be7f6-3f07-414f-8a95-b3439a1f1eb0","added_by":"auto","created_at":"2025-10-12 14:25:08","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":296351,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementalmaterials.docx","url":"https://assets-eu.researchsquare.com/files/rs-7531855/v1/34e1917d4a81d68bb8f4bb0e.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Radiomics Based on the Tumor–Parenchyma Invasive Interface Predicts Major Pathological Response to Neoadjuvant Immunochemotherapy in Non-small Cell Lung Cancer","fulltext":[{"header":"Introduction","content":"\u003cp\u003eLung cancer remains the leading cause of cancer-related mortality worldwide and is among the most frequently diagnosed malignancies[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Non-small cell lung cancer (NSCLC) accounts for approximately 85% of all cases[\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eSurgical resection remains the cornerstone of curative treatment for NSCLC in both early and locally advanced stages[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. The extent of residual tumor cells after surgery is a key prognostic factor influencing long-term survival. Studies have shown that NSCLC patients whose resected specimens demonstrate a major pathologic response (MPR) after neoadjuvant treatment experience significantly improved survival outcomes[\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. Compared to chemotherapy alone, neoadjuvant immunochemotherapy (NAIC) improves the MPR rate and long-term survival, making it a promising strategy for resectable NSCLC[\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. However, a substantial proportion of patients fail to achieve MPR and may even experience immune-related adverse effects after NAIC[\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e], underscoring the urgent need for reliable methods to identify those most likely to benefit from this approach.\u003c/p\u003e\u003cp\u003eTumor mutational burden (TMB) and PD-L1 expression are widely used biomarkers for predicting responses to immune checkpoint inhibitors[\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. However, their assessment relies on invasive tissue sampling, and tumor heterogeneity poses challenges to the consistency and reliability of test results.\u003c/p\u003e\u003cp\u003eRadiomics and deep learning can analyze a broad spectrum of quantifiable features from medical imaging and have emerged as promising approaches in lung cancer precision medicine[\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e, \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. Numerous studies have leveraged CT image features to predict MPR in NSCLC following NAIC, but they primarily analyzed the entire tumor as a whole, thereby overlooking the tumoral heterogeneity. Tumor heterogeneity is increasingly recognized as a critical factor reflecting distinct biological properties[\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e, \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. This may be attributed to central necrosis and increased cellular proliferation at the tumor periphery[\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. The tumor-stroma interface is the most biologically diverse and heterogeneous region within the tumor microenvironment, serving as a crucial hub for tumor-host interactions. Studies have demonstrated that tumor margin region is a hotspot for key biological processes, including angiogenesis, immune cell infiltration, and tumor invasion[\u003cspan additionalcitationids=\"CR15\" citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eTo the best of our knowledge, no previous studies have explored the predictive value of tumor margin region features for assessing NAIC response in NSCLC. This study aimed to evaluate these features and develop a preoperative model to predict NAIC response in NSCLC.\u003c/p\u003e"},{"header":"Materials and Method","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003ePatients\u003c/h2\u003e\u003cp\u003e The study was approved by the Ethics Committee (retrospective study approval 2023\u0026thinsp;\u0026minus;\u0026thinsp;121) and the requirement for informed consent was waived. We retrospectively screened patients with NSCLC who underwent surgery following NAIC at two medical centers between August 2019 and March 2025. Inclusion criteria included: (1) NSCLC diagnosis confirmed by biopsy pathology; (2) clinically staged II to III; (3) completion of at least two cycles of NAIC; (4) postoperative pathological evaluation of tumor and lymph nodes as per International Association for the Study of Lung Cancer (IASLC) guidelines. Exclusion criteria included: (1) prior immunotherapy; (2) absence of pre-NAIC contrasted-enhanced CT images; (3) CT images with insufficient quality for radiomic analysis; and (4) time interval between chest CT and treatment initiation exceeds one month. We collected baseline clinical information and contrasted-enhanced CT images acquired within one month prior to the initiation of NAIC. NAIC regimens usually consist of 2 to 5 cycles of pembrolizumab or nivolumab administered in combination with platinum-based chemotherapy. Finally, 169 patients were included in the study. For model development, patients from the Second Xiangya Hospital were randomly assigned to training and internal validation sets in a 7:3 ratio, while the cohort from Hunan Cancer Hospital served as an external test set to evaluate model performance. The patient selection process and distribution flowchart are depicted in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, and the overall study design is illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eHistopathological assessment and definition of MPR\u003c/h3\u003e\n\u003cp\u003eAccording to the multidisciplinary recommendations from the IASLC regarding pathological assessment of lung cancer excision specimens after neoadjuvant therapy[\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e], all pathologic information were independently performed by two pathologists, each with over 10 years of experience. MPR was defined as 0\u0026ndash;10% of viable tumor cells remaining in the residual tumor. In cases of disagreement, discussions were held until a consensus was reached.\u003c/p\u003e\n\u003ch3\u003eCT image acquisition and ROI segmentation\u003c/h3\u003e\n\u003cp\u003eAll patients underwent baseline CT scans within one month prior to NAIC treatment, with the following CT imaging using: Somatom Definition Flash (Siemens, Germany), uCT780 (United Imaging, Shanghai, China), Somatom Perspective 128 (Siemens, Germany), and Somatom Definition Force (Siemens, Germany). Scanning parameters were standardized as follows: 120 kVp, 100\u0026ndash;200 mAs, and a pitch of 0.75\u0026ndash;1.5. CT images were acquired with patients in the supine position at full inspiration. Iodine contrast agent agent (e.g., Omnipaque, 300mgI/ml, GE Healthcare) was administered by power injector at a flow rate of 3.0 to 3.5 mL/s and the contrasted images were acquired after the injection of iodine contrast agent at 30\u0026ndash;40 second. No adverse reactions occurred after the injection of contrast agent in all patients. Then, contrasted-enhanced CT images were retained in DICOM format and resampled to a uniform resolution of 1 \u0026times; 1 \u0026times; 1 mm to mitigate the impact of variations in acquisition equipment. Region of interest (ROI) was manually segmented slice by slice using 3D Slicer software[\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e] (version 5.6.2, Brigham and Women\u0026rsquo;s Hospital) by one junior radiologists with over 10 years of experience. A senior radiologist then reviewed the segmented ROIs and made necessary adjustments. Image dilation expanded the tumor areas to generate outer peritumor areas, while image erosion shrank the tumor areas to yield inner peritumor areas. The tumor margin region was generated by the \u0026ldquo;ROI operation\u0026rdquo; module of the RIAS software[\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. Annular 6 mm (defined as the tumor margin region) wide areas at a radial distance of \u0026minus;\u0026thinsp;3 mm (inside) to 3 mm (outside) from the edge of the segmented region were created finally.\u003c/p\u003e\n\u003ch3\u003eFeature extraction and selection\u003c/h3\u003e\n\u003cp\u003eRadiomic features were extracted from the whole tumor region and tumor margin region using the open-source PyRadiomics package in Python[\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. To evaluate robustness, 50 cases were randomly selected for intraclass correlation coefficient (ICC) analysis, with an ICC\u0026thinsp;\u0026ge;\u0026thinsp;0.75 indicating satisfactory reproducibility. The Minimum Redundancy Maximum Relevance algorithm was employed to select the top 20 most valuable features. Following this, Least Absolute Shrinkage and Selection Operator (LASSO) regression was applied using a tenfold cross-validation to retain the most important features. A radiomics score (Rad-score) for each patient was then calculated by taking a linear combination of the selected features, weighted according to their respective coefficients.\u003c/p\u003e\n\u003ch3\u003eModel construction and comparison\u003c/h3\u003e\n\u003cp\u003eThe dataset was randomly split into training and internal validation sets at a 7:3 ratio. Three models were constructed: the Whole Tumor Model (WTM), based on radiomic features extracted from the whole tumor region; the Tumor Margin Model (TMM), based on radiomic features derived from the tumor margin region; and the Clinical model (CM). The hybrid model (HM) was developed by integrating the optimized radiomics signature with clinically predictors to enhance predictive performance. Model performance was subsequently evaluated by plotting receiver operating characteristic (ROC) curves and calculating the corresponding area under the receiver operating characteristic curve (AUC).\u003c/p\u003e\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003eNomogram Development and Evaluation\u003c/h2\u003e\u003cp\u003eClinically significant predictors were combined with the Rad-Score in a multivariate logistic regression model. The resulting model coefficients were then used to build the nomogram. A calibration curve displayed the agreement between actual clinical outcomes and model predictions. The AUC was used to measure the discrimination performance. Decision curves analysis (DCA) was used to evaluate and compare the net benefit of the constructed models.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e\u003ch2\u003eStatistical Analysis\u003c/h2\u003e\u003cp\u003eAll statistical analysis was conducted with R software (version 4.1.0, Vienna, Austria). Continuous variables were presented as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation, and categorical variables as frequency (percentage). Univariate and multivariate logistic regression analyses were conducted to identify risk factors, with odds ratios and 95% confidence intervals provided. The model's performance was evaluated using AUC, accuracy (ACC), sensitivity, specificity, positive predictive value, and negative predictive value. The DeLong test was used to assess the statistical significance of differences between models. The \"glmnet\" package in R was used to perform LASSO logistic regression. The \"rms\" package was used for nomogram construction and calibration plotting. ROC plots were constructed using the \"pROC\" package. The \"rmda\" package was used to construct the DCA curve plots. The \"rms\" package in R was used to calibrate the radiomic signature using the calibration curve. Statistical significance was accepted at P\u0026thinsp;\u0026lt;\u0026thinsp;0.05.\u003c/p\u003e\u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\u003ch2\u003ePatient Characteristics\u003c/h2\u003e\u003cp\u003eA total of 169 patients were divided into training set (n\u0026thinsp;=\u0026thinsp;93), internal validation set (n\u0026thinsp;=\u0026thinsp;39) and external test set (n\u0026thinsp;=\u0026thinsp;37). Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e presents the characteristics across different cohorts. The overall cohort had a mean age of 60 years, with 91.1% (n\u0026thinsp;=\u0026thinsp;154) being male. Histologically, 130 patients (76.9%) had squamous cell carcinoma, while 39 (23.1%) had adenocarcinoma. Most patients were staged as clinical stage T2 (n\u0026thinsp;=\u0026thinsp;72, 42.6%) and clinical stage N2 (n\u0026thinsp;=\u0026thinsp;90, 53.3%), with clinical stage III (n\u0026thinsp;=\u0026thinsp;126, 74.6%) being the most common. Pathologic response assessment showed that 61.5% (n\u0026thinsp;=\u0026thinsp;104) achieved MPR. The primary immune checkpoint inhibitors administered across the two centers included tislelizumab (30.2%), pembrolizumab (27.8%), sintilimab (13.6%), and toripalimab (13.0%). No statistically significant differences in the neoadjuvant treatment regimens were observed between the MPR and non-MPR groups across all three cohorts. After conducting univariable and multivariable logistic regression analyses, pathology was confirmed as an independent risk factor and subsequently included in the CM (p\u0026thinsp;=\u0026thinsp;0.006; OR\u0026thinsp;=\u0026thinsp;4.26, 95% CI: 1.52,11.98) (Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eClinical characteristics of the entire dataset.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"12\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c11\" colnum=\"11\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c12\" colnum=\"12\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colspan=\"2\" morerows=\"1\" nameend=\"c2\" namest=\"c1\" rowspan=\"2\"\u003e\u003cp\u003eClinical factors\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"3\" nameend=\"c5\" namest=\"c3\"\u003e\u003cp\u003eTrain set (n\u0026thinsp;=\u0026thinsp;93)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"3\" nameend=\"c8\" namest=\"c6\"\u003e\u003cp\u003eInternal validation set (n\u0026thinsp;=\u0026thinsp;39)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"3\" nameend=\"c11\" namest=\"c9\"\u003e\u003cp\u003eExternal test set (n\u0026thinsp;=\u0026thinsp;37)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c12\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eTotal\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eMPR (n\u0026thinsp;=\u0026thinsp;56)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eNMPR (n\u0026thinsp;=\u0026thinsp;37)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003ep-value\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eMPR (n\u0026thinsp;=\u0026thinsp;24)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eNMPR (n\u0026thinsp;=\u0026thinsp;15)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u003cp\u003ep-value\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c9\"\u003e\u003cp\u003eMPR (n\u0026thinsp;=\u0026thinsp;24)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c10\"\u003e\u003cp\u003eNMPR (n\u0026thinsp;=\u0026thinsp;13)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c11\"\u003e\u003cp\u003ep-value\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eGender\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e*0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMale\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e53 (94.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e35 (94.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e23 (95.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e9 (60.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e22 (91.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e12 (92.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e154\u0026nbsp;(91.1)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eFemale\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3 (5.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e2 (5.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1 (4.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e6 (40.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e2 (8.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e1 (7.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e15\u0026nbsp;(8.9)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eAge (mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e59.5 (6.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e61.7 (7.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.13\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e61.4 (6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e55.8 (8.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e*0.01\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e59.8 (7.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e62.7 (6.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.24\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eAge group\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.39\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.21\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.35\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e41 (73.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e24 (64.9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e15 (62.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e13 (86.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e18 (75.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e7 (53.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e118\u0026nbsp;(69.8)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026ge;\u0026thinsp;65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e15 (26.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e13 (35.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e9 (37.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e2 (13.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e6 (25.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e6 (46.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e51 (30.2)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSmoking history\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.26\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e*0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.57\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e45 (80.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e26 (70.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e21 (87.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e7 (46.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e23 (95.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e11 (84.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e133\u0026nbsp;(78.7)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e11 (19.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e11 (29.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e3 (12.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e8 (53.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e1 (4.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e2 (15.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e36\u0026nbsp;(21.3)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eLung lobe\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.64\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.13\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.96\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRight\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e29 (51.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e21 (56.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e10 (41.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e10 (66.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e15 (62.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e9 (69.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e93\u0026nbsp;(55.0)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLeft\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e27 (48.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e16 (43.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e14 (58.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e5 (33.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e9 (37.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e4 (30.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e76\u0026nbsp;(45.0)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eClinical T Stage\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.09\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.19\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3 (5.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e3 (8.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e2 (8.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0 (0.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e11 (6.5)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e25 (44.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e15 (40.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e12 (50.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e4 (26.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e72\u0026nbsp;(42.6)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e15 (26.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e7 (18.9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e4 (16.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e8 (53.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e48\u0026nbsp;(28.4)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e13 (23.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e12 (32.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e6 (25.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e3 (20.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e38\u0026nbsp;(22.5)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eClinical N Stage\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.35\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.16\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.73\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e6 (10.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e9 (24.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1 (4.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e3 (20.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e20\u0026nbsp;(11.8)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e15 (26.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e7 (18.9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e7 (29.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e1 (6.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e45\u0026nbsp;(26.6)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e31 (55.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e19 (51.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e11 (45.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e9 (60.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e12\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e90 (53.3)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e4 (7.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e2 (5.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e5 (20.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e2 (13.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e14\u0026nbsp;(8.3)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eClinical Stage\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.84\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.51\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eII\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e7 (12.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e6 (16.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e2 (8.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0 (0.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e18\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e43\u0026nbsp;(25.4)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eIII\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e49 (87.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e31 (83.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e22 (91.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e15 (100.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e126\u0026nbsp;(74.6)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003ePathology\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e*0.004\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.42\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.28\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSquamous\u0026nbsp;carcinoma\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e49 (87.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e23 (62.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e20 (83.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e10 (66.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e20 (83.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e8 (61.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e130\u0026nbsp;(76.9)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAdenocarcinoma\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e7 (12.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e14 (37.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e4 (16.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e5 (33.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e4 (16.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e5 (38.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e39\u0026nbsp;(23.1)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eNAIC cycle\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.22\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.24\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e13 (23.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e6 (16.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e5 (20.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e4 (26.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e6 (25.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e6 (46.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e40 (23.7)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e22 (39.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e10 (27.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e11 (45.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e5 (33.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e15 (62.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e7 (53.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e70 (41.4)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e21 (37.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e20 (54.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e6 (25.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e5 (33.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e3 (12.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0 (0.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e55 (32.5)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0 (0.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1 (2.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e2 (8.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e1 (6.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e4 (2.4)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eImmunotherapy agent\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.51\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.38\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eTislelizumab\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e23 (41.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e12 (32.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e7 (29.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e6 (40.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e1 (4.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e2 (15.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e51 (30.2)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePembrolizumab\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e21 (37.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e12 (32.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e7 (29.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e7 (46.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e47 (27.8)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSintilimab\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e7 (12.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e5 (13.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e6 (25.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e2 (13.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e2 (8.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e1 (7.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e23 (13.6)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eToripalimab\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3 (5.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e4 (10.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e3 (12.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0 (0.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e9 (37.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e3 (23.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e22 (13.0)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eOther\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e2 (3.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e4 (10.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1 (4.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0 (0.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e12 (50.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e7 (53.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e26 (15.4)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003ePD-L1_1\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.50\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026le;\u0026thinsp;50%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e9 (16.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e8 (21.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e22 (91.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e13 (86.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e23 (95.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e13 (100.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e125 (74.0)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026gt;50%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e47 (83.9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e29 (78.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e2 (8.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e2 (13.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e1 (4.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0 (0.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e44 (26.0)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003ePD-L1_2\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.88\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026le;\u0026thinsp;1%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e39 (69.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e26 (70.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e15 (62.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e9 (60.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e23 (95.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e13 (100.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e125 (74.0)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026gt;1%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e17 (30.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e11 (29.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e9 (37.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e6 (40.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e1 (4.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0 (0.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e44 (26.0)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eKi 67\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.35\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.59\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.78\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026gt;40%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e16 (28.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e14 (37.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e8 (33.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e3 (20.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e16 (66.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e10 (76.9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e67\u0026nbsp;(39.6)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026le;\u0026thinsp;40%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e40 (71.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e23 (62.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e16 (66.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e12 (80.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e8 (33.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e3 (23.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e102\u0026nbsp;(60.4)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eNLR\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.58\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.72\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.37\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026le;\u0026thinsp;2.75\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e24 (42.9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e18 (48.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e11 (45.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e6 (40.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e11 (45.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e4 (30.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e74\u0026nbsp;(43.8)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026gt;2.75\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e32 (57.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e19 (51.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e13 (54.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e9 (60.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e13 (54.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e9 (69.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e95\u0026nbsp;(56.2)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"12\"\u003eData in parentheses are percentages; MPR, major pathological response; NMPR, non-MPR; NAIC, neoadjuvant immunochemotherapy; PD-L1, Programmed Death-Ligand 1; NLR, neutrophil to lymphocyte ratioNLR, neutrophil to lymphocyte ratio.\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd colspan=\"12\"\u003e*p\u0026thinsp;\u0026lt;\u0026thinsp;0.05\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eUnivariate and multivariate analysis of clinical data in the training set.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"5\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eVariable\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003eUnivariate analysis\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u003cp\u003eMultivariate analysis\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eOR (95%CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eP-value\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eOR (95%CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eP-value\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGender\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.01 (0.16, 6.35)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAge\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.05 (0.99, 1.12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.13\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAge group\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.48 (0.60, 3.63)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.39\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSmoking history\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.58(0.22, 1.52)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.27\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLung lobe\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.22 (0.53, 2.82)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.64\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eClinical T Stage\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.09 (0.70, 1.71)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.69\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eClinical N Stage\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.74 (0.45, 1.22)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.24\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eClinical Stage\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.74 (0.23, 2.40)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.61\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePathology\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e4.26 (1.52, 11.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e*0.01\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e4.26 (1.52,11.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e*0.006\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNAIC cycle\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.62 (0.93, 2.81)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.09\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eImmunotherapy agent\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.36 (0.95, 1.94)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.09\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePD-L1_1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.69 (0.24, 2.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.50\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePD-L1_2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.97 (0.39, 2.40)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eKi-67\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.66 (0.27, 1.59)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.35\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNLR\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.79 (0.34, 1.82)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.58\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"5\"\u003eOR, odds ratio; CI, confidence interval; NAIC, neoadjuvant immunochemotherapy; NAIC, neoadjuvant immunochemotherapy; PD-L1, Programmed Death-Ligand 1; NLR, neutrophil to lymphocyte ratio.\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd colspan=\"5\"\u003e*p\u0026thinsp;\u0026lt;\u0026thinsp;0.05\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\u003ch2\u003eDevelopment of the Radiomics Signature\u003c/h2\u003e\u003cp\u003eA total of 1410 radiomics features were extracted from two regions using Pyradiomics, of which 1340 (95.03%) features were retained after ICC analysis. After Z-score normalization, all extracted features underwent reproducibility assessment using ICC analysis, and 1,340 features with ICC\u0026thinsp;\u0026ge;\u0026thinsp;0.75 were retained. The retained features consisted of 258 first-order features describing voxel intensity distributions, 14 shape features quantifying tumor geometry, and 1,068 texture features characterizing spatial relationships and heterogeneity patterns. The texture category was further divided into 334 gray level co-occurrence matrix features, 233 gray level run length matrix features, 226 gray level size zone matrix features, 205 gray level dependence matrix features, and 70 neighboring gray tone difference matrix features. These features were derived from multiple image transformation filters, including original, wavelet, logarithm, square, exponential, square root, and local binary pattern, to enhance specific signal properties and capture multi-scale information.\u003c/p\u003e\u003cp\u003eTo reduce dimensionality and avoid overfitting, the LASSO regression method was applied to the extracted radiomic features (Figure \u003cspan refid=\"MOESM1\" class=\"InternalRef\"\u003eS1\u003c/span\u003e-2). As a result, 10 features from the tumor margin region and 6 features from the whole tumor region were retained as the most predictive for constructing the TMM and WTM models, respectively (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eA, \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eB). The Wilcoxon rank-sum test showed that the Rad-scores derived from above two region features differed significantly between MPR and NMPR patients in both cohorts (p\u0026thinsp;\u0026lt;\u0026thinsp;0.05) (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eC, \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eD).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec13\" class=\"Section2\"\u003e\u003ch2\u003ePerformance Comparison of Model\u003c/h2\u003e\u003cp\u003eThe evaluation performance of the three model was assessed using ROC curves (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e4\u003c/span\u003e). The CM exhibited limited predictive performance, with AUCs of 0.63 (95% CI: 0.54\u0026ndash;0.72), 0.58 (95% CI: 0.44\u0026ndash;0.73) and 0.61 (95% CI: 0.45\u0026ndash;0.77) in the training and internal validation sets, respectively. The TMM achieved AUCs of 0.84 (95% CI: 0.76\u0026ndash;0.92) and 0.84 (95% CI: 0.71\u0026ndash;0.97) in the respective datasets, exceeding the WTM (AUC\u0026thinsp;=\u0026thinsp;0.74 [95% CI: 0.64\u0026ndash;0.85] in training set, 0.71 [95% CI: 0.54\u0026ndash;0.89] in the internal validation set (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e4\u003c/span\u003eA, \u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e4\u003c/span\u003eB). The HM, integrating tumor margin radiomic features with clinicopathological data, further improved predictive performance, achieving AUCs of 0.88 (95% CI: 0.81\u0026ndash;0.95) and 0.86 (95% CI: 0.74\u0026ndash;0.98) in the training and internal validation sets, respectively. The HM achieved the highest ACC of 0.79 (95% CI: 0.64\u0026ndash;0.91), surpassing the CM (ACC\u0026thinsp;=\u0026thinsp;0.64, 95% CI: 0.47\u0026ndash;0.79), TMM (ACC\u0026thinsp;=\u0026thinsp;0.62, 95% CI: 0.45\u0026ndash;0.77) and WTM (ACC\u0026thinsp;=\u0026thinsp;0.69, 95% CI: 0.52\u0026ndash;0.83) in the internal validation set. Additional diagnostic metrics are summarized in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eModel predictive performance.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"16\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c11\" colnum=\"11\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c12\" colnum=\"12\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c13\" colnum=\"13\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c14\" colnum=\"14\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c15\" colnum=\"15\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c16\" colnum=\"16\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colspan=\"5\" nameend=\"c6\" namest=\"c2\"\u003e\u003cp\u003eTraining set\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"5\" nameend=\"c11\" namest=\"c7\"\u003e\u003cp\u003eInternal validation set\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"5\" nameend=\"c16\" namest=\"c12\"\u003e\u003cp\u003eExternal test set\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eModel\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eACC (95% CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSEN\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eSPE\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003ePPV\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eNPV\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eACC (95% CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u003cp\u003eSEN\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c9\"\u003e\u003cp\u003eSPE\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c10\"\u003e\u003cp\u003ePPV\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c11\"\u003e\u003cp\u003eNPV\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c12\"\u003e\u003cp\u003eACC (95% CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c13\"\u003e\u003cp\u003eSEN\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c14\"\u003e\u003cp\u003eSPE\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c15\"\u003e\u003cp\u003ePPV\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c16\"\u003e\u003cp\u003eNPV\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTMM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.71 (0.61\u0026ndash;0.80)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.52\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.58\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.62 (0.45\u0026ndash;0.77)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.46\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e0.50\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.85\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e0.76 (0.59\u0026ndash;0.88)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c13\"\u003e\u003cp\u003e0.38\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c14\"\u003e\u003cp\u003e0.96\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c15\"\u003e\u003cp\u003e0.83\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c16\"\u003e\u003cp\u003e0.74\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWTM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.74 (0.64\u0026ndash;0.83)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.70\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.77\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.67\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.80\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.69 (0.52\u0026ndash;0.83)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.47\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.83\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e0.64\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.71\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e0.73 (0.56\u0026ndash;0.86)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c13\"\u003e\u003cp\u003e0.23\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c14\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c15\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c16\"\u003e\u003cp\u003e0.71\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.68 (0.57\u0026ndash;0.77)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.38\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.88\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.678\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.68\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.64 (0.47\u0026ndash;0.79)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.33\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.83\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e0.56\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.67\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e0.68 (0.50\u0026ndash;0.82)-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c13\"\u003e\u003cp\u003e0.38\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c14\"\u003e\u003cp\u003e0.83\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c15\"\u003e\u003cp\u003e0.56\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c16\"\u003e\u003cp\u003e0.72\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.83 (0.74\u0026ndash;0.90)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.76\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.88\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.80\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.84\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.79 (0.64\u0026ndash;0.91)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.67\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.88\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e0.77\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.81\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e0.76 (0.59\u0026ndash;0.88)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c13\"\u003e\u003cp\u003e0.31\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c14\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c15\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c16\"\u003e\u003cp\u003e0.73\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"16\"\u003eACC, Accuracy; CI, Confidence Interval; TMM, Tumor Margin Model; WTM, Whole Tumor Model; CM, Clinical Model; HM, Hybrid Model; SPE, Specificity; SEN, Sensitivity; PPV, Positive Predictive Value; NPV, Negative Predictive Value.\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eIn the external test set, the HM maintained favorable performance (AUC 0.87; 95% CI, 0.76\u0026ndash;0.98) (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e4\u003c/span\u003eC), supporting its potential utility for preoperative risk stratification and patient selection.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec14\" class=\"Section2\"\u003e\u003ch2\u003eNomogram Construction and Clinical Utility Assessment\u003c/h2\u003e\u003cp\u003eThe variables included in the HM are presented as a nomogram to allow clinicians to intuitively and conveniently assess the likelihood of MPR using patient-specific information (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e5\u003c/span\u003eA). Each factor was assigned a weighted point value. Using the nomogram, these points were summed for each patient to yield a total score, which was then translated into an estimated probability of MPR. The calibration curves also indicated minimal overall deviation between the model-predicted and expected probabilities (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e5\u003c/span\u003eB). DCA showed that nomogram provided a larger net benefit across the range of reasonable threshold probabilities compared with the other models (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e5\u003c/span\u003eC).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eNAIC has revolutionized the treatment paradigm for NSCLC by reducing tumor burden prior to surgical resection, thereby decreasing the risk of recurrence[\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. However, a considerable proportion of NSCLC patients fail to achieve MPR after NAIC, identifying patients most likely to benefit from this advanced therapy is of considerable clinical significance. In the present study, a HM was developed to predict MPR in NSCLC following NAIC, achieving AUC of 0.88 in the training set and 0.86 in the internal validation set. Additionally, the DCA confirmed that HM provided the greatest clinical benefit. Finally, a nomogram based on HM was developed to assist clinicians in better assessing the likelihood of achieving MPR in NSCLC patients.\u003c/p\u003e\u003cp\u003eConsistent with previous studies, pathology was identified as a clinical variable closely associated with MPR prediction in NSCLC patients[\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. MPR is more likely in patients with lung squamous cell carcinoma compared to those with non-squamous carcinoma, which may be attributable to higher PD-L1 expression, TMB, and functional tumor-infiltrating lymphocyte density in the tumor microenvironment of squamous cell carcinoma[\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eCT has been a standard imaging modality in clinical practice for evaluating treatment response in lung cancer. Due to immune cell infiltration, relying solely on conventional CT characteristics is insufficient for accurately predicting treatment response[\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]. Radiomics enables the extraction of a vast array of imaging features from multimodal medical images and has played an increasingly pivotal role in lung cancer, encompassing screening, treatment decision-making, and survival prediction[\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]. Liu et al.[\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e] were the first to develop a radiomics model integrating clinical features, achieving an AUC of 0.81 in the test set for MPR prediction in NSCLC patients who underwent NAIC. Han et al.[\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e] extracted radiomic features from pre- and post-treatment contrast-enhanced CT images to quantify feature changes, resulting in an AUC of 0.732 in the testing cohort. She et al.[\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e] utilized deep learning-derived features to construct a predictive model for MPR, yielding an AUC of 0.75 in an external test cohort. Recent studies have also demonstrated that peritumoral microenvironment can predict the response to NAIC. These studies have generally assumed tumor homogeneity, using features from the entire tumor or including the peritumoral area without addressing its heterogeneity.\u003c/p\u003e\u003cp\u003eIndeed, increasing evidence suggests that the tumor stroma interface is where immune microenvironment alterations and metabolic changes in tumor cells are most pronounced. The tumor margin areas, where tumor cells invade surrounding tissues and interact with other cells, are the most active regions for cell infiltration and invasion[\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e, \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. Recently, Wu et al.[\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e] identified a region within 250 \u0026micro;m on both sides of the tumor border in patients with liver cancer. The zone is characterized by an immunosuppressive microenvironment, metabolic reprogramming of tumor cells, and significant damaged hepatocytes, all of which influence the risk of tumor invasion and patient prognosis. Similarly, in colorectal cancer, spatial transcriptomic analyses revealed that immune cell organization within a 300 \u0026micro;m tumor stroma boundary was highly predictive of response to immune checkpoint blockade[\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]. These studies provide compelling biological justification for analyzing tumor margins as distinct and informative regions. Analogous findings have been reported in neuro-oncology. The interface between the brain parenchyma and the tumor, known as the brain-to-tumor interface (BTI), is recognized as the key region where brain tumors interact with intracranial cells and the immune system[\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]. Previous studies have demonstrated that the BTI is critically associated with brain invasion status[\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e, \u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e], tumor grading[\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e], and the differentiation of metastatic tumor types[\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eHowever, in NSCLC, prior studies have predominantly examined intratumoral region, whereas the significance of tumor margin region remains underexplored. Given that immune checkpoint inhibitors exert antitumor effects by modulating the tumor and peritumoral immune microenvironment[\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e], we investigated the potential of tumor margin characteristics in predicting the response to NAIC in NSCLC patients. While peritumoral regions in lung cancer research are commonly extended in 3 mm increments, there is no standardized definition for the optimal tumor margin. A margin that is too narrow (e.g., 1\u0026ndash;2 mm) may fail to capture key edge features, whereas an overly wide margin (e.g., \u0026ge;\u0026thinsp;10 mm) may introduce substantial normal tissue and background noise, diluting critical biological signals. To balance these factors, we defined the \u0026minus;\u0026thinsp;3\u0026thinsp;~\u0026thinsp;+\u0026thinsp;3 mm region as the tumor margin, aiming to capture essential peritumoral information while minimizing extraneous interference.\u003c/p\u003e\u003cp\u003eNotably, our HM yielded AUCs of 0.86 (internal validation) and 0.87 (external test), surpassing the performance of previously reported models\u0026mdash;such as Ye et al.[\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e] (AUC\u0026thinsp;=\u0026thinsp;0.78, habitat model) and Wang et al.[\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e] (AUC\u0026thinsp;=\u0026thinsp;0.80, radiomics-clinical combined model). These findings support the hypothesis that explicitly modeling the tumor-lung interface may provide complementary and clinically meaningful information for NAIC response prediction. This finding aligns with prior research by Hu et al.[\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e], who divided tumors into marginal (S1) and internal (S2) subregions and found that features from S1 consistently outperformed those from S2 or the entire tumor in predicting response to anti-PD1 therapy. Notably, this margin-dominant predictive pattern has been validated across multiple cancer types and imaging modalities, including MRI-based cervical cancer radiomics[\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e] and PET/CT-driven nasopharyngeal carcinoma studies[\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e]. The enhanced performance of TMM may be attributed to its ability to capture critical tumor-host interactions[\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e, \u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e], such as immune infiltration, angiogenesis, and invasive behavior, which are strongly associated with response to NAIC. In contrast, the whole tumor features may include both active and less informative areas (e.g., necrotic or hypoxic regions), potentially diluting predictive signals.\u003c/p\u003e\u003cp\u003eThis study has several limitations. First, the overall sample size is relatively small, which may constrain the generalizability of the findings. Although we have added an independent external test cohort to enhance validation, future prospective studies with larger and more diverse populations across multiple centers are warranted to confirm model robustness. Second, the proportion of female patients in our cohort is limited, which may reduce the precision of subgroup estimates for women. This gender imbalance reflects real-world treatment patterns in thoracic oncology, where male patients are more frequently diagnosed with smoking-related NSCLC, but nonetheless warrants caution when extrapolating the model\u0026rsquo;s performance to female populations. Future work should aim to recruit more gender-balanced cohorts to ensure broader applicability. Third, the biological underpinnings of tumor margin region characteristics in NSCLC remain to be directly validated. Future studies integrating imaging, pathology, and spatial transcriptomics will be essential to better understand the mechanistic basis of the radiomic signal captured at the tumor margin. Finally, due to the short follow-up period, we have not yet investigated the predictive value of tumor margin characteristics for survival outcomes. Therefore, further studies incorporating survival as the primary endpoint are necessary to comprehensively evaluate the prognostic value of the tumor marginal region.\u003c/p\u003e\u003cp\u003eIn conclusion, this study proposes a novel tumor margin radiomics approach to predict NAIC response in resectable NSCLC. By facilitating more precise clinical decision-making, the HM holds the potential to minimize overtreatment and optimize personalized therapeutic strategies for resectable NSCLC.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cp\u003eNAIC, Neoadjuvant immunochemotherapy\u003c/p\u003e\u003cp\u003eNSCLC, Non-small cell lung cancer\u003c/p\u003e\u003cp\u003eWTM, Whole Tumor Model\u003c/p\u003e\u003cp\u003eTMM, Tumor Margin model\u003c/p\u003e\u003cp\u003eCM, Clinical model\u003c/p\u003e\u003cp\u003eHM, Hybrid model\u003c/p\u003e\u003cp\u003eMPR, Major pathological response\u003c/p\u003e\u003cp\u003eAUC, Area under the receiver operating characteristic curve\u003c/p\u003e\u003cp\u003eROC, Receiver operating characteristic\u003c/p\u003e\u003cp\u003eTMB, Tumor mutational burden\u003c/p\u003e\u003cp\u003eROI, Region of interest\u003c/p\u003e\u003cp\u003eICC, Intraclass correlation coefficient\u003c/p\u003e\u003cp\u003eLASSO, Least Absolute Shrinkage and Selection Operator\u003c/p\u003e\u003cp\u003eRad-score, Radiomics score\u003c/p\u003e\u003cp\u003eDCA, Decision curves analysis\u003c/p\u003e\u003cp\u003eACC, Accuracy\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003cp\u003e All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and the 1964 Helsinki Declaration and its later amendments or comparable ethical standards. This study was approved by an Institutional Review Board approval from the Second Xiangya Hospital of Central South University prior to the commencement of this study (retrospective study approval 2023\u0026thinsp;\u0026minus;\u0026thinsp;121), and informed consent was waived because of the study design.\u003c/p\u003e\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003cp\u003eNot applicable.\u003c/p\u003e\u003cp\u003e\u003ch2\u003eCompeting Interests\u003c/h2\u003e\u003cp\u003eThe authors declare no competing interests\u003c/p\u003e\u003c/p\u003e\u003ch2\u003eFunding\u003c/h2\u003e\u003cp\u003eThe study was supported by National Natural Science Foundation of China (62476291), Hunan Provincial Natural Science Foundation for Distinguished Young Scholars (2025JJ20097), Hunan Provincial Natural Science Foundation (2022JJ70139), the Research Foundation of Education Bureau of Hunan Province (24B0003), the Fundamental Research Funds for the central Universities of Central South University (2025ZZTS0873).\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eYisong Wang and Wei Zhao designed the study. Xiaohuang Yang, Feiping Li, Xiaoping Yu and Wei Han extracted, collected and analyzed data. Youlan Shang, Xiangru Song prepared tables and figures. Yisong Wang and Xiaoying Li reviewed the results, interpreted data, and wrote the manuscript. Wei Zhao and Jun Liu have accessed and verified all the data in the study. All authors have made an intellectual contribution to the manuscript and approved the submission.\u003c/p\u003e\u003ch2\u003eAcknowledgements\u003c/h2\u003e\u003cp\u003eNot applicable.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eThe datasets used and/or analyzed during the current study available from the corresponding author on reasonable request.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eEttinger DS, Wood DE, Aisner DL, Akerley W, Bauman JR, Bharat A, et al. NCCN Guidelines\u0026reg; Insights: Non-Small Cell Lung Cancer, Version 2.2023. J Natl Compr Canc Netw. 2023;21:340\u0026ndash;50. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.6004/jnccn.2023.0020\u003c/span\u003e\u003cspan address=\"10.6004/jnccn.2023.0020\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSiegel RL, Giaquinto AN, Jemal A, Cancer statistics. 2024. CA: A Cancer Journal for Clinicians. 2024;74:12\u0026ndash;49. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3322/caac.21820\u003c/span\u003e\u003cspan address=\"10.3322/caac.21820\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMiller M, Hanna N. Advances in systemic therapy for non-small cell lung cancer. BMJ. 2021;375:n2363. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1136/bmj.n2363\u003c/span\u003e\u003cspan address=\"10.1136/bmj.n2363\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTravis WD, Dacic S, Wistuba I, Sholl L, Adusumilli P, Bubendorf L, et al. IASLC Multidisciplinary Recommendations for Pathologic Assessment of Lung Cancer Resection Specimens After Neoadjuvant Therapy. J Thorac Oncol. 2020;15:709\u0026ndash;40. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.jtho.2020.01.005\u003c/span\u003e\u003cspan address=\"10.1016/j.jtho.2020.01.005\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eProvencio M, Nadal E, Insa A, Garc\u0026iacute;a-Campelo MR, Casal-Rubio J, D\u0026oacute;mine M, et al. Neoadjuvant chemotherapy and nivolumab in resectable non-small-cell lung cancer (NADIM): an open-label, multicentre, single-arm, phase 2 trial. Lancet Oncol. 2020;21:1413\u0026ndash;22. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/S1470-2045(20)30453-8\u003c/span\u003e\u003cspan address=\"10.1016/S1470-2045(20)30453-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eForde PM, Spicer J, Lu S, Provencio M, Mitsudomi T, Awad MM, et al. Neoadjuvant Nivolumab plus Chemotherapy in Resectable Lung Cancer. N Engl J Med. 2022;386:1973\u0026ndash;85. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1056/NEJMoa2202170\u003c/span\u003e\u003cspan address=\"10.1056/NEJMoa2202170\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKluger HM, Zito CR, Turcu G, Baine MK, Zhang H, Adeniran A, et al. PD-L1 Studies Across Tumor Types, Its Differential Expression and Predictive Value in Patients Treated with Immune Checkpoint Inhibitors. Clin Cancer Res. 2017;23:4270\u0026ndash;9. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1158/1078-0432.CCR-16-3146\u003c/span\u003e\u003cspan address=\"10.1158/1078-0432.CCR-16-3146\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eShi W-J, Zhao W. Biomarkers or factors for predicting the efficacy and adverse effects of immune checkpoint inhibitors in lung cancer: achievements and prospective. Chin Med J (Engl). 2020;133:2466\u0026ndash;75. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1097/CM9.0000000000001090\u003c/span\u003e\u003cspan address=\"10.1097/CM9.0000000000001090\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eChen M, Copley SJ, Viola P, Lu H, Aboagye EO. Radiomics and artificial intelligence for precision medicine in lung cancer treatment. Semin Cancer Biol. 2023;93:97\u0026ndash;113. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.semcancer.2023.05.004\u003c/span\u003e\u003cspan address=\"10.1016/j.semcancer.2023.05.004\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTunali I, Gillies RJ, Schabath MB. Application of Radiomics and Artificial Intelligence for Lung Cancer Precision Medicine. Cold Spring Harb Perspect Med. 2021;11:a039537. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1101/cshperspect.a039537\u003c/span\u003e\u003cspan address=\"10.1101/cshperspect.a039537\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eXu H, Lv W, Feng H, Du D, Yuan Q, Wang Q, et al. Subregional Radiomics Analysis of PET/CT Imaging with Intratumor Partitioning: Application to Prognosis for Nasopharyngeal Carcinoma. Mol Imaging Biol. 2020;22:1414\u0026ndash;26. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s11307-019-01439-x\u003c/span\u003e\u003cspan address=\"10.1007/s11307-019-01439-x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eO\u0026rsquo;Connor JPB, Rose CJ, Waterton JC, Carano RAD, Parker GJM, Jackson A. Imaging intratumor heterogeneity: role in therapy response, resistance, and clinical outcome. Clin Cancer Res. 2015;21:249\u0026ndash;57. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1158/1078-0432.CCR-14-0990\u003c/span\u003e\u003cspan address=\"10.1158/1078-0432.CCR-14-0990\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWu J, Gensheimer MF, Dong X, Rubin DL, Napel S, Diehn M, et al. Robust Intratumor Partitioning to Identify High-Risk Subregions in Lung Cancer: A Pilot Study. Int J Radiat Oncol Biol Phys. 2016;95:1504\u0026ndash;12. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.ijrobp.2016.03.018\u003c/span\u003e\u003cspan address=\"10.1016/j.ijrobp.2016.03.018\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSch\u0026uuml;rch CM, Bhate SS, Barlow GL, Phillips DJ, Noti L, Zlobec I, et al. Coordinated Cellular Neighborhoods Orchestrate Antitumoral Immunity at the Colorectal Cancer Invasive Front. Cell. 2020;182:1341\u0026ndash;e135919. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.cell.2020.07.005\u003c/span\u003e\u003cspan address=\"10.1016/j.cell.2020.07.005\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJi AL, Rubin AJ, Thrane K, Jiang S, Reynolds DL, Meyers RM, et al. Multimodal Analysis of Composition and Spatial Architecture in Human Squamous Cell Carcinoma. Cell. 2020;182:497\u0026ndash;e51422. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.cell.2020.05.039\u003c/span\u003e\u003cspan address=\"10.1016/j.cell.2020.05.039\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZheng L, Qin S, Si W, Wang A, Xing B, Gao R, et al. Pan-cancer single-cell landscape of tumor-infiltrating T cells. Science. 2021;374:abe6474. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1126/science.abe6474\u003c/span\u003e\u003cspan address=\"10.1126/science.abe6474\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTravis WD, Dacic S, Wistuba I, Sholl L, Adusumilli P, Bubendorf L, et al. IASLC Multidisciplinary Recommendations for Pathologic Assessment of Lung Cancer Resection Specimens After Neoadjuvant Therapy. J Thorac Oncol. 2020;15:709\u0026ndash;40. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.jtho.2020.01.005\u003c/span\u003e\u003cspan address=\"10.1016/j.jtho.2020.01.005\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eFedorov A, Beichel R, Kalpathy-Cramer J, Finet J, Fillion-Robin J-C, Pujol S, et al. 3D Slicer as an image computing platform for the Quantitative Imaging Network. Magn Reson Imaging. 2012;30:1323\u0026ndash;41. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.mri.2012.05.001\u003c/span\u003e\u003cspan address=\"10.1016/j.mri.2012.05.001\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLi M, Li X, Guo Y, Miao Z, Liu X, Guo S, et al. Development and assessment of an individualized nomogram to predict colorectal cancer liver metastases. Quant Imaging Med Surg. 2020;10:397\u0026ndash;414. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.21037/qims.2019.12.16\u003c/span\u003e\u003cspan address=\"10.21037/qims.2019.12.16\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003evan Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, et al. Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res. 2017;77:e104\u0026ndash;7. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1158/0008-5472.CAN-17-0339\u003c/span\u003e\u003cspan address=\"10.1158/0008-5472.CAN-17-0339\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLahiri A, Maji A, Potdar PD, Singh N, Parikh P, Bisht B, et al. Lung cancer immunotherapy: progress, pitfalls, and promises. Mol Cancer. 2023;22:40. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1186/s12943-023-01740-y\u003c/span\u003e\u003cspan address=\"10.1186/s12943-023-01740-y\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLi F, Zhai S, Lv Z, Yuan L, Wang S, Jin D, et al. Effect of histology on the efficacy of immune checkpoint inhibitors in advanced non-small cell lung cancer: A systematic review and meta-analysis. Front Oncol. 2022;12:968517. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fonc.2022.968517\u003c/span\u003e\u003cspan address=\"10.3389/fonc.2022.968517\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLiu C, Zhao W, Xie J, Lin H, Hu X, Li C, et al. Development and validation of a radiomics-based nomogram for predicting a major pathological response to neoadjuvant immunochemotherapy for patients with potentially resectable non-small cell lung cancer. Front Immunol. 2023;14:1115291. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fimmu.2023.1115291\u003c/span\u003e\u003cspan address=\"10.3389/fimmu.2023.1115291\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTian Y, Zhai X, Yan W, Zhu H, Yu J. Clinical outcomes of immune checkpoint blockades and the underlying immune escape mechanisms in squamous and adenocarcinoma NSCLC. Cancer Med. 2021;10:3\u0026ndash;14. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1002/cam4.3590\u003c/span\u003e\u003cspan address=\"10.1002/cam4.3590\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eChiou VL, Burotto M. Pseudoprogression and Immune-Related Response in Solid Tumors. J Clin Oncol. 2015;33:3541\u0026ndash;3. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1200/JCO.2015.61.6870\u003c/span\u003e\u003cspan address=\"10.1200/JCO.2015.61.6870\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHuang S, Yang J, Shen N, Xu Q, Zhao Q. Artificial intelligence in lung cancer diagnosis and prognosis: Current application and future perspective. Semin Cancer Biol. 2023;89:30\u0026ndash;7. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.semcancer.2023.01.006\u003c/span\u003e\u003cspan address=\"10.1016/j.semcancer.2023.01.006\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHan X, Wang M, Zheng Y, Wang N, Wu Y, Ding C, et al. Delta-radiomics features for predicting the major pathological response to neoadjuvant chemoimmunotherapy in non-small cell lung cancer. Eur Radiol. 2024;34:2716\u0026ndash;26. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00330-023-10241-x\u003c/span\u003e\u003cspan address=\"10.1007/s00330-023-10241-x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eShe Y, He B, Wang F, Zhong Y, Wang T, Liu Z, et al. Deep learning for predicting major pathological response to neoadjuvant chemoimmunotherapy in non-small cell lung cancer: A multicentre study. EBioMedicine. 2022;86:104364. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.ebiom.2022.104364\u003c/span\u003e\u003cspan address=\"10.1016/j.ebiom.2022.104364\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWu L, Yan J, Bai Y, Chen F, Zou X, Xu J, et al. An invasive zone in human liver cancer identified by Stereo-seq promotes hepatocyte-tumor cell crosstalk, local immunosuppression and tumor progression. Cell Res. 2023;33:585\u0026ndash;603. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1038/s41422-023-00831-1\u003c/span\u003e\u003cspan address=\"10.1038/s41422-023-00831-1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eFeng Y, Ma W, Zang Y, Guo Y, Li Y, Zhang Y, et al. Spatially organized tumor-stroma boundary determines the efficacy of immunotherapy in colorectal cancer patients. Nat Commun. 2024;15:10259. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1038/s41467-024-54710-3\u003c/span\u003e\u003cspan address=\"10.1038/s41467-024-54710-3\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBerghoff AS, Rajky O, Winkler F, Bartsch R, Furtner J, Hainfellner JA, et al. Invasion patterns in brain metastases of solid cancers. Neuro Oncol. 2013;15:1664\u0026ndash;72. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1093/neuonc/not112\u003c/span\u003e\u003cspan address=\"10.1093/neuonc/not112\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJoo L, Park JE, Park SY, Nam SJ, Kim Y-H, Kim JH, et al. Extensive peritumoral edema and brain-to-tumor interface MRI features enable prediction of brain invasion in meningioma: development and validation. Neuro Oncol. 2021;23:324\u0026ndash;33. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1093/neuonc/noaa190\u003c/span\u003e\u003cspan address=\"10.1093/neuonc/noaa190\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLi N, Mo Y, Huang C, Han K, He M, Wang X, et al. A Clinical Semantic and Radiomics Nomogram for Predicting Brain Invasion in WHO Grade II Meningioma Based on Tumor and Tumor-to-Brain Interface Features. Front Oncol. 2021;11:752158. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fonc.2021.752158\u003c/span\u003e\u003cspan address=\"10.3389/fonc.2021.752158\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZhao Z, Nie C, Zhao L, Xiao D, Zheng J, Zhang H, et al. Multi-parametric MRI-based machine learning model for prediction of WHO grading in patients with meningiomas. Eur Radiol. 2024;34:2468\u0026ndash;79. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00330-023-10252-8\u003c/span\u003e\u003cspan address=\"10.1007/s00330-023-10252-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJiang M, Sun Y, Yang C, Wang Z, Xie M, Wang Y, et al. Radiomics based on brain-to-tumor interface enables prediction of metastatic tumor type of brain metastasis: a proof-of-concept study. Radiol Med. 2024. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s11547-024-01934-4\u003c/span\u003e\u003cspan address=\"10.1007/s11547-024-01934-4\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZhou F, Qiao M, Zhou C. The cutting-edge progress of immune-checkpoint blockade in lung cancer. Cell Mol Immunol. 2021;18:279\u0026ndash;93. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1038/s41423-020-00577-5\u003c/span\u003e\u003cspan address=\"10.1038/s41423-020-00577-5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYe G, Wu G, Zhang C, Wang M, Liu H, Song E, et al. CT-based quantification of intratumoral heterogeneity for predicting pathologic complete response to neoadjuvant immunochemotherapy in non-small cell lung cancer. Front Immunol. 2024;15:1414954. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fimmu.2024.1414954\u003c/span\u003e\u003cspan address=\"10.3389/fimmu.2024.1414954\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWang F, Yang H, Chen W, Ruan L, Jiang T, Cheng L, et al. A combined model using pre-treatment CT radiomics and clinicopathological features of non-small cell lung cancer to predict major pathological responses after neoadjuvant chemoimmunotherapy. Curr Probl Cancer. 2024;50:101098. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.currproblcancer.2024.101098\u003c/span\u003e\u003cspan address=\"10.1016/j.currproblcancer.2024.101098\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHu Y, Jiang T, Wang H, Song J, Yang Z, Wang Y, et al. Ct-based subregional radiomics using hand-crafted and deep learning features for prediction of therapeutic response to anti-PD1 therapy in NSCLC. Phys Med. 2024;117:103200. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.ejmp.2023.103200\u003c/span\u003e\u003cspan address=\"10.1016/j.ejmp.2023.103200\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCui L, Yu T, Kan Y, Dong Y, Luo Y, Jiang X. Multi-parametric MRI-based peritumoral radiomics on prediction of lymph-vascular space invasion in early-stage cervical cancer. Diagn Interv Radiol. 2022;28:312\u0026ndash;21. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.5152/dir.2022.20657\u003c/span\u003e\u003cspan address=\"10.5152/dir.2022.20657\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eXu H, Lv W, Feng H, Du D, Yuan Q, Wang Q, et al. Subregional Radiomics Analysis of PET/CT Imaging with Intratumor Partitioning: Application to Prognosis for Nasopharyngeal Carcinoma. Mol Imaging Biol. 2020;22:1414\u0026ndash;26. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s11307-019-01439-x\u003c/span\u003e\u003cspan address=\"10.1007/s11307-019-01439-x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePietras K, Ostman A. Hallmarks of cancer: interactions with the tumor stroma. Exp Cell Res. 2010;316:1324\u0026ndash;31. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.yexcr.2010.02.045\u003c/span\u003e\u003cspan address=\"10.1016/j.yexcr.2010.02.045\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJoyce JA, Pollard JW. Microenvironmental regulation of metastasis. Nat Rev Cancer. 2009;9:239\u0026ndash;52. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1038/nrc2618\u003c/span\u003e\u003cspan address=\"10.1038/nrc2618\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-cancer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bcan","sideBox":"Learn more about [BMC Cancer](http://bmccancer.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bcan/default.aspx","title":"BMC Cancer","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Radiomics, Neoadjuvant immunochemotherapy, Major pathological response, Non-small cell lung cancer, nomogram","lastPublishedDoi":"10.21203/rs.3.rs-7531855/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7531855/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cb\u003eBackground\u003c/b\u003e Accurate prediction of tumor response to neoadjuvant immunochemotherapy (NAIC) enables personalized perioperative therapy for resectable non-small cell lung cancer (NSCLC).\u003c/p\u003e\u003cp\u003e\u003cb\u003eObjective\u003c/b\u003e The present aimed to evaluate the predictive value of radiomics derived from the tumor-parenchyma invasive zone for response to NAIC in resectable NSCLC, with the goal of developing a more accurate and clinically applicable model.\u003c/p\u003e\u003cp\u003e\u003cb\u003eMethods\u003c/b\u003e Patients with pathologically proven NSCLC from August 2019 and March 2025 were retrospectively included from two medical centers. In the training set, radiomics features were extracted from the whole tumor region and tumor margin region (6mm) respectively. Following feature selection via intraclass correlation coefficient and least absolute shrinkage and selection operator, the Whole Tumor Model (WTM) and Tumor Margin model (TMM) were developed to non-invasively predict major pathological response (MPR) following NAIC. The performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value, and negative predictive value in the internal validation and external test sets. The optimal radiomics model and clinical characteristics were combined to build the hybrid model (HM).\u003c/p\u003e\u003cp\u003e\u003cb\u003eResults\u003c/b\u003e A total of 169 patients (median age, 60 years; 154 men) were divided into training, internal validation and external test sets, with 104 patients (61.5%) achieving MPR. In the test dataset, WTM and TMM achieved AUCs of 0.71 (95% CI: 0.54\u0026ndash;0.89) and 0.84 (95% CI: 0.71\u0026ndash;0.97), respectively. After incorporating tumor margin radiomics features and clinical predictors(pathology), the HM demonstrated satisfactory performance in the training set (AUC: 0.88, 95% CI: 0.81\u0026ndash;0.95) and internal validation set (AUC: 0.86, 95% CI: 0.74\u0026ndash;0.98). In the independent external test set, the HM obtained satisfactory performance (AUC\u0026thinsp;=\u0026thinsp;0.87, 95% CI: 0.76\u0026ndash;0.98). Decision curves analysis indicated that the radiomics-clinical combined nomogram provided significant clinical utility.\u003c/p\u003e\u003cp\u003e\u003cb\u003eConclusion\u003c/b\u003e A radiomics model based on the tumor margin region outperformed the whole-tumor model in predicting MPR in NSCLC. Our study developed a novel tool to predict the response of NSCLC to NAIC, which demonstrated excellent performance.\u003c/p\u003e","manuscriptTitle":"Radiomics Based on the Tumor–Parenchyma Invasive Interface Predicts Major Pathological Response to Neoadjuvant Immunochemotherapy in Non-small Cell Lung Cancer","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-12 14:09:03","doi":"10.21203/rs.3.rs-7531855/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2025-10-15T01:38:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"301643796259394781446611084288664810380","date":"2025-10-07T22:57:41+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-29T11:20:07+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-23T09:43:42+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-09-05T09:20:19+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-05T04:42:29+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Cancer","date":"2025-09-05T04:39:10+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-cancer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bcan","sideBox":"Learn more about [BMC Cancer](http://bmccancer.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bcan/default.aspx","title":"BMC Cancer","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"5faf4d82-b3e8-479b-81f9-8fe745f600fa","owner":[],"postedDate":"October 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-10-12T14:09:03+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-12 14:09:03","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7531855","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7531855","identity":"rs-7531855","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}