CT-Based Radiomic Nomogram for Preoperative Prediction of Ki-67 in Lung Neuroendocrine Neoplasms: A Multicenter Study

CT-Based Radiomic Nomogram for Preoperative Prediction of Ki-67 in Lung Neuroendocrine Neoplasms: A Multicenter Study | 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 CT-Based Radiomic Nomogram for Preoperative Prediction of Ki-67 in Lung Neuroendocrine Neoplasms: A Multicenter Study Xiao Pan, Yanni Zou, Xiaoxiao Huang, Tao Li, Quan Zhang, Jing Hu, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7705743/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 24 Jan, 2026 Read the published version in BMC Medical Imaging → Version 1 posted 12 You are reading this latest preprint version Abstract Objective The Lung neuroendocrine neoplasms (L-NENs) are increasingly recognised, yet reliable pre-operative assessment of the Ki-67 proliferation index remains invasive and heterogeneous. We aimed to develop and validate a clinical-radiomics nomogram that uses routine chest CT to estimate Ki-67 status in patients with L-NENs. Methods In this retrospective multicentre study, 199 patients (four hospitals, January 2014–December 2024) with histologically confirmed L-NENs and pre-operative dual-phase contrast-enhanced CT were included. After manual 3D tumour segmentation, 1,874 radiomics features were extracted from fused unenhanced and arterial / venous-phase images. Feature selection combined Pearson correlation (r > 0.8 removed) and LASSO regression. Five classifiers were compared; logistic regression (LR) performed best and was used to build a radiomics signature (Rad-score). Clinical predictors of Ki-67 were identified by multivariable logistic regression and integrated with the Rad-score to construct a nomogram. Discrimination, calibration and clinical utility were assessed by AUC, calibration plot and decision curve analysis in training (n = 116), internal testing (n = 50) and external validation (n = 33) sets. Results High Ki-67 (> 30%) was present in 119 (59.8%) patients. The LR radiomics model yielded AUCs of 0.912 (95% CI 0.858–0.965) and 0.943 (0.887–0.999) in training and testing sets, respectively. Independent clinical predictors were largest tumour diameter, smoking history and age. The combined nomogram achieved AUCs of 0.958 (0.925–0.990), 0.930 (0.865–0.995) and 0.911 (0.867–0.955) in training, testing and external validation sets, with good calibration and superior net benefit on decision-curve analysis. Conclusion The CT-based clinical–radiomics nomogram provides an accurate, non-invasive tool for pre-operative Ki-67 estimation in L-NENs, potentially guiding treatment decisions. Prospective, larger-scale validation is warranted. Clinical trial number: Not applicable. Lung Neuroendocrine Neoplasm Nomogram prediction Radiomics Ki-67 Machine learning Multicenter study Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Background Lung neuroendocrine neoplasms (L-NENs), which arise from neuroendocrine and peptidergic cells in the bronchial mucosa and submucosal glands, account for about 20% of lung malignancies [ 1 ]. Possibly due to improved diagnostic techniques and growing clinical awareness, the prevalence of NENs is steadily increasing [ 2 ]. In terms of the World Health Organization's diagnosis and classification standards, L-NENs are categorized according to tumor necrosis and mitotic index, as well as neuroendocrine tumor appearance, which is verified by immunohistochemistry (IHC) staining for neuroendocrine markers. Typical carcinoid and atypical carcinoid are classified as well-differentiated neuroendocrine tumors (NETs), while large cell neuroendocrine carcinoma (LCNEC) and small cell lung carcinoma (SCLC) are categorized as poorly differentiated neuroendocrine carcinomas (NECs).[ 3 ]. Significant crushing artifacts frequently occur in tissue fragments acquired via preoperative biopsy, hindering the evaluation of mitotic counts and complicating the interpretation of morphological images and precise preoperative diagnosis. In such cases, the Ki-67 proliferation index (PI) is highly valuable [ 4 ]. The WHO lists the Ki-67 antigen, a well-known cell proliferation marker, as a non-mandatory but desirable criterion for L-NENs, in which ≤ 5%, 30% Ki-67-positive cells indicate typical carcinoids (TC), atypical carcinoids (AC), and neuroendocrine carcinoma (small or large cell subtypes), respectively [ 3 ]. Although the current grading system does not incorporate Ki-67 for staging L-NENs, Ki-67 IHC testing of biopsy samples is vital for differentiating between NETs and NECs and preventing misdiagnosis [ 4 , 5 ]. Radical surgery remains optimal for TC and early-stage atypical AC with Ki-67 < 30%. LCNEC and SCLC, characterized by high Ki-67 levels and high-grade malignancy, exhibit significant rates of local and systemic metastases, with treatment primarily involving a combination of radiotherapy and chemotherapy [ 6 ]. Furthermore, patients with TC with increased Ki-67 expression show significantly reduced survival [ 7 ]. Preoperative Ki-67 expression is primarily assessed through IHC testing, which involves obtaining tissue samples by puncture and evaluating them by routine visual observation by a pathologist [ 8 – 10 ]. Owing to tumor heterogeneity and the relatively small sample size, Ki-67 evaluation based on biopsy samples may not accurately represent the entire tumor. Furthermore, biopsy sampling is invasive and non-repeatable. Additionally, in many critical cases where core needle biopsies are not feasible, Ki-67 assessment is unavailable.here is a pressing need to establish reliable, advanced, and noninvasive techniques for the accurate prediction of Ki-67 status in L-NEN cases, which could significantly improve clinical management and treatment outcomes. Radiomics offers comprehensive and quantitative tumor measurements to facilitate non-invasive,comprehensive analysis of tumor phenotypes. This technique provides significant insights into clinical diagnosis and prognosis prediction. It is frequently employed in diagnosing, treating, and prognostic evaluating various cancers, offering a valuable tool for enhancing treatment strategies and patient outcomes [ 11 ]. Radiomics can help improve tumor behavior and patient treatment management comprehension by extracting high-throughput data from medical images, leading to more personalized and precise medical care [ 12 – 15 ]. However, limited research has been conducted to evaluate the potential of radiomics in assessing Ki-67 expression levels in L-NENs..Meyer et al. [ 16 ] assessed chest computed tomography (CT) scans in patients' plain and arterial phases from the same institution and identified several CT texture features correlated with the PI of the lung neuroendocrine Ki-67 antigen to differentiate TC and AC potentially. Another single-institution study analyzing baseline and venous-phase chest CT images obtained using different CT scanner models demonstrated a correlation between texture features and the histological heterogeneity of L-NENs, Ki-67 values, and metastatic foci. Thus, textural features may help assess tumor type and aggressiveness in L-NENs [ 17 ]. However, these single-centre studies did not establish effective predictive models. As a result, this study intended to develop a radiographic score using plain and dual-phase enhanced CT fusion images from various hospitals and to create a nomogram for the prediction of Ki-67 PI levels in L-NENs by amalgamating clinical data and imaging characteristics.Additionally, the study evaluated this model's performance and generalisability, aiming to serve clinical diagnosis and treatment better while alleviating patient suffering. Research Methodology Patients The four participating hospitals' institutional ethics committees authorized this retrospective study, eliminating the need for informed consent. This study was carried out in full compliance with the ethical principles set forth in the Declaration of Helsinki.The study examined data from consecutive patients with pathologically diagnosed L-NENs at the Guangxi Medical University Cancer Hospital (Centre 2) and the First Affiliated Hospital of Guangxi Medical University (Centre 1) between January 2014 and April 2024, as well as at the Guangxi Zhuang Autonomous Region Chest Hospital (Centre 4) and the Liuzhou Workers' Hospital (Centre 3) between January 2019 and April 2024. The inclusion criteria were: (1) Diagnosis of L-NENs through surgical pathology specimens and immunohistochemical examination, and (2) preoperative chest CT scan with dual-phase enhancement. The following were the exclusion criteria: (1) no Ki-67 immunohistochemistry data; (2) poor image quality with severe artifacts; (3) tumor too small (largest diameter < 5 mm); (4) incomplete clinical data; (5) Received radiotherapy or chemotherapy before surgery; (6) The tumor with non-small cell carcinoma components. Patients from Centers 1–4, 112, 54, 19, and 14 were selected according to the above criteria. For model development, the 166 patients from Centers 1 and 2 were subsequently divided into training (n = 116) and test (n = 50) cohorts at random in a 7:3 proportion ratio. The external validation cohort comprised the 33 patients from Centers 3 and 4. Figure 1 depicts the patient selection procedure. CT examinations The detailed CT protocol is provided in the Supplementary Material1. Evaluation of radiological features and clinical data Clinical data, including sex, age, and smoking status, were extracted from each patient's electronic medical records system. Two chest radiologists with 10 and 20 years of expertise in interpreting chest imaging evaluated CT pictures, which included both contrast-enhanced and non-contrast images. They were blinded to the pathological and clinical results. Consensus was used to settle disagreements. The radiological characteristics listed below were assessed: (1) longest tumor diameter (cm) on axial images; (2) spiculation sign; (3) liquefaction necrosis; (4) calcification; and (5) obstructive pneumonia. A sharp, linear protrusion between the tumor and the surrounding lung parenchyma was identified as the spiculation sign [ 18 ]. Immunohistochemical analysis of Ki-67 index After being fixed in 10% neutral buffered formalin, each sample was regularly dehydrated, embedded in paraffin, and cut into 4-micron-thick slices. Using the Ventana Benchmark Ultra automated IHC staining equipment (Roche Ventana, Inc.), Ki-67 was detected for proliferation by IHC. The percentage of positive tumor cell nuclei was referred to as the PI, and cells with brownish nuclei were considered Ki-67-positive. Based on the Ki-67 PI, L-NENs were divided into low (PI ≤ 30%) and high (PI > 30%) expression groups [ 3 ]. Tumor segmentation and feature extraction The Picture Archiving and Communication System (PACS) provided the CT images, which were then converted to Digital Imaging and Communications in Medicine (DICOM) format. 3D Slicer 5.2.2 ( https://www.slicer.org ), was used to segment the images. All CT image slices were reviewed in each patient to select the slice with the largest tumor area for measuring the maximum tumour diameter. In the present study, all extraction and selection of CT features were completed using UltraScholar 2.0 (Shukun Network Technology Co., Ltd., Beijing). To define the volumes of interest (VOIs), a 3D slicer was utilized for manual delineation of tumor areas on axial CT images in the plain, arterial, and venous phases of the CT scan. To assess intra-observer reliability, radiologist A re-segmented 30 randomly selected cases after two weeks. Furthermore, to assess interobserver reliability, a second radiologist (B) independently segmented these 30 instances without informing either radiologist of the histological findings. Before feature extraction, the obtained pictures underwent pre-processing, which involved normalization, modification of image resolution to 1×1×1 mm³ by B-spline interpolation, and discretization of grey levels using a fixed bin width 25. The plain and dual-phase-enhanced fusion images yielded 1,874 radiomic features in total, comprising 1,500 second-order (texture) characteristics, 360 first-order (histogram) features, and 14 shape features.The workflow is illustrated in Fig. 2 . Features with an intraclass correlation coefficient (ICC) and an intra-reader correlation coefficient, both exceeding 0.75, were deemed to show satisfactory agreement. Feature selection and model building First, the system identified anomalies where features have different names but identical values during pre-processing and removed features with identical values after processing. Second, Pearson correlation coefficients were utilized to remove redundancy, using a correlation coefficient threshold 0.8. The pertinent characteristics were selected by Least Absolute Shrinkage and Selection Operator (LASSO) assessments. After that, radiomic signatures were developed using five machine learning algorithms: logistic regression (LR), support vector machine (SVM), extreme gradient boosting (XGBoost), Gaussian Naive Bayes (GaussianNB), and linear support vector machine (LinearSVC). The training cohort underwent ten-fold cross-validation, and the test cohort's outcomes were assessed. For the external cohort, the optimal model was then applied. Significant clinical factors and radiological features were investigated as independent risk predictors of Ki-67 status L-NEN cases by univariate and multivariate analyses following the completion of chi-square tests and independent samples t-tests. The clinical model was developed using clinical parameters that had a P -value of < 0.05 in these analyses. The radiomic score and the clinical signature were merged in the radiomic nomogram. Statistical analysis R version 4.4.0 (R Foundation for Statistical Computing, Vienna, Austria) and SPSS 26.0 (IBM Corp., Armonk, NY, USA) were employed for all statistical analyses. The Mann-Whitney and Chi-square tests assessed the qualitative and categorical variables, respectively. P < 0.05 represented statistical significance. The AUCs of ROC curves were utilized to assess the models' diagnostic performance in differentiating between the high and low Ki-67 groups. Decision curve analysis (DCA) was utilized for assessing the clinical applicability of the models. Results Patient characteristics This retrospective study enrolled 199 patients in total, including 143 males (71.86%) and 56 females (28.14%), with a median age of 59 years. The high (Ki > 30%) and low (Ki ≤ 30%) Ki-67 status groups included 119 (59.8%) and 80 (40.2%) patients, respectively.Radiological CT features and the clinical data of L-NENs in each cohort are summarised in Table 1. Age, sex, smoking status, and longest diameter significantly correlated with high Ki-67 expression in univariate analysis ( P < 0.05). The radiomic-clinical nomogram contained the following independent characteristics that influenced Ki-67 expression in multi-variable logistic regression: smoking status (OR: 12.80, P < 0.001), largest tumor diameter (OR: 1.79, P < 0.001), and age ( [OR]: 1.09, P = 0.006) (Table 2). Radiomic-based model performance A radiological model was constructed using four characteristics with non-zero coefficients based on the most effective features in the feature selection process (Fig. 3 ). With AUCs of 0.912 (95% CI: 0.858–0.965) in the training set and 0.943 (95% CI: 0.887–0.999) in the testing set, the LR algorithm showed strong performance(Table 3 ). The output was converted into a Radscore to signify the relative risk associated with a high Ki-67 status. This approach was designated as the radiomic model. Construction and validation of the radiomic nomogram Using the three independent predictors of age, maximum tumor diameter, and smoking status, a clinical model associated with Ki-67 levels was developed. In the training, testing, and external validation sets, the model's AUC values were 0.898 (95%CI: 0.841–0.955), 0.863 (95%CI: 0.749–0.978), and 0.882 (95%CI: 0.828–0.936), respectively (Fig. 4 ., Table 4). Figure 4 .shows the ROC curves for the clinical, radiomics, and clinical-radiomics nomogram models for the training, testing, and external validation populations. The AUC values, sensitivity, specificity, accuracy, F1 score, positive predictive value (PPV), and negative predictive value (NPV) for the individual models are detailed in Table 4. In the training, testing, and external validation cohorts, the nomogram for clinical-radiomics showed the best diagnostic performance for Ki-67 PI expression, with AUC values of 0.958 (95%CI: 0.925–0.990), 0.930 (95%CI: 0.865–0.995), and 0.911 (95%CI: 0.867–0.955), respectively. The DeLong test indicated that the training cohort's nomogram and clinical models had significantly different AUCs. However, there was a insignificant difference between the models in the internal and external validation sets ( P > 0.05) and between the AUCs of the radiomics model and the nomogram ( P = 0.23). Per the calibration curve analysis, the nomogram model exhibits good agreement with the actual trends in the training, testing, and external validation sets (Fig. 5 ). The DCA (Fig. 6 ) also indicates that, compared to radiological and clinical parameters models, the nomogram model tends to show a marginal net benefit in differentiating between individuals with high and low Ki-67 PI levels within the most appropriate threshold probability ranges. Discussion In this multicenter retrospective study we constructed and externally validated a CT-based radiomics nomogram that fuses quantitative imaging features with routine clinical variables (age, largest tumor diameter, and smoking history) to pre-operatively estimate the probability of Ki-67 > 30% in lung neuroendocrine neoplasms (L-NENs). Although the proposed model achieved high AUCs of 0.958, 0.930 and 0.911 in the training, internal testing and external validation cohorts, respectively, several methodological considerations merit cautious interpretation of these results. First, radiomic analyses are intrinsically high-dimensional and vulnerable to overfitting when the number of extracted features exceeds the number of clinical events [ 19 ]. We attempted to mitigate this risk by removing highly correlated variables (Pearson |r|>0.8), applying LASSO logistic regression with 10-fold cross-validation, and evaluating the final model in an independent external data set. Nevertheless, the external validation cohort comprised only 33 patients, producing a 95% confidence interval that remains wide (0.867–0.955) and whose upper bound approaches unity, suggesting that random variation may partly explain the observed performance (authors’inference), consistent with reports of unstable AUC estimates in small external cohorts [ 20 ]. Larger, prospective, geographically distinct cohorts scanned with heterogeneous CT platforms are required to confirm generalizability. Second, all four radiomic features retained in our logistic regression model belong to the grey-level size-zone matrix (GLSZM) family, which quantifies intra-tumoral heterogeneity. Previous single-centre studies have correlated GLSZM parameters with Ki-67 expression in pulmonary and other neoplasms [ 16 , 21 ], providing biological plausibility for our findings. Likewise, recent radiomics models for Ki-67 in sinonasal malignancies[ 22 ] and hepatocellular carcinoma[ 23 ] confirm the added value of high-order texture features, reinforcing the biological link between intra-tumoral heterogeneity and proliferation. However, radiomic surrogates remain indirect; integration with digital pathology or multi-omic profiling will be necessary to uncover mechanistic links between imaging phenotypes and tumor proliferation [ 11 ]. Third, multivariable analysis generated an odds ratio of 12.8 (95% CI 3.4–48.3) for smoking history, reflecting the marked imbalance in our cohort (85% of smokers versus 28% of non-smokers had Ki-67 > 30%) and the limited number of events, both of which can inflate point estimates. Comparable extreme odds ratios have been reported in small-sample radiomics studies for multiple myeloma [ 24 ] and bladder cancer [ 25 ], where sparse-event logistic regression was likewise employed. Bootstrapping or Bayesian shrinkage methods should be considered in future work to obtain more stable effect sizes. Finally, decision curve analysis indicated a marginal net benefit for the nomogram within the threshold probability range of 15–70%. However, DCA does not incorporate real-world costs such as unnecessary biopsies, false-positive downstream imaging, or patient anxiety [ 26 ]. Prospective interventional trials are therefore needed to determine whether application of the nomogram truly alters clinical management and to evaluate cost-effectiveness before widespread adoption . Limitations Our investigation has several limitations. (1) The retrospective design predisposes to selection and ascertainment bias. (2) The external validation sample was small (n = 33), limiting precision of performance estimates. (3) All L-NEN subtypes were pooled; subtype-specific models might yield better accuracy. (4) Ki-67 assessment followed local pathology protocols without central review. (5) Cost-utility and impact on patient outcomes were not evaluated. Larger prospective studies that address these issues are warranted. Conclusions A nomogram combining CT radiomics and routinely available clinical variables can estimate the likelihood of Ki-67 > 30% in patients with lung neuroendocrine neoplasms with good discrimination and appropriate calibration. These findings justify larger prospective studies to verify generalizability, define clinical utility, and determine whether the model safely reduces invasive procedures or improves treatment planning. Abbreviations AC atypical carcinoids DICOM digital imaging and communications in medicine DCA decision curve analysis AUC the area under the curve CT computed tomography GLSZM grey level size zone matrix IHC immunohistochemical L-NENs lung neuroendocrine neoplasms NETs neuroendocrine tumors NENs neuroendocrine neoplasms NECs neuroendocrine carcinomas ROC receiver operating curve PACS picture archiving and communication system PI proliferation index SCLC small-cell lung cancer LCNEC large-cell neuroendocrine carcinomas of the lung TC typical carcinoids VOI volume of interest Declarations Ethics approval and consent to participate This retrospective study, conducted in accordance with the Declaration of Helsinki, received approval from the institutional review boards of The First Affiliated Hospital of Guangxi Medical University (approval No. 2025-E0595), Guangxi Medical University Cancer Hospital (approval No. KY-2022-301), Liuzhou Worker’s Hospital (approval No. KY2025614), and The Chest Hospital of Guangxi Zhuang Autonomous Region (approval No. 2023-S004-01), each of which waived the requirement for informed patient consent. Consent for publication Not applicable. Data availability The data supporting this study are available from the corresponding author upon reasonable request but may be restricted to protect patient confidentiality and comply with ethical guidelines, given the study's retrospective design. Competing interests The authors declare that they have no competing interests except Jing Hu, who is employed as a senior clinical scientist by ShuKun (Beijing) Technology Co., Ltd. This company had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Funding This work was supported by① the Joint Regional Epidemic Disease Research Grant (project No. 2022JJA140455), titled ‘A quantitative MRI study of pituitary iron deposition in patients with Mediterranean anemia’;② the Provincial Science and Technology Program (project No. S2022072), titled ‘A quantitative study on the correlation between hepatic iron deposition and glucose metabolism in Mediterranean anemia using multimodal MRI’. Authors' contributions Xiao Pan, Yanni Zou, Tao Li, Peng Pengm, and Wenhua Zhao contributed to the study conception and design. Material preparation and data collection were performed by Xiao Pan, Yanni Zou, Xiaoxiao Huang, and Quan Zhang. Data analyses were performed by Xiao Pan, Jing Hu. The first draft of the manuscript was written by Xiao Pan, Yanni Zou. Jing Hu is employed as a senior clinical scientist in a company in medical industry ShuKun (BeiJing) Technology Co., Ltd., who was contributed in statistical analysis/ manuscript editing and did not control the study. All authors commented on previous versions of the manuscript. All authors read and approved the final manuscript. Acknowledgements We would like to express our sincere gratitude to all the participants of our study, as well as to the hospitals involved for their generous support. At the same time, we extend our appreciation to Editage (www.editage.cn) for their assistance in English language editing. References Dam, Gitte, et al. Nordic 2023 guidelines for the diagnosis and treatment of lung neuroendocrine neoplasms. Acta Oncol. 2023;62(5):431-437. doi:10.1080/0284186X.2023.2212411 Chen SH, Chang YC, Hwang TL, et al. 68Ga-DOTATOC and 18F-FDG PET/CT for identifying the primary lesions of suspected and metastatic neuroendocrine tumors: A prospective study in Taiwan. J Formos Med Assoc. 2018;117(6):480-487. doi:10.1016/j.jfma.2017.07.007 WHO Classification of Tumours Editorial Board Thoracic tumours. WHO classification of tumours series, 5th ed.; vol. 5. Lyon: International Agency for Research on Cancer; 2021. La Rosa S. Diagnostic, Prognostic, and Predictive Role of Ki-67 Proliferative Index in Neuroendocrine and Endocrine Neoplasms: Past, Present, and Future. Endocr Pathol. 2023;34(1):79-97. doi:10.1007/s12022-023-09755-3 Pelosi G, Travis WD. Head-to-head: Should Ki67 proliferation index be included in the formal classification of pulmonary neuroendocrine neoplasms?. Histopathology. 2024;85(4):535-548. doi:10.1111/his.15206 Pelosi G, Travis WD. The Ki-67 antigen in the new 2021 World Health Organization classification of lung neuroendocrine neoplasms. Pathologica. 2021;113(5):377-387. doi:10.32074/1591-951X-542 Granberg D, Wilander E, Oberg K, Skogseid B. Prognostic markers in patients with typical bronchial carcinoid tumors. J Clin Endocrinol Metab. 2000;85(9):3425-3430. doi:10.1210/jcem.85.9.6785 MacCallum DE, Hall PA. The location of pKi67 in the outer dense fibrillary compartment of the nucleolus points to a role in ribosome biogenesis during the cell division cycle. J Pathol. 2000;190(5):537-544. doi:10.1002/(SICI)1096-9896(200004)190:53.0.CO;2-W Gerdes J, Li L, Schlueter C, et al. Immunobiochemical and molecular biologic characterization of the cell proliferation-associated nuclear antigen that is defined by monoclonal antibody Ki-67. Am J Pathol. 1991;138(4):867-873. Kim HS, Park S, Koo JS, et al. Risk Factors Associated with Discordant Ki-67 Levels between Preoperative Biopsy and Postoperative Surgical Specimens in Breast Cancers. PLoS One. 2016;11(3):e0151054. Published 2016 Mar 8. doi:10.1371/journal.pone.0151054 Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer. 2012;48(4):441-446. doi:10.1016/j.ejca.2011.11.036 Zhang H, Qi L, Cai Y, Gao X. Gastrin-releasing peptide receptor (GRPR) as a novel biomarker and therapeutic target in prostate cancer. Ann Med. 2024;56(1):2320301. doi:10.1080/07853890.2024.2320301 Angelone, F, Ciliberti, F, Tobia, G, et al. Innovative Diagnostic Approaches for Predicting Knee Cartilage Degeneration in Osteoarthritis Patients: A Radiomics-Based Study INFORM SYST FRONT. 2024; doi: 10.1007/s10796-024-10527-5 Cheng L, Gao H, Wang Z, Guo L, Wang X, Jin G. Prospective study of dual-phase 99mTc-MIBI SPECT/CT nomogram for differentiating non-small cell lung cancer from benign pulmonary lesions [published correction appears in Eur J Radiol. 2024 Sep 5;181:111704. doi: 10.1016/j.ejrad.2024.111704]. Eur J Radiol. 2024;179:111657. doi:10.1016/j.ejrad.2024.111657 Wu J, Ge L, Guo Y, Xu D, Wang Z. Utilizing multiclassifier radiomics analysis of ultrasound to predict high axillary lymph node tumour burden in node-positive breast cancer patients: a multicentre study. Ann Med. 2024;56(1):2395061. doi:10.1080/07853890.2024.2395061 Meyer HJ, Leonhardi J, Höhn AK, et al. CT Texture Analysis of Pulmonary Neuroendocrine Tumors-Associations with Tumor Grading and Proliferation. J Clin Med. 2021;10(23):5571. Published 2021 Nov 26. doi:10.3390/jcm10235571 Cozzi D, Bicci E, Cavigli E, et al. Radiomics in pulmonary neuroendocrine tumours (NETs). Radiol Med. 2022;127(6):609-615. doi:10.1007/s11547-022-01494-5 Gu Q, Feng Z, Liang Q, et al. Machine learning-based radiomics strategy for prediction of cell proliferation in non-small cell lung cancer. Eur J Radiol. 2019;118:32-37. doi:10.1016/j.ejrad.2019.06.025 Welch ML, McIntosh C, Haibe-Kains B, et al. Vulnerabilities of radiomic signature development: The need for safeguards. Radiother Oncol. 2019;130:2-9. doi:10.1016/j.radonc.2018.10.027 Liu J, Wang C, Guo W, et al. A preliminary study using spinal MRI-based radiomics to predict high-risk cytogenetic abnormalities in multiple myeloma. Radiol Med. 2021;126(9):1226-1235. doi:10.1007/s11547-021-01388-y Li Q, Song Z, Li X, et al. Development of a CT radiomics nomogram for preoperative prediction of Ki-67 index in pancreatic ductal adenocarcinoma: a two-center retrospective study. Eur Radiol. 2024;34(5):2934-2943. doi:10.1007/s00330-023-10393-w Bi S, Li J, Wang T, et al. Multi-parametric MRI-based radiomics signature for preoperative prediction of Ki-67 proliferation status in sinonasal malignancies: a two-centre study. Eur Radiol. 2022;32(10):6933-6942. doi:10.1007/s00330-022-08780-w Zhang D, Zhang XY, Lu WW, et al. Predicting Ki-67 expression in hepatocellular carcinoma: nomogram based on clinical factors and contrast-enhanced ultrasound radiomics signatures. Abdom Radiol (NY). 2024;49(5):1419-1431. doi:10.1007/s00261-024-04191-1 Liu J, Wang C, Guo W, et al. A preliminary study using spinal MRI-based radiomics to predict high-risk cytogenetic abnormalities in multiple myeloma. Radiol Med. 2021;126(9):1226-1235. doi:10.1007/s11547-021-01388-y Xiong S, Fu Z, Deng Z, et al. Machine learning-based CT radiomics enhances bladder cancer staging predictions: A comparative study of clinical, radiomics, and combined models. Med Phys. 2024;51(9):5965-5977. doi:10.1002/mp.17288 Vickers AJ, Van Calster B, Steyerberg EW. Net benefit approaches to the evaluation of prediction models, molecular markers, and diagnostic tests. BMJ. 2016;352:i6. Published 2016 Jan 25. doi:10.1136/bmj.i6 Tables Tables are available in the Supplementary Files section. Additional Declarations No competing interests reported. Supplementary Files Supplementarymaterial1.docx Tables.docx Cite Share Download PDF Status: Published Journal Publication published 24 Jan, 2026 Read the published version in BMC Medical Imaging → Version 1 posted Editorial decision: Revision requested 17 Nov, 2025 Reviews received at journal 13 Nov, 2025 Reviewers agreed at journal 13 Nov, 2025 Reviews received at journal 05 Nov, 2025 Reviews received at journal 22 Oct, 2025 Reviewers agreed at journal 13 Oct, 2025 Reviewers agreed at journal 11 Oct, 2025 Reviewers invited by journal 09 Oct, 2025 Editor assigned by journal 08 Oct, 2025 Editor invited by journal 08 Oct, 2025 Submission checks completed at journal 08 Oct, 2025 First submitted to journal 08 Oct, 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-7705743","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":531812481,"identity":"4282e12a-1908-41c6-908a-2cbc6fe0e32e","order_by":0,"name":"Xiao Pan","email":"","orcid":"","institution":"Liuzhou Worker’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Xiao","middleName":"","lastName":"Pan","suffix":""},{"id":531812482,"identity":"5c09016b-3f60-4543-809f-6f8690d3b29c","order_by":1,"name":"Yanni Zou","email":"","orcid":"","institution":"Chest Hospital of Guangxi Zhuang Autonomous Region","correspondingAuthor":false,"prefix":"","firstName":"Yanni","middleName":"","lastName":"Zou","suffix":""},{"id":531812483,"identity":"6c05ccd9-f375-4cfe-a394-5cda0060dd99","order_by":2,"name":"Xiaoxiao Huang","email":"","orcid":"","institution":"Guangxi Medical University Cancer Hospital","correspondingAuthor":false,"prefix":"","firstName":"Xiaoxiao","middleName":"","lastName":"Huang","suffix":""},{"id":531812484,"identity":"547bb554-27d6-464c-a247-d5408a6b890b","order_by":3,"name":"Tao Li","email":"","orcid":"","institution":"Liuzhou Worker’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Tao","middleName":"","lastName":"Li","suffix":""},{"id":531812485,"identity":"7569bd0c-d9c7-43a6-8108-0015ed386923","order_by":4,"name":"Quan Zhang","email":"","orcid":"","institution":"Guangxi Medical University Cancer Hospital","correspondingAuthor":false,"prefix":"","firstName":"Quan","middleName":"","lastName":"Zhang","suffix":""},{"id":531812486,"identity":"73932fab-631c-4d38-91f2-6b6467dedb94","order_by":5,"name":"Jing Hu","email":"","orcid":"","institution":"Shukun Technology Co.","correspondingAuthor":false,"prefix":"","firstName":"Jing","middleName":"","lastName":"Hu","suffix":""},{"id":531812487,"identity":"0cd3ac50-4515-4726-baff-9796089fd48a","order_by":6,"name":"Wenhua Zhao","email":"","orcid":"","institution":"Guangxi Medical University Cancer Hospital","correspondingAuthor":false,"prefix":"","firstName":"Wenhua","middleName":"","lastName":"Zhao","suffix":""},{"id":531812488,"identity":"3b8a1614-0105-4087-ab72-4a54a1a2499a","order_by":7,"name":"Peng Peng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAsUlEQVRIiWNgGAWjYDCCAwxsDA8YGOTY2JsPkKAlgYHBmI/nWAJpWhLnSeQoEKeD73iP2YOEijvpbQw5DAw/KrYR1iJ55oy5QcKZZ7ltDGcPMPacuU1Yi8GNHDOJxLbDuW2MfQnMjG1Ea/l3OJ2NmceAFC0NhxPY2IjVInnmWLlBwrFnhm08bAkHifIL3/HmbQ8+1NyRl5//+OCDHxVEaIGCA0gkSVpGwSgYBaNgFGAFAEKsQLd9a+i3AAAAAElFTkSuQmCC","orcid":"","institution":"The First Affiliated Hospital of Guangxi Medical University","correspondingAuthor":true,"prefix":"","firstName":"Peng","middleName":"","lastName":"Peng","suffix":""}],"badges":[],"createdAt":"2025-09-24 16:38:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7705743/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7705743/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12880-025-02132-y","type":"published","date":"2026-01-24T15:58:16+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":94140797,"identity":"1f9d16c7-036d-4ef8-9394-9aad9c6e73a3","added_by":"auto","created_at":"2025-10-22 19:47:39","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2731977,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/384f2223bf7bf882211baca3.docx"},{"id":94139126,"identity":"fa31f576-aabe-4d0b-be28-208bfb80b3fd","added_by":"auto","created_at":"2025-10-22 19:31:39","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9763,"visible":true,"origin":"","legend":"","description":"","filename":"b79501b0cbb14471a52110bc4dc8ac42.json","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/85b03aebf1fa9fa0aa138c20.json"},{"id":94139131,"identity":"1ebe143c-3809-4492-ac35-e624b7f1fbcd","added_by":"auto","created_at":"2025-10-22 19:31:39","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":23162,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementarymaterial1.docx","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/3a094f721cbd05f8350bba29.docx"},{"id":94139132,"identity":"cbbccadd-4ab8-4b14-82d9-7ea247ebfbf2","added_by":"auto","created_at":"2025-10-22 19:31:39","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":112232,"visible":true,"origin":"","legend":"","description":"","filename":"b79501b0cbb14471a52110bc4dc8ac421enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/0668ee60525958fe65fa92bf.xml"},{"id":94139147,"identity":"629b2c25-4c7c-4b45-8844-9a7c2e343866","added_by":"auto","created_at":"2025-10-22 19:31:40","extension":"eps","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":127402,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/2cac1b62cba03a53158a829f.eps"},{"id":94139139,"identity":"663d9bd0-84a3-4de7-ab46-ab7ff4c4413b","added_by":"auto","created_at":"2025-10-22 19:31:39","extension":"eps","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":218672,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage3.eps","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/7e38a3104bf993f1fb84e653.eps"},{"id":94139141,"identity":"1039e498-9af9-4170-b25e-641b19988510","added_by":"auto","created_at":"2025-10-22 19:31:40","extension":"eps","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":82423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage4.eps","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/5e416bf156c52dbe9c4d0287.eps"},{"id":94139154,"identity":"c07e94f3-3bd1-4ad6-a361-c9069feba5ed","added_by":"auto","created_at":"2025-10-22 19:31:40","extension":"eps","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":134752,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage5.eps","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/d86cb84afc43ffa1704518e8.eps"},{"id":94139156,"identity":"654552aa-1df8-48c1-9fb3-36f6e1a6153f","added_by":"auto","created_at":"2025-10-22 19:31:40","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":83677,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/81bba9ebf3043419a08d0908.png"},{"id":94139136,"identity":"13ba7ff2-7439-49aa-87fb-04fdce435940","added_by":"auto","created_at":"2025-10-22 19:31:39","extension":"jpeg","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":367106,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/27d486232de8a24e957083ea.jpeg"},{"id":94140280,"identity":"7382b228-813a-44d0-a371-a145a72a0ba5","added_by":"auto","created_at":"2025-10-22 19:39:39","extension":"jpeg","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":151094,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/f1bf6ad8b23799a6ae0aeb9b.jpeg"},{"id":94139145,"identity":"28298ae3-31df-4f7a-9907-2ca14fea2c02","added_by":"auto","created_at":"2025-10-22 19:31:40","extension":"jpeg","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1074,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/ee52ef0d610de94dee955d60.jpeg"},{"id":94139146,"identity":"fcb83bc2-9977-4ad0-b27d-f0ab1efab7b3","added_by":"auto","created_at":"2025-10-22 19:31:40","extension":"jpeg","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":99662,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/eb77381ddf204f4e27b1c0c1.jpeg"},{"id":94139134,"identity":"3b5cac13-769f-4b4c-8694-008c31b289ee","added_by":"auto","created_at":"2025-10-22 19:31:39","extension":"jpeg","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":250919,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/17c41b25d18832b003f2f7f7.jpeg"},{"id":94139140,"identity":"646646b6-5f91-443a-81fc-4d03f1de799f","added_by":"auto","created_at":"2025-10-22 19:31:39","extension":"jpeg","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":191085,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/803a47fb5148865c8395c992.jpeg"},{"id":94139144,"identity":"720acd05-42e2-4408-9450-ab78568ac45b","added_by":"auto","created_at":"2025-10-22 19:31:40","extension":"jpeg","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":283952,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/45dac71dc51a9a26257c3c0b.jpeg"},{"id":94140283,"identity":"4313def4-631b-422e-a5e0-bc6a472ce008","added_by":"auto","created_at":"2025-10-22 19:39:40","extension":"jpeg","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":220140,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/6fa123e176f5124de92b7bcb.jpeg"},{"id":94140282,"identity":"51fb0ded-2798-4e93-add7-029e5902653e","added_by":"auto","created_at":"2025-10-22 19:39:40","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36109,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/9a10bed4134e5a891a3aff44.png"},{"id":94140285,"identity":"6ad9a226-e618-46fd-9b8b-5a8f71c3a9c8","added_by":"auto","created_at":"2025-10-22 19:39:40","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":77981,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/34928fededa61660dd2c4da7.png"},{"id":94139157,"identity":"31036c3a-070c-4505-8376-e206b7dfb3f2","added_by":"auto","created_at":"2025-10-22 19:31:40","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":31673,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/9c1a79b1fbb974aab0b29560.png"},{"id":94140284,"identity":"fdd0edb8-c817-4ec3-aac6-dd47d4f9fa7d","added_by":"auto","created_at":"2025-10-22 19:39:40","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":935,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/1914da29c2bfbd71bef0ad7b.png"},{"id":94140798,"identity":"bf2aef67-186d-40b3-a74b-ff8b9c95ba4e","added_by":"auto","created_at":"2025-10-22 19:47:39","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16899,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/fa39a98b8d8fa24f8f54711f.png"},{"id":94139149,"identity":"e9357c99-ae3d-4ff7-af8f-eb222cea7d80","added_by":"auto","created_at":"2025-10-22 19:31:40","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":50127,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/daf1b31b34db9e1369b65218.png"},{"id":94139142,"identity":"48be7439-bdfe-4679-93c0-f0f902cebdcd","added_by":"auto","created_at":"2025-10-22 19:31:40","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":34777,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/8060b67615a53faba091efc2.png"},{"id":94139143,"identity":"383afa7e-313a-4ae5-86c1-9cbda6c7e935","added_by":"auto","created_at":"2025-10-22 19:31:40","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":68694,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/04f8a6b8064d358c7b27d558.png"},{"id":94139158,"identity":"08ed1fe3-b8df-40ba-92ab-b1234566f723","added_by":"auto","created_at":"2025-10-22 19:31:40","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":44324,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/09e449dac7ea79a79331bec8.png"},{"id":94139153,"identity":"8fd5390c-8572-4713-91ee-18f8ffc71569","added_by":"auto","created_at":"2025-10-22 19:31:40","extension":"xml","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":109678,"visible":true,"origin":"","legend":"","description":"","filename":"b79501b0cbb14471a52110bc4dc8ac421structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/d7ef97e8f6c9b9aa5b4d3138.xml"},{"id":94139152,"identity":"564b9359-9a43-4233-b750-870a75c5aecf","added_by":"auto","created_at":"2025-10-22 19:31:40","extension":"html","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":122116,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/de538af92e2ee41b07dcbe51.html"},{"id":94140275,"identity":"01bf5fe6-51d1-4fb6-8ab1-f6c2086b590c","added_by":"auto","created_at":"2025-10-22 19:39:39","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":83677,"visible":true,"origin":"","legend":"\u003cp\u003eFlowchart illustrating the participant selection process.\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/17eabf54db413b7015ef31f2.png"},{"id":94139129,"identity":"81933ced-143d-45ac-8c48-dc7154c74ab6","added_by":"auto","created_at":"2025-10-22 19:31:39","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":286120,"visible":true,"origin":"","legend":"\u003cp\u003eDetails of the radiomic analyses.\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/b6c737f9ca9d5cab6c88d06a.png"},{"id":94140276,"identity":"f0ee806b-e1d4-4ba9-87d7-860f57d65781","added_by":"auto","created_at":"2025-10-22 19:39:39","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":103540,"visible":true,"origin":"","legend":"\u003cp\u003eThe features selected for constructing the radiomics score.\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/2eb83a2d130aa99f00682016.png"},{"id":94139130,"identity":"3a9c1170-57b2-484c-b95f-2aaf48daf8ae","added_by":"auto","created_at":"2025-10-22 19:31:39","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":166424,"visible":true,"origin":"","legend":"\u003cp\u003eThe ROC curves for the nomogram, radiomics signature, and clinical models in the prediction of Ki-67 PI levels in L-NENs throughout training (a), testing (b), and validation cohorts (c). ROC, receiver operating characteristic. PI, proliferative index;\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/a3a7c21439426362d8fb2746.png"},{"id":94139133,"identity":"d21fea5d-9978-4bce-ac14-288e41060b4a","added_by":"auto","created_at":"2025-10-22 19:31:39","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":280790,"visible":true,"origin":"","legend":"\u003cp\u003e(a) presents a nomogram model that predicts the Ki-67 PI expression risk in L-NENs, integrating Radscore, tumor maximal diameter, age, and smoking status. (b-d) The nomogram calibration curves for the training, testing and external validation sets. Radscore, radiomics score\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/8fda9146d1a151e542bb7a71.png"},{"id":94140278,"identity":"a5352ad6-0f8f-48d6-8a23-c05068129620","added_by":"auto","created_at":"2025-10-22 19:39:39","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":230610,"visible":true,"origin":"","legend":"\u003cp\u003eDecision curve analysis (DCA) for clinical model, radiomics model, and nomogram model in the training cohort (a) ,internal validation cohortand (b) and external validation cohort (c). The x-axis indicates threshold probability and the y-axis indicates the net benefit.\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/407356aa0da3461237d9ea48.png"},{"id":101151749,"identity":"39ab0726-363f-482b-b0dc-c1810acfb3d8","added_by":"auto","created_at":"2026-01-26 16:04:33","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1716112,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/786d94bf-d09e-4a7b-9606-bc51328fe5ca.pdf"},{"id":94139123,"identity":"28063b5c-c98e-4262-b140-a6a0cff1634a","added_by":"auto","created_at":"2025-10-22 19:31:39","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":23162,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementarymaterial1.docx","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/a0bfec01482b3bbddbe31965.docx"},{"id":94139125,"identity":"8df96af0-b1c0-4f0a-a127-353e7d5470b8","added_by":"auto","created_at":"2025-10-22 19:31:39","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":41644,"visible":true,"origin":"","legend":"","description":"","filename":"Tables.docx","url":"https://assets-eu.researchsquare.com/files/rs-7705743/v1/b8dec441ecbc0340f7a17a31.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eCT-Based Radiomic Nomogram for Preoperative Prediction of Ki-67 in Lung Neuroendocrine Neoplasms: A Multicenter Study\u003c/p\u003e","fulltext":[{"header":"Background","content":"\u003cp\u003eLung neuroendocrine neoplasms (L-NENs), which arise from neuroendocrine and peptidergic cells in the bronchial mucosa and submucosal glands, account for about 20% of lung malignancies [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Possibly due to improved diagnostic techniques and growing clinical awareness, the prevalence of NENs is steadily increasing [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eIn terms of the World Health Organization's diagnosis and classification standards, L-NENs are categorized according to tumor necrosis and mitotic index, as well as neuroendocrine tumor appearance, which is verified by immunohistochemistry (IHC) staining for neuroendocrine markers. Typical carcinoid and atypical carcinoid are classified as well-differentiated neuroendocrine tumors (NETs), while large cell neuroendocrine carcinoma (LCNEC) and small cell lung carcinoma (SCLC) are categorized as poorly differentiated neuroendocrine carcinomas (NECs).[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. Significant crushing artifacts frequently occur in tissue fragments acquired via preoperative biopsy, hindering the evaluation of mitotic counts and complicating the interpretation of morphological images and precise preoperative diagnosis. In such cases, the Ki-67 proliferation index (PI) is highly valuable [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eThe WHO lists the Ki-67 antigen, a well-known cell proliferation marker, as a non-mandatory but desirable criterion for L-NENs, in which\u0026thinsp;\u0026le;\u0026thinsp;5%, \u0026lt;\u0026thinsp;30%, and \u0026gt;\u0026thinsp;30% Ki-67-positive cells indicate typical carcinoids (TC), atypical carcinoids (AC), and neuroendocrine carcinoma (small or large cell subtypes), respectively [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. Although the current grading system does not incorporate Ki-67 for staging L-NENs, Ki-67 IHC testing of biopsy samples is vital for differentiating between NETs and NECs and preventing misdiagnosis [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e, \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eRadical surgery remains optimal for TC and early-stage atypical AC with Ki-67\u0026thinsp;\u0026lt;\u0026thinsp;30%. LCNEC and SCLC, characterized by high Ki-67 levels and high-grade malignancy, exhibit significant rates of local and systemic metastases, with treatment primarily involving a combination of radiotherapy and chemotherapy [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. Furthermore, patients with TC with increased Ki-67 expression show significantly reduced survival [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e].\u003c/p\u003e\u003cp\u003ePreoperative Ki-67 expression is primarily assessed through IHC testing, which involves obtaining tissue samples by puncture and evaluating them by routine visual observation by a pathologist [\u003cspan additionalcitationids=\"CR9\" citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. Owing to tumor heterogeneity and the relatively small sample size, Ki-67 evaluation based on biopsy samples may not accurately represent the entire tumor. Furthermore, biopsy sampling is invasive and non-repeatable. Additionally, in many critical cases where core needle biopsies are not feasible, Ki-67 assessment is unavailable.here is a pressing need to establish reliable, advanced, and noninvasive techniques for the accurate prediction of Ki-67 status in L-NEN cases, which could significantly improve clinical management and treatment outcomes.\u003c/p\u003e\u003cp\u003eRadiomics offers comprehensive and quantitative tumor measurements to facilitate non-invasive,comprehensive analysis of tumor phenotypes. This technique provides significant insights into clinical diagnosis and prognosis prediction. It is frequently employed in diagnosing, treating, and prognostic evaluating various cancers, offering a valuable tool for enhancing treatment strategies and patient outcomes [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. Radiomics can help improve tumor behavior and patient treatment management comprehension by extracting high-throughput data from medical images, leading to more personalized and precise medical care [\u003cspan additionalcitationids=\"CR13 CR14\" citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eHowever, limited research has been conducted to evaluate the potential of radiomics in assessing Ki-67 expression levels in L-NENs..Meyer et al. [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e] assessed chest computed tomography (CT) scans in patients' plain and arterial phases from the same institution and identified several CT texture features correlated with the PI of the lung neuroendocrine Ki-67 antigen to differentiate TC and AC potentially. Another single-institution study analyzing baseline and venous-phase chest CT images obtained using different CT scanner models demonstrated a correlation between texture features and the histological heterogeneity of L-NENs, Ki-67 values, and metastatic foci. Thus, textural features may help assess tumor type and aggressiveness in L-NENs [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]. However, these single-centre studies did not establish effective predictive models.\u003c/p\u003e\u003cp\u003eAs a result, this study intended to develop a radiographic score using plain and dual-phase enhanced CT fusion images from various hospitals and to create a nomogram for the prediction of Ki-67 PI levels in L-NENs by amalgamating clinical data and imaging characteristics.Additionally, the study evaluated this model's performance and generalisability, aiming to serve clinical diagnosis and treatment better while alleviating patient suffering.\u003c/p\u003e"},{"header":"Research Methodology","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003ePatients\u003c/h2\u003e\u003cp\u003e The four participating hospitals' institutional ethics committees authorized this retrospective study, eliminating the need for informed consent. This study was carried out in full compliance with the ethical principles set forth in the Declaration of Helsinki.The study examined data from consecutive patients with pathologically diagnosed L-NENs at the Guangxi Medical University Cancer Hospital (Centre 2) and the First Affiliated Hospital of Guangxi Medical University (Centre 1) between January 2014 and April 2024, as well as at the Guangxi Zhuang Autonomous Region Chest Hospital (Centre 4) and the Liuzhou Workers' Hospital (Centre 3) between January 2019 and April 2024.\u003c/p\u003e\u003cp\u003eThe inclusion criteria were: (1) Diagnosis of L-NENs through surgical pathology specimens and immunohistochemical examination, and (2) preoperative chest CT scan with dual-phase enhancement. The following were the exclusion criteria: (1) no Ki-67 immunohistochemistry data; (2) poor image quality with severe artifacts; (3) tumor too small (largest diameter\u0026thinsp;\u0026lt;\u0026thinsp;5 mm); (4) incomplete clinical data; (5) Received radiotherapy or chemotherapy before surgery; (6) The tumor with non-small cell carcinoma components.\u003c/p\u003e\u003cp\u003ePatients from Centers 1\u0026ndash;4, 112, 54, 19, and 14 were selected according to the above criteria. For model development, the 166 patients from Centers 1 and 2 were subsequently divided into training (n\u0026thinsp;=\u0026thinsp;116) and test (n\u0026thinsp;=\u0026thinsp;50) cohorts at random in a 7:3 proportion ratio. The external validation cohort comprised the 33 patients from Centers 3 and 4. Figure\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e depicts the patient selection procedure.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eCT examinations\u003c/h3\u003e\n\u003cp\u003eThe detailed CT protocol is provided in the Supplementary Material1.\u003c/p\u003e\n\u003ch3\u003eEvaluation of radiological features and clinical data\u003c/h3\u003e\n\u003cp\u003eClinical data, including sex, age, and smoking status, were extracted from each patient's electronic medical records system. Two chest radiologists with 10 and 20 years of expertise in interpreting chest imaging evaluated CT pictures, which included both contrast-enhanced and non-contrast images. They were blinded to the pathological and clinical results. Consensus was used to settle disagreements. The radiological characteristics listed below were assessed: (1) longest tumor diameter (cm) on axial images; (2) spiculation sign; (3) liquefaction necrosis; (4) calcification; and (5) obstructive pneumonia. A sharp, linear protrusion between the tumor and the surrounding lung parenchyma was identified as the spiculation sign [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e].\u003c/p\u003e\n\u003ch3\u003eImmunohistochemical analysis of Ki-67 index\u003c/h3\u003e\n\u003cp\u003eAfter being fixed in 10% neutral buffered formalin, each sample was regularly dehydrated, embedded in paraffin, and cut into 4-micron-thick slices. Using the Ventana Benchmark Ultra automated IHC staining equipment (Roche Ventana, Inc.), Ki-67 was detected for proliferation by IHC. The percentage of positive tumor cell nuclei was referred to as the PI, and cells with brownish nuclei were considered Ki-67-positive. Based on the Ki-67 PI, L-NENs were divided into low (PI\u0026thinsp;\u0026le;\u0026thinsp;30%) and high (PI\u0026thinsp;\u0026gt;\u0026thinsp;30%) expression groups [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e].\u003c/p\u003e\n\u003ch3\u003eTumor segmentation and feature extraction\u003c/h3\u003e\n\u003cp\u003eThe Picture Archiving and Communication System (PACS) provided the CT images, which were then converted to Digital Imaging and Communications in Medicine (DICOM) format. 3D Slicer 5.2.2 (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.slicer.org\u003c/span\u003e\u003cspan address=\"https://www.slicer.org\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e), was used to segment the images. All CT image slices were reviewed in each patient to select the slice with the largest tumor area for measuring the maximum tumour diameter. In the present study, all extraction and selection of CT features were completed using UltraScholar 2.0 (Shukun Network Technology Co., Ltd., Beijing).\u003c/p\u003e\u003cp\u003eTo define the volumes of interest (VOIs), a 3D slicer was utilized for manual delineation of tumor areas on axial CT images in the plain, arterial, and venous phases of the CT scan. To assess intra-observer reliability, radiologist A re-segmented 30 randomly selected cases after two weeks. Furthermore, to assess interobserver reliability, a second radiologist (B) independently segmented these 30 instances without informing either radiologist of the histological findings.\u003c/p\u003e\u003cp\u003eBefore feature extraction, the obtained pictures underwent pre-processing, which involved normalization, modification of image resolution to 1\u0026times;1\u0026times;1 mm\u0026sup3; by B-spline interpolation, and discretization of grey levels using a fixed bin width 25. The plain and dual-phase-enhanced fusion images yielded 1,874 radiomic features in total, comprising 1,500 second-order (texture) characteristics, 360 first-order (histogram) features, and 14 shape features.The workflow is illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. Features with an intraclass correlation coefficient (ICC) and an intra-reader correlation coefficient, both exceeding 0.75, were deemed to show satisfactory agreement.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003eFeature selection and model building\u003c/h2\u003e\u003cp\u003eFirst, the system identified anomalies where features have different names but identical values during pre-processing and removed features with identical values after processing. Second, Pearson correlation coefficients were utilized to remove redundancy, using a correlation coefficient threshold 0.8. The pertinent characteristics were selected by Least Absolute Shrinkage and Selection Operator (LASSO) assessments.\u003c/p\u003e\u003cp\u003eAfter that, radiomic signatures were developed using five machine learning algorithms: logistic regression (LR), support vector machine (SVM), extreme gradient boosting (XGBoost), Gaussian Naive Bayes (GaussianNB), and linear support vector machine (LinearSVC). The training cohort underwent ten-fold cross-validation, and the test cohort's outcomes were assessed. For the external cohort, the optimal model was then applied.\u003c/p\u003e\u003cp\u003eSignificant clinical factors and radiological features were investigated as independent risk predictors of Ki-67 status L-NEN cases by univariate and multivariate analyses following the completion of chi-square tests and independent samples t-tests. The clinical model was developed using clinical parameters that had a \u003cem\u003eP\u003c/em\u003e-value of \u0026lt;\u0026thinsp;0.05 in these analyses. The radiomic score and the clinical signature were merged in the radiomic nomogram.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e\u003ch2\u003eStatistical analysis\u003c/h2\u003e\u003cp\u003eR version 4.4.0 (R Foundation for Statistical Computing, Vienna, Austria) and SPSS 26.0 (IBM Corp., Armonk, NY, USA) were employed for all statistical analyses. The Mann-Whitney and Chi-square tests assessed the qualitative and categorical variables, respectively. P\u0026thinsp;\u0026lt;\u0026thinsp;0.05 represented statistical significance. The AUCs of ROC curves were utilized to assess the models' diagnostic performance in differentiating between the high and low Ki-67 groups. Decision curve analysis (DCA) was utilized for assessing the clinical applicability of the models.\u003c/p\u003e\u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\n \u003ch2\u003ePatient characteristics\u003c/h2\u003e\n \u003cp\u003eThis retrospective study enrolled 199 patients in total, including 143 males (71.86%) and 56 females (28.14%), with a median age of 59 years. The high (Ki\u0026thinsp;\u0026gt;\u0026thinsp;30%) and low (Ki\u0026thinsp;\u0026le;\u0026thinsp;30%) Ki-67 status groups included 119 (59.8%) and 80 (40.2%) patients, respectively.Radiological CT features and the clinical data of L-NENs in each cohort are summarised in Table 1.\u003c/p\u003e\n \u003cp\u003eAge, sex, smoking status, and longest diameter significantly correlated with high Ki-67 expression in univariate analysis (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). The radiomic-clinical nomogram contained the following independent characteristics that influenced Ki-67 expression in multi-variable logistic regression: smoking status (OR: 12.80, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001), largest tumor diameter (OR: 1.79, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001), and age ( [OR]: 1.09, P\u0026thinsp;=\u0026thinsp;0.006) (Table 2).\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\n \u003ch2\u003eRadiomic-based model performance\u003c/h2\u003e\n \u003cp\u003eA radiological model was constructed using four characteristics with non-zero coefficients based on the most effective features in the feature selection process (Fig. \u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e ). With AUCs of 0.912 (95% CI: 0.858\u0026ndash;0.965) in the training set and 0.943 (95% CI: 0.887\u0026ndash;0.999) in the testing set, the LR algorithm showed strong performance(Table 3 ). The output was converted into a Radscore to signify the relative risk associated with a high Ki-67 status. This approach was designated as the radiomic model.\u003c/p\u003e\n \u003ctable border=\"1\"\u003e\u003c/table\u003e\n \u003cp\u003e\u003c/p\u003e\n \u003cp\u003eConstruction and validation of the radiomic nomogram\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec13\" class=\"Section2\"\u003e\n \u003cp\u003eUsing the three independent predictors of age, maximum tumor diameter, and smoking status, a clinical model associated with Ki-67 levels was developed. In the training, testing, and external validation sets, the model\u0026apos;s AUC values were 0.898 (95%CI: 0.841\u0026ndash;0.955), 0.863 (95%CI: 0.749\u0026ndash;0.978), and 0.882 (95%CI: 0.828\u0026ndash;0.936), respectively (Fig. \u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e., Table\u0026nbsp;4).\u003c/p\u003e\n \u003cp\u003eFigure \u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e.shows the ROC curves for the clinical, radiomics, and clinical-radiomics nomogram models for the training, testing, and external validation populations. The AUC values, sensitivity, specificity, accuracy, F1 score, positive predictive value (PPV), and negative predictive value (NPV) for the individual models are detailed in Table\u0026nbsp;4. In the training, testing, and external validation cohorts, the nomogram for clinical-radiomics showed the best diagnostic performance for Ki-67 PI expression, with AUC values of 0.958 (95%CI: 0.925\u0026ndash;0.990), 0.930 (95%CI: 0.865\u0026ndash;0.995), and 0.911 (95%CI: 0.867\u0026ndash;0.955), respectively. The DeLong test indicated that the training cohort\u0026apos;s nomogram and clinical models had significantly different AUCs. However, there was a insignificant difference between the models in the internal and external validation sets (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05) and between the AUCs of the radiomics model and the nomogram (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.23).\u003c/p\u003e\n \u003cp\u003ePer the calibration curve analysis, the nomogram model exhibits good agreement with the actual trends in the training, testing, and external validation sets (Fig. \u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e). The DCA (Fig. \u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003e) also indicates that, compared to radiological and clinical parameters models, the nomogram model tends to show a marginal net benefit in differentiating between individuals with high and low Ki-67 PI levels within the most appropriate threshold probability ranges.\u003c/p\u003e\n\u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eIn this multicenter retrospective study we constructed and externally validated a CT-based radiomics nomogram that fuses quantitative imaging features with routine clinical variables (age, largest tumor diameter, and smoking history) to pre-operatively estimate the probability of Ki-67\u0026thinsp;\u0026gt;\u0026thinsp;30% in lung neuroendocrine neoplasms (L-NENs). Although the proposed model achieved high AUCs of 0.958, 0.930 and 0.911 in the training, internal testing and external validation cohorts, respectively, several methodological considerations merit cautious interpretation of these results.\u003c/p\u003e\u003cp\u003eFirst, radiomic analyses are intrinsically high-dimensional and vulnerable to overfitting when the number of extracted features exceeds the number of clinical events [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. We attempted to mitigate this risk by removing highly correlated variables (Pearson |r|\u0026gt;0.8), applying LASSO logistic regression with 10-fold cross-validation, and evaluating the final model in an independent external data set. Nevertheless, the external validation cohort comprised only 33 patients, producing a 95% confidence interval that remains wide (0.867\u0026ndash;0.955) and whose upper bound approaches unity, suggesting that random variation may partly explain the observed performance (authors\u0026rsquo;inference), consistent with reports of unstable AUC estimates in small external cohorts [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. Larger, prospective, geographically distinct cohorts scanned with heterogeneous CT platforms are required to confirm generalizability.\u003c/p\u003e\u003cp\u003eSecond, all four radiomic features retained in our logistic regression model belong to the grey-level size-zone matrix (GLSZM) family, which quantifies intra-tumoral heterogeneity. Previous single-centre studies have correlated GLSZM parameters with Ki-67 expression in pulmonary and other neoplasms [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e], providing biological plausibility for our findings. Likewise, recent radiomics models for Ki-67 in sinonasal malignancies[\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e] and hepatocellular carcinoma[\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e] confirm the added value of high-order texture features, reinforcing the biological link between intra-tumoral heterogeneity and proliferation. However, radiomic surrogates remain indirect; integration with digital pathology or multi-omic profiling will be necessary to uncover mechanistic links between imaging phenotypes and tumor proliferation [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eThird, multivariable analysis generated an odds ratio of 12.8 (95% CI 3.4\u0026ndash;48.3) for smoking history, reflecting the marked imbalance in our cohort (85% of smokers versus 28% of non-smokers had Ki-67\u0026thinsp;\u0026gt;\u0026thinsp;30%) and the limited number of events, both of which can inflate point estimates. Comparable extreme odds ratios have been reported in small-sample radiomics studies for multiple myeloma [\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e] and bladder cancer [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e], where sparse-event logistic regression was likewise employed. Bootstrapping or Bayesian shrinkage methods should be considered in future work to obtain more stable effect sizes.\u003c/p\u003e\u003cp\u003eFinally, decision curve analysis indicated a marginal net benefit for the nomogram within the threshold probability range of 15\u0026ndash;70%. However, DCA does not incorporate real-world costs such as unnecessary biopsies, false-positive downstream imaging, or patient anxiety [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]. Prospective interventional trials are therefore needed to determine whether application of the nomogram truly alters clinical management and to evaluate cost-effectiveness before widespread adoption .\u003c/p\u003e\u003cdiv id=\"Sec15\" class=\"Section2\"\u003e\u003ch2\u003eLimitations\u003c/h2\u003e\u003cp\u003eOur investigation has several limitations. (1) The retrospective design predisposes to selection and ascertainment bias. (2) The external validation sample was small (n\u0026thinsp;=\u0026thinsp;33), limiting precision of performance estimates. (3) All L-NEN subtypes were pooled; subtype-specific models might yield better accuracy. (4) Ki-67 assessment followed local pathology protocols without central review. (5) Cost-utility and impact on patient outcomes were not evaluated. Larger prospective studies that address these issues are warranted.\u003c/p\u003e\u003c/div\u003e"},{"header":"Conclusions","content":"\u003cp\u003eA nomogram combining CT radiomics and routinely available clinical variables can estimate the likelihood of Ki-67\u0026thinsp;\u0026gt;\u0026thinsp;30% in patients with lung neuroendocrine neoplasms with good discrimination and appropriate calibration. These findings justify larger prospective studies to verify generalizability, define clinical utility, and determine whether the model safely reduces invasive procedures or improves treatment planning.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cp\u003eAC \u0026nbsp; \u0026nbsp; \u0026nbsp;atypical carcinoids\u003c/p\u003e\n\u003cp\u003eDICOM \u0026nbsp;digital imaging and communications in medicine\u003c/p\u003e\n\u003cp\u003eDCA \u0026nbsp; \u0026nbsp; decision curve analysis\u003c/p\u003e\n\u003cp\u003eAUC \u0026nbsp; \u0026nbsp; the area under the curve\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eCT \u0026nbsp; \u0026nbsp; \u0026nbsp; computed tomography\u003c/p\u003e\n\u003cp\u003eGLSZM \u0026nbsp; grey level size zone matrix\u003c/p\u003e\n\u003cp\u003eIHC \u0026nbsp; \u0026nbsp; \u0026nbsp;immunohistochemical\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eL-NENs \u0026nbsp; lung neuroendocrine neoplasms\u003c/p\u003e\n\u003cp\u003eNETs \u0026nbsp; \u0026nbsp; neuroendocrine tumors\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eNENs \u0026nbsp; \u0026nbsp; neuroendocrine neoplasms\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eNECs \u0026nbsp; \u0026nbsp; neuroendocrine carcinomas\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eROC \u0026nbsp; \u0026nbsp; \u0026nbsp;receiver operating curve\u0026nbsp;\u003c/p\u003e\n\u003cp\u003ePACS \u0026nbsp; \u0026nbsp; picture archiving and communication system\u0026nbsp;\u003c/p\u003e\n\u003cp\u003ePI \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;proliferation index\u003c/p\u003e\n\u003cp\u003eSCLC \u0026nbsp; \u0026nbsp;small-cell lung cancer\u003c/p\u003e\n\u003cp\u003eLCNEC \u0026nbsp;large-cell neuroendocrine carcinomas of the lung\u003c/p\u003e\n\u003cp\u003eTC \u0026nbsp; \u0026nbsp; \u0026nbsp;typical carcinoids\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eVOI \u0026nbsp; \u0026nbsp; volume of interest\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis retrospective study, conducted in accordance with the Declaration of Helsinki, received approval from the institutional review boards of The First Affiliated Hospital of Guangxi Medical University (approval No. 2025-E0595), Guangxi Medical University Cancer Hospital (approval No. KY-2022-301), Liuzhou Worker\u0026rsquo;s Hospital (approval No. KY2025614), and The Chest Hospital of Guangxi Zhuang Autonomous Region (approval No. 2023-S004-01), each of which waived the requirement for informed patient consent.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;Not applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe data supporting this study are available from the corresponding author upon reasonable request but may be restricted to protect patient confidentiality and comply with ethical guidelines, given the study\u0026apos;s retrospective design.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no competing interests except Jing Hu, who is employed as a senior clinical scientist by ShuKun (Beijing) Technology Co., Ltd. This company had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis work was supported by① the Joint Regional Epidemic Disease Research Grant (project No. 2022JJA140455), titled \u0026lsquo;A quantitative MRI study of pituitary iron deposition in patients with Mediterranean anemia\u0026rsquo;;② the Provincial Science and Technology Program (project No. S2022072), titled \u0026lsquo;A quantitative study on the correlation between hepatic iron deposition and glucose metabolism in Mediterranean anemia using multimodal MRI\u0026rsquo;.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors\u0026apos; contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eXiao Pan, Yanni Zou, Tao Li, Peng Pengm, and Wenhua Zhao contributed to the study conception and design. Material preparation and data collection were performed by Xiao Pan, Yanni Zou, Xiaoxiao Huang, and Quan Zhang. Data analyses were performed by Xiao Pan, Jing Hu. The first draft of the manuscript was written by Xiao Pan, Yanni Zou. Jing Hu is employed as a senior clinical scientist in a company in medical industry ShuKun (BeiJing) Technology Co., Ltd., who was contributed in statistical analysis/ manuscript editing and did not control the study. All authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eWe would like to express our sincere gratitude to all the participants of our study, as well as to the hospitals involved for their generous support. At the same time, we extend our appreciation to Editage (www.editage.cn) for their assistance in English language editing.\u003c/p\u003e\n"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eDam, Gitte, et al. Nordic 2023 guidelines for the diagnosis and treatment of lung neuroendocrine neoplasms. Acta Oncol. 2023;62(5):431-437. doi:10.1080/0284186X.2023.2212411\u003c/li\u003e\n\u003cli\u003eChen SH, Chang YC, Hwang TL, et al. 68Ga-DOTATOC and 18F-FDG PET/CT for identifying the primary lesions of suspected and metastatic neuroendocrine tumors: A prospective study in Taiwan. J Formos Med Assoc. 2018;117(6):480-487. doi:10.1016/j.jfma.2017.07.007\u003c/li\u003e\n\u003cli\u003eWHO Classification of Tumours Editorial Board Thoracic tumours. WHO classification of tumours series, 5th ed.; vol. 5. Lyon: International Agency for Research on Cancer; 2021.\u003c/li\u003e\n\u003cli\u003eLa Rosa S. Diagnostic, Prognostic, and Predictive Role of Ki-67 Proliferative Index in Neuroendocrine and Endocrine Neoplasms: Past, Present, and Future. Endocr Pathol. 2023;34(1):79-97. doi:10.1007/s12022-023-09755-3\u003c/li\u003e\n\u003cli\u003ePelosi G, Travis WD. Head-to-head: Should Ki67 proliferation index be included in the formal classification of pulmonary neuroendocrine neoplasms?. Histopathology. 2024;85(4):535-548. doi:10.1111/his.15206\u003c/li\u003e\n\u003cli\u003ePelosi G, Travis WD. The Ki-67 antigen in the new 2021 World Health Organization classification of lung neuroendocrine neoplasms. Pathologica. 2021;113(5):377-387. doi:10.32074/1591-951X-542\u003c/li\u003e\n\u003cli\u003eGranberg D, Wilander E, Oberg K, Skogseid B. Prognostic markers in patients with typical bronchial carcinoid tumors. J Clin Endocrinol Metab. 2000;85(9):3425-3430. doi:10.1210/jcem.85.9.6785\u003c/li\u003e\n\u003cli\u003eMacCallum DE, Hall PA. The location of pKi67 in the outer dense fibrillary compartment of the nucleolus points to a role in ribosome biogenesis during the cell division cycle. J Pathol. 2000;190(5):537-544. doi:10.1002/(SICI)1096-9896(200004)190:5\u0026lt;537::AID PATH577\u0026gt;3.0.CO;2-W\u003c/li\u003e\n\u003cli\u003eGerdes J, Li L, Schlueter C, et al. Immunobiochemical and molecular biologic characterization of the cell proliferation-associated nuclear antigen that is defined by monoclonal antibody Ki-67. Am J Pathol. 1991;138(4):867-873.\u003c/li\u003e\n\u003cli\u003eKim HS, Park S, Koo JS, et al. Risk Factors Associated with Discordant Ki-67 Levels between Preoperative Biopsy and Postoperative Surgical Specimens in Breast Cancers. PLoS One. 2016;11(3):e0151054. Published 2016 Mar 8. doi:10.1371/journal.pone.0151054\u003c/li\u003e\n\u003cli\u003eLambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer. 2012;48(4):441-446. doi:10.1016/j.ejca.2011.11.036\u003c/li\u003e\n\u003cli\u003eZhang H, Qi L, Cai Y, Gao X. Gastrin-releasing peptide receptor (GRPR) as a novel biomarker and therapeutic target in prostate cancer. Ann Med. 2024;56(1):2320301. doi:10.1080/07853890.2024.2320301\u003c/li\u003e\n\u003cli\u003eAngelone, F, Ciliberti, F, Tobia, G, et al. Innovative Diagnostic Approaches for Predicting Knee Cartilage Degeneration in Osteoarthritis Patients: A Radiomics-Based Study INFORM SYST FRONT. 2024; doi: 10.1007/s10796-024-10527-5\u003c/li\u003e\n\u003cli\u003eCheng L, Gao H, Wang Z, Guo L, Wang X, Jin G. Prospective study of dual-phase 99mTc-MIBI SPECT/CT nomogram for differentiating non-small cell lung cancer from benign pulmonary lesions [published correction appears in Eur J Radiol. 2024 Sep 5;181:111704. doi: 10.1016/j.ejrad.2024.111704]. Eur J Radiol. 2024;179:111657. doi:10.1016/j.ejrad.2024.111657\u003c/li\u003e\n\u003cli\u003eWu J, Ge L, Guo Y, Xu D, Wang Z. Utilizing multiclassifier radiomics analysis of ultrasound to predict high axillary lymph node tumour burden in node-positive breast cancer patients: a multicentre study. Ann Med. 2024;56(1):2395061. doi:10.1080/07853890.2024.2395061\u003c/li\u003e\n\u003cli\u003eMeyer HJ, Leonhardi J, H\u0026ouml;hn AK, et al. CT Texture Analysis of Pulmonary Neuroendocrine Tumors-Associations with Tumor Grading and Proliferation. J Clin Med. 2021;10(23):5571. Published 2021 Nov 26. doi:10.3390/jcm10235571\u003c/li\u003e\n\u003cli\u003eCozzi D, Bicci E, Cavigli E, et al. Radiomics in pulmonary neuroendocrine tumours (NETs). Radiol Med. 2022;127(6):609-615. doi:10.1007/s11547-022-01494-5\u003c/li\u003e\n\u003cli\u003eGu Q, Feng Z, Liang Q, et al. Machine learning-based radiomics strategy for prediction of cell proliferation in non-small cell lung cancer. Eur J Radiol. 2019;118:32-37. doi:10.1016/j.ejrad.2019.06.025\u003c/li\u003e\n\u003cli\u003eWelch ML, McIntosh C, Haibe-Kains B, et al. Vulnerabilities of radiomic signature development: The need for safeguards. Radiother Oncol. 2019;130:2-9. doi:10.1016/j.radonc.2018.10.027\u003c/li\u003e\n\u003cli\u003eLiu J, Wang C, Guo W, et al. A preliminary study using spinal MRI-based radiomics to predict high-risk cytogenetic abnormalities in multiple myeloma. Radiol Med. 2021;126(9):1226-1235. doi:10.1007/s11547-021-01388-y\u003c/li\u003e\n\u003cli\u003eLi Q, Song Z, Li X, et al. Development of a CT radiomics nomogram for preoperative prediction of Ki-67 index in pancreatic ductal adenocarcinoma: a two-center retrospective study. Eur Radiol. 2024;34(5):2934-2943. doi:10.1007/s00330-023-10393-w\u003c/li\u003e\n\u003cli\u003eBi S, Li J, Wang T, et al. Multi-parametric MRI-based radiomics signature for preoperative prediction of Ki-67 proliferation status in sinonasal malignancies: a two-centre study. Eur Radiol. 2022;32(10):6933-6942. doi:10.1007/s00330-022-08780-w\u003c/li\u003e\n\u003cli\u003eZhang D, Zhang XY, Lu WW, et al. Predicting Ki-67 expression in hepatocellular carcinoma: nomogram based on clinical factors and contrast-enhanced ultrasound radiomics signatures. Abdom Radiol (NY). 2024;49(5):1419-1431. doi:10.1007/s00261-024-04191-1\u003c/li\u003e\n\u003cli\u003eLiu J, Wang C, Guo W, et al. A preliminary study using spinal MRI-based radiomics to predict high-risk cytogenetic abnormalities in multiple myeloma. Radiol Med. 2021;126(9):1226-1235. doi:10.1007/s11547-021-01388-y\u003c/li\u003e\n\u003cli\u003eXiong S, Fu Z, Deng Z, et al. Machine learning-based CT radiomics enhances bladder cancer staging predictions: A comparative study of clinical, radiomics, and combined models. Med Phys. 2024;51(9):5965-5977. doi:10.1002/mp.17288\u003c/li\u003e\n\u003cli\u003eVickers AJ, Van Calster B, Steyerberg EW. Net benefit approaches to the evaluation of prediction models, molecular markers, and diagnostic tests. BMJ. 2016;352:i6. Published 2016 Jan 25. doi:10.1136/bmj.i6\u003c/li\u003e\n\u003c/ol\u003e"},{"header":"Tables","content":"\u003cp\u003eTables are available in the Supplementary Files section.\u003c/p\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-imaging","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmim","sideBox":"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmim/default.aspx","title":"BMC Medical Imaging","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Lung Neuroendocrine Neoplasm, Nomogram prediction, Radiomics, Ki-67, Machine learning, Multicenter study","lastPublishedDoi":"10.21203/rs.3.rs-7705743/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7705743/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eObjective\u003c/h2\u003e\u003cp\u003eThe Lung neuroendocrine neoplasms (L-NENs) are increasingly recognised, yet reliable pre-operative assessment of the Ki-67 proliferation index remains invasive and heterogeneous. We aimed to develop and validate a clinical-radiomics nomogram that uses routine chest CT to estimate Ki-67 status in patients with L-NENs.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e\u003cp\u003eIn this retrospective multicentre study, 199 patients (four hospitals, January 2014\u0026ndash;December 2024) with histologically confirmed L-NENs and pre-operative dual-phase contrast-enhanced CT were included. After manual 3D tumour segmentation, 1,874 radiomics features were extracted from fused unenhanced and arterial / venous-phase images. Feature selection combined Pearson correlation (r\u0026thinsp;\u0026gt;\u0026thinsp;0.8 removed) and LASSO regression. Five classifiers were compared; logistic regression (LR) performed best and was used to build a radiomics signature (Rad-score). Clinical predictors of Ki-67 were identified by multivariable logistic regression and integrated with the Rad-score to construct a nomogram. Discrimination, calibration and clinical utility were assessed by AUC, calibration plot and decision curve analysis in training (n\u0026thinsp;=\u0026thinsp;116), internal testing (n\u0026thinsp;=\u0026thinsp;50) and external validation (n\u0026thinsp;=\u0026thinsp;33) sets.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e\u003cp\u003eHigh Ki-67 (\u0026gt;\u0026thinsp;30%) was present in 119 (59.8%) patients. The LR radiomics model yielded AUCs of 0.912 (95% CI 0.858\u0026ndash;0.965) and 0.943 (0.887\u0026ndash;0.999) in training and testing sets, respectively. Independent clinical predictors were largest tumour diameter, smoking history and age. The combined nomogram achieved AUCs of 0.958 (0.925\u0026ndash;0.990), 0.930 (0.865\u0026ndash;0.995) and 0.911 (0.867\u0026ndash;0.955) in training, testing and external validation sets, with good calibration and superior net benefit on decision-curve analysis.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e\u003cp\u003eThe CT-based clinical\u0026ndash;radiomics nomogram provides an accurate, non-invasive tool for pre-operative Ki-67 estimation in L-NENs, potentially guiding treatment decisions. Prospective, larger-scale validation is warranted.\u003c/p\u003e\u003ch2\u003eClinical trial number:\u003c/h2\u003e\u003cp\u003eNot applicable.\u003c/p\u003e","manuscriptTitle":"CT-Based Radiomic Nomogram for Preoperative Prediction of Ki-67 in Lung Neuroendocrine Neoplasms: A Multicenter Study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-22 19:31:34","doi":"10.21203/rs.3.rs-7705743/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-11-17T07:43:45+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-13T10:34:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"22562857396302224072732086841747702196","date":"2025-11-13T09:21:47+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-05T15:07:58+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-22T14:51:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"185000728922921838834408347985859457644","date":"2025-10-13T11:15:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"312038185633455600692625275454709562403","date":"2025-10-11T05:08:48+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-09T08:44:16+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-08T11:14:09+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-10-08T09:53:29+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-08T09:46:31+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Imaging","date":"2025-10-08T09:42:36+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-imaging","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmim","sideBox":"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmim/default.aspx","title":"BMC Medical Imaging","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"796192a1-a1b3-414f-a391-0f31b91430fa","owner":[],"postedDate":"October 22nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-01-26T16:01:18+00:00","versionOfRecord":{"articleIdentity":"rs-7705743","link":"https://doi.org/10.1186/s12880-025-02132-y","journal":{"identity":"bmc-medical-imaging","isVorOnly":false,"title":"BMC Medical Imaging"},"publishedOn":"2026-01-24 15:58:16","publishedOnDateReadable":"January 24th, 2026"},"versionCreatedAt":"2025-10-22 19:31:34","video":"","vorDoi":"10.1186/s12880-025-02132-y","vorDoiUrl":"https://doi.org/10.1186/s12880-025-02132-y","workflowStages":[]},"version":"v1","identity":"rs-7705743","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7705743","identity":"rs-7705743","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}