Computed Tomography Enterography-Based Radiomics Nomograms to Predict Inflammatory Activity for Ileocolonic Crohn’s Disease

Computed Tomography Enterography-Based Radiomics Nomograms to Predict Inflammatory Activity for Ileocolonic Crohn’s Disease | 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 Computed Tomography Enterography-Based Radiomics Nomograms to Predict Inflammatory Activity for Ileocolonic Crohn’s Disease Yuping Ma, Luanxin Zhu, Bota Cui, Faming Zhang, Haige Li, Jianguo Zhu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4465032/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 27 Jan, 2025 Read the published version in BMC Medical Imaging → Version 1 posted 12 You are reading this latest preprint version Abstract Objectives To develop and validate nomograms, derived from morphological features, and computed tomography enterography (CTE) -based radiomics, for evaluating inflammatory activity in patients with ileocolonic Crohn’s disease (CD). Methods A total of 54 CD patients (237 bowel segments) with clinically confirmed CD were retrospectively reviewed. The simple endoscopic score for Crohn’s disease (SES-CD) was used as a reference standard to quantify the degree of mucosal inflammation and evaluate the disease severity. Radiomics and image morphological features were extracted in the training cohort, and then a morphological model (M-score) and a radiomics model (Rad-score) were built respectively. A combined nomogram was further generated by incorporating M-score and Rad-score. Predictive values of each model were assessed using receiver operating characteristic (ROC) curve analysis. Calibration curve and decision curve analysis (DCA) were employed to evaluate the accuracy and clinical applicability of the nomogram in the testing cohort. Results The area under the ROC curve (AUC) of the nomogram, based on the stenosis, comb sign and Rad-score, was 0.834 [95% confidence interval (CI): 0.728–0.940] for distinguishing active from remissive disease. Moreover, the nomogram built using comb sign and Rad-score also achieved satisfied AUC [0.781 (95%CI: 0.611–0.951)] in distinguishing mild activity from moderate-to-severe activity. The calibration curve and DCA confirmed the accuracy and clinical utility of both nomograms. Conclusions Nomograms constructed by combining CTE-based radiomics and morphological features might be a useful supporting tool for grading inflammatory activity, aiding clinical decision-making for the management of CD. Crohn’s disease computed tomography enterography radiomics inflammatory activity Figures Figure 1 Figure 2 Figure 3 Figure 4 Key Points Radiomics features from CTE can predict the inflammatory activity of CD. The nomograms perform best in the prediction of inflammatory activity. The radiomics improved radiologists’ performance in evaluating inflammatory activity. Introduction Crohn’s disease (CD) is a chronic, relapsing and inflammatory disease involving the whole gastrointestinal tract that can impact patient's quality of life and lead to various complications if not properly managed[ 1 ]. Therefore, an accurate and efficient evaluation of activity severity is vitally important in CD monitoring and management[ 2 ]. There are multiple well-established scoring criteria to assess disease activity in CD, including Crohn’s disease activity index and Harvey-Bradshaw index based on symptoms and physical signs, Crohn’s disease endoscopic index of severity and simple endoscopic score for Crohn’s disease (SES-CD) according to endoscopic findings, magnetic resonance index of activity (MaRIA), Clermont score and magnetic resonance enterograpgy global score (MEGS) using magnetic resonance enterography[ 3 – 6 ]. Among them, endoscopic scoring has been commonly used and considered as the reference standard in many studies. However, endoscopic procedure has some limitations, e.g., invasive, costly, and accompanied by risks of complications[ 7 , 8 ]. Computed tomography enterography (CTE) is usually the first-choice modality for CD[ 9 ]. Compared with MRE, CTE demonstrates a similar specificity and sensitivity in diagnosing CD[ 10 ], and, moreover, reveals greater feasibility because of shorter imaging time, higher spatial and temporal resolution, fewer artifacts, and lower cost[ 11 ]. Radiomics, a well-acknowledged method for high-throughput extraction of quantitative parameters from medical images, can illustrate invisible tissue heterogeneity and has been recently proposed as a promising tool to facilitate the transition to personalized medicine in clinical practice[ 12 ]. A few studies reported that the radiomic model based on MRI data predicted CD diagnosis with better performance than MaRIA evaluated by the senior radiologist[ 13 , 14 ]. Moreover, there are some studies using mesenteric or/and intestinal CTE radiomics signatures to predict the therapeutic response, postoperative anastomotic recurrence, fibrosis and disease progression and are more accurate than clinical factors or senior radiologists[ 11 , 13 , 15 – 19 ]. However, there are no validated CD activity scores derived from CTE. Therefore, it is essential to develop a reliable, objective and validated method to identify CTE CD lesions and assess CD activity. In this study, we aimed to establish and validate nomograms to predict different CD activity statuses by combining CTE-based radiomics and morphological features. Materials and methods Patient selection This retrospective study was approved by the institutional review board of our hospital (approval number: 2013KY034), and written informed consent from each participant was waived. We searched the radiology reports for the term Crohn’s disease on CTE scans obtained between January 2017 and June 2023. The inclusion criteria were as follows: (1) established CD diagnosis by conventional clinical, endoscopic and histologic criteria, (2) undergo ileocolonoscopy within two days after CTE, and (3) had not received any new medication between the 2 examinations. The exclusion criteria were as follows: (1) inadequate imaging quality which was unable to segment, for example breathing artifact, (2) not readily identifiable intestinal contour on CTE due to severe perienteric effusion, intestinal adhesion or intestinal peristalsis. Enrolled segments were randomly divided into a training cohort and a testing cohort at a ratio of 7:3. The study flow diagram is shown in Fig. 1 . Reference Standard for intestinal inflammatory activity The ileocolonoscopic procedure and evaluation were performed by two gastroenterologists (with 15- and 20-years work experience) without knowledge of CTE results. The ileocolon was divided into 5 segments on ileocolonoscopy and CTE including terminal ileum (the last 20 cm of small bowel proximal to the ileocecal valve), right colon (ileocecal valve, cecum and ascending colon), transverse colon, left colon (descending and sigmoid colon), and rectum[ 15 ]. The gastroenterologists scored the ileocolonoscopy findings in consensus for each segment according to SES-CD during endoscopy. The bowel segments were classified by SES-CD as inactive (0–2), mild (3–6), or moderate-severe (≥ 7)[ 15 ]. Discrepancies between reviewers were resolved by consensus reading. The final results were used for further statistical analyses. Computed tomography enterography examination and CT morphological features by radiologists CTE imaging technique CTE examinations were performed on a dual-source dual-energy CT scanner (Somatom Definition, Siemens Healthineers, Forchheim GER) with tube current modulation (Care-Dose 4D), tube voltages of 100 kVp (A tube) and Sn-filtered 140 kVp (B tube). All subjects were scanned in supine position. Fasting for solid food with a time interval of 8 hours prior to CTE scan was requested for each subject. Also, all subjects needed to drink 300 mL of mannitol (2.5%) every 15 min until a total of 1.5 L had been consumed within 60 minutes. Intravenous contrast dosing (Ultravist, Bayer, GA) delivered at 3 mL/s was utilized. Images at axial direction with slice thickness of 1 mm from the diaphragm to pubic symphysis were acquired and sent to the picture archiving and communication system (PACS) (Carestream Health, Inc, Rochester, US). CTE acquisition consisted of the venous phase at 60 seconds after contrast administration. CTE morphological analysis and model construction There are five qualitative morphological features obtained by evaluating CTE: (1) bowel wall thickness graded with a score of 0 ( 10mm), (2) lumen stenosis[ 15 ] characterized as ≥ 50% reduction in luminal diameter in comparison with that of the adjacent loop, together with unequivocal upstream dilation of the same loop (> 3 cm in caliber) and graded with a score of 0 (none), 1 (present), (3) mural enhancement[ 15 ], 0 (homogenous), 1 (asymmetric), 2 (stratified), (4) comb sign defined by CT features of segmental dilatation of the vasa recta involving a bowel loop[ 15 ], 0 (none), 1 (present), (5) fat infiltration defined as locally and increased inhomogeneous attenuation in the perienteric fat, compared with the perienteric fat adjacent to non-inflamed bowel loops[ 15 ], 0 (none), 1 (present). A radiologist with 20 years of experience in abdominal CT, blinded to the endoscopic results, evaluated these five features and scored. The above five morphological features were used as the input of the multiple logistic regression analysis, and then a morphological model (M-score) was built. Bowel segmentation and radiomics features extraction Figure 1 shows the flow chart of our study. CTE venous phase images were used for lesion extraction. The volumes of interest (VOIs) were drawn along the lesion contour on each transverse section until the full lesion was captured excluding the intestinal lumen. A radiologist (reader 1, with 5 years of diagnostic experience in abdominal imaging) manually delineated three-dimensional (3D) VOIs by using an open-source medical imaging software (3D-Slicer, version 5.5.0, https://www.slicer.org ), and was blinded to the results of ileocolonoscopy. To standardize the voxel spacing across the cohort, all CT voxels were resampled to 1×1×1mm 3 before feature extraction. A fixed bin width of 25 Hounfield units (HU) was used during the calculation of texture features. A total of 851 radiomics features were extracted, including shape, first-order, second-order and wavelet-filter features. To evaluate the inter-/intra-observer reproducibility of the extracted features, 30 segments randomly selected from the training cohort were segmented twice over a 4-weeks interval by another radiologist (reader 2, with 5 years’ working experience in abdominal imaging) with the same procedures. The intraclass correlation coefficients (ICCs) were calculated using a two-way random effects model to determine inter-/intra-observer reliabilities. Only the features with ICC more than 0.75 were included in further analysis. Radiomics model and morphological radiomics nomogram construction Firstly, pair-wise correlation analysis was performed to remove redundant radiomics features, by using the “findCorrelation” function in R package “caret” with the absolute correlation cutoff set at 0.9. Then, least absolute shrinkage and selection (LASSO) logistic regression was adopted to select the most predictive radiomics features from the training cohort[ 20 ]. The penalty parameter lambda determining feature selection was chosen by 10-fold cross-validation. Next, a radiomics signature score (Rad-score) was constructed with a linear combination of selected features weighted by their coefficients. A nomogram by combining the M-score and the Rad-score was constructed. Statistical analysis All categorical variables were summarized as number (percent) and compared using the Fisher’s exact test. The diagnostic performance of the morphological model, the radiomics model, and the nomogram was evaluated based on the area under the receiver operating characteristic (ROC) curve in both the training cohort and testing cohort. Delong method was employed to test the differences of the area under the ROC curves (AUC) among three models. Calibration curves were applied to evaluate the performance of the nomogram. Decision curve analysis (DCA) was conducted to evaluate the clinical efficacy of the nomogram by quantifying the net benefit at different threshold probabilities across the training and testing cohorts. Statistical analysis was performed using R software (version 4.3.1, www.r-project.org ) with packages caret , glmnet , pROC , reportROC , rms , rmda and survival . A two-sided P < 0.05 was considered significant. Results Patient characteristics A total of 54 patients with 237 bowel segments were included in the study. According to the SES-CD, 237 ileocolonic segments with CD lesions were identified as: inactive (n = 158), mild (n = 47), and moderate to severe (n = 32). The stratified distributions of SES-CD scores were compared between the training and test cohorts (Table 1 ). 166 segments in training cohort and 71 segments in testing cohort were applied for differentiating active from remissive disease, while 55 in training cohort and 24 in testing cohort were used for distinguishing mild from moderate-to-severe active disease. Table 1 Comparison of clinical data between training and testing cohort Active vs. inactive Mild vs. moderate-to-severe Training cohort n = 166 Testing cohort n = 71 Training cohort n = 55 Testing cohort n = 24 Segments with SES-CD score available , n (%) P = 0.988 P = 0.689 terminal ileum 25 (15.1) 12 (16.9) 11 (20.0) 6 (25.0) right colon 33 (19.9) 14 (19.7) 17 (30.9) 8 (33.3) transverse colon 32 (19.3) 15 (21.1) 7 (12.7) 2 (8.3) left colon 38 (22.9) 15 (21.1) 13 (23.6) 3 (12.5) rectum 38 (22.9) 15 (21.1) 7 (12.7) 5 (20.8) Morphology features bowel wall thickness, n (%) P = 0.462 P = 0.566 0 62 (37.3) 25 (35.2) 1 (1.8) 1 (4.2) 1 48 (28.9) 21 (29.6) 7 (12.7) 4 (16.7) 2 30 (18.1) 18 (25.4) 22 (40.0) 12 (50.0) 3 26 (15.7) 7 (9.9) 25 (45.5) 7 (29.2) lumen stenosis P = 0.289 P = 0.941 0 133 (80.1) 61 (85.9) 28 (50.9) 12 (50.0) 1 33 (19.9) 10 (14.1) 27 (49.1) 12 (50.0) mural enhancement P = 0.738 P = 0.632 0 114 (68.7) 50 (70.4) 16 (29.1) 9 (37.5) 1 51 (30.7) 20 (28.2) 38 (69.1) 15 (62.5) 2 1 (0.06) 1 (1.4) 1 (1.8) 0 (0) comb sign P = 0.030 P = 0.975 0 124 (74.7) 53 (74.6) 25 (45.5) 11 (45.8) 1 42 (25.3) 18 (25.4) 30 (54.5) 13 (54.2) fat infiltration P = 0.267 P = 0.128 0 102 (61.4) 49 (69.0) 8 (14.5) 7 (29.2) 1 64 (38.6) 22 (31.0) 47 (85.5) 17 (70.8) SES-CD , n (%) P = 0.160 P = 0.719 Inactive (0–2) 106 (63.9) 52 (73.2) Mild (3–6) 60 (36.1) 19 (26.8) 32 (58.2) 15 (62.5) Moderate-to-severe (≥ 7) 23 (41.8) 9 (37.5) Note: SES-CD = simple endoscopic score for Crohn’s disease Development and validation of models and nomogram for discriminating inactive from active bowel segments Morphological features selection and M-score1 development Bowel stenosis and comb sign were significantly related to the activity of segments by using multivariate analysis ( P < 0.05). Both morphological features were thus included to build M-score1: -2.197 + 3.960×stenosis + 3.407×comb sign. The AUC was 0.870 (95% CI: 0.810–0.930) in the training cohort and 0.747 (95% CI: 0.638–0.855) in the testing cohort (Table 2 ). Table 2 Performance of models for differentiating active from inactive disease models Training cohort Testing cohort AUC (95%CI) Accuracy Sensitivity Specificity AUC (95%CI) Accuracy Sensitivity Specificity M-score1 0.870(0.810–0.930) 0.892 0.774 0.947 0.747(0.638–0.855) 0.775 0.577 0.889 Rad-score1 0.857(0.797–0.918) 0.771 0.830 0.743 0.828(0.720–0.937) 0.789 0.769 0.800 Combine-model1 0.944(0.905–0.982) 0.916 0.868 0.938 0.834(0.728–0.940) 0.803 0.692 0.867 Radiomics features selection and Rad-score1 development There were 851 radiomics features extracted from the venous CT images per segment. A total of 830 features with inter-/intra-observer ICCs of ≥ 0.75 were retained as factors for developing the radiomics model. Further reduction of pair-wise correlations led to 494 independent features. After LASSO logistic regression from the training cohort (Fig. 2 ), three radiomics features with non-zero coefficients were selected to distinguish inactive from active segments. The Rad-score1 (inactive vs. active) was calculated by the following formula: -0.8875 + 0.9790×wavelet-LLL-firstorder-Energy + 0.6177×wavelet-HLL-glszm-SizeZoneNonUniformity + 0.6542×original-firstorder-Median. The AUC was 0.857 (95% CI: 0.797–0.918) in the training cohort and 0.828 (95% CI: 0.720–0.917) in the testing cohort (Table 2 ) for differentiating active from inactive bowel segments. Although M-score1 performed better than Rad-score1 in differentiating activities in training cohort, Delong test showed that there was no significant difference between the two models ( P > 0.05). Development and validation of combine-model1 and nomogram Finally, we combined the M-score1 and Rad-scor1 to construct the combine-model1: 0.4841 + 0.7422×M-score1 + 0.8732×Rad-score1. The prediction performance of combine-model1 achieved the optimal efficacy in bowel segments with an AUC, accuracy, sensibility and specificity of 0.834 (95% CI: 0.728–0.940), 0.803, 0.692, 0.867 in the testing cohort respectively (Table 2 ). Either in training cohort or in testing cohort, the AUC of combine-model1 performed better than M-score1 ( P < 0.05) (Table 4 ). A nomogram based on the combine-model1 was built to visualize the results (Fig. 2 ). The calibration curve of the nomogram revealed good predictive accuracy between the actual probability and predicted probability. The DCA demonstrated a highly positive net benefit of the nomogram within a certain range (Fig. 3 ). Development and validation of models and nomogram for discriminating mild active from moderate-to-severe active bowel segments Construction of three models We used the same modelling process aforementioned for distinguishing mild active from moderate-to-severe active bowel segments. The M-score2 (mild vs. moderate-to-severe) was calculated as following: -1.1787 + 1.0916×comb sign. There was one radiomics feature included in Rad-score 2 after LASSO logistic regression from the training cohort: -1.2670 + 1.3048×wavelet-HLL-glszm-SizeZoneNonUniformity. Then, the combine-model2 was constructed with the linear combination of the M-score2 and the Rad-model2 as following: -1.9143 + 1.0340×M-score2 + 1.3627×Rad-score2, and the nomogram for differentiating mild activity from moderate-to-severe activity was plotted based on the combine-model2 (Fig. 4 ). Performance comparison Table 3 summarized the AUC, accuracy, sensibility and specificity. The combine-model2 showed a favorable performance with AUC of 0.817 (95% CI: 0.676–0.958) and 0.781 (95% CI: 0.611–0.951) in the training and testing cohort, respectively. Moreover, Delong test revealed that the difference of predictive performance was statistically significant between combine-model2 and M-model2 or Rad-score2 (both, P < 0.05, Table 4 ). Table 3 Performance of models for distinguishing mild from moderate-to-severe activity models Training cohort Testing cohort AUC (95%CI) Accuracy Sensitivity Specificity AUC (95%CI) Accuracy Sensitivity Specificity M-score2 0.701(0.554–0.847) 0.692 0.765 0.636 0.627(0.474–0.780) 0.600 0.733 0.520 Rad-score2 0.755(0.590–0.921) 0.795 0.588 0.955 0.757(0.585–0.930) 0.825 0.533 1.000 Combine-model2 0.817(0.676–0.958) 0.795 0.706 0.864 0.781(0.611–0.951) 0.825 0.600 0.960 Table 4 The comparison among the three different models Active vs. inactive Mild vs. moderate-to-severe Training cohort Testing cohort Training cohort Testing cohort M-score versus combine 0.002 ※ 0.028 ※ 0.040 ※ 0.033 ※ Rad versus combine 0.001 ※ 0.841 0.042 ※ 0.055 Rad versus M-score 0.755 0.171 0.631 0.647 ※ Delong test Calibration and clinical utility of models Calibration plots and DCA of three models in the testing cohort for distinguishing mild activity from moderate-to-severe activity were shown in Fig. 4 . Discussion We used CTE images to develop and validate a radiomics-based nomogram for identifying the activity of CD lesions. Our study demonstrated that in both the training and testing cohorts, the nomogram combined by imaging morphological features and radiomics features could accurately distinguish the activity severity and act better than either single radiomics model or imaging morphological model. Furthermore, DCA confirmed its clinical effect. CD has a variable clinical course, with alternating periods of disease activity and remission[ 15 ]. Hence, it is essential to accurately and timely distinguish the activity of CD to help clinicians choose the appropriate treatments. The SES-CD score is the most reliable and easy-to-use endoscopic scoring tool for CD[ 21 ]. However, failure to intubate the ileum is a major challenge when using the SES-CD as a primary outcome in clinical trials[ 22 ]. CTE is an imaging method that can evaluate not only the whole gastrointestinal tract involvement but also the extra-intestinal complications noninvasively. Our study researched the imaging morphological features. Multi-logistic analysis indicated that stenosis and comb sign were significant correlated. Stenosis is the most often seen in patients with active inflammation, although fibrosis and inflammation are often both present[ 15 ]. Comb sign results from increased blood supply and drainage of a small bowel segment[ 23 ]. Wu et al [ 24 ]reported that quantitative comb sign results are robust in predicting CD activity with the accuracy rate of 80% at venous stage. A simplified CT enterography index of activity combined with mural thickness, mural stratification and comb sign revealed high and significant correlation with CD activity[ 25 ], with the AUC of 0.901, where our combined model is better than this (AUC = 0.944). In addition, Lopes et al[ 26 ] found that endoscopic remission at 1-year follow up significantly correlated with improvement in mural hyperenhancement, mesenteric fat densification, comb sign, and strictures in CTE. Those results also proved our morphological models were robust. We included 851 radiomics features. Based on the results of multivariate analysis, we built the radiomics model, including: original-firstorder-Median, wavelet-LLL-firstorder-Energy, wavelet-HLL-glszm-SizeZoneNonUniformity. “Median” represents the median gray level intensity within the ROI. Previous studies confirmed that the mean normalized iodine density is highly sensitive and specific for endoscopic active inflammation in CD patients[ 27 , 28 ]. It suggests that the gray level intensity is related to the activity of bowel segments, which is consistent with our results. The two other features were Wavelet-filter features, Prior researches have concluded that it may reveal the heterogeneity of ROI and suggested a poor prognosis[ 29 ]. Ding et al [ 13 ]also reported that a MR radiomics model included five Wavelet-filter features can evaluate the inflammatory severity and was comparable to MaRIA evaluated by a senior radiologist. As radiomics researches in many other diseases[ 30 – 32 ], we constructed the nomogram by combining both morphological and radiomics features, which achieved the best predictive ability both in training cohorts and testing cohorts. To the best of our knowledge, few studies have been conducted to develop a radiomics model based on CTE imaging for assessing the disease activity. We also develop different models to discriminate not only active from inactive but also mild active from moderate-to-severe active diseases. It should be recognized that our study has several limitations. Firstly, this study was retrospective in nature, which needs further evaluation to validate these results. Secondly, the number of patients was small. We need to test multi-center and more patients to validate the accuracy of these models in future. Finally, we employed 3D segmentation technology manually in the colon and ileocecal regions, which elapsed more time than those of 2D segmentation. It is essential to develop a high-throughput method for automatic extraction of a large number of quantitative imaging features from medical images in the future. In conclusion, the combined model based on CTE radiomics and morphological features was built for the discrimination of mucosal activity measured by SES-CD. The nomogram is of satisfactory ability in clinical utility in differentiating different levels of activities in patients with CD. Abbreviations 3D Three-dimensional AUC Area under the ROC curve CD Crohn’s Disease CTE Computed tomography enterography DCA Decision curve analysis ROC Receiver operating characteristic VOI Volume of interest SES-CD Simple endoscopic score for Crohn’s disease Declarations Acknowledgements No. Authors’ contributions All authors played an important role in this research. Specific contributions are listed as follows: Yuping Ma : Data curation, Software, Writing-original draft. Luanxin Zhu : Data curation, Software, Writing-original draft. Bota Cui : Data curation. Faming Zhang : Data curation. Writing-review & editing. Haige Li : Validation, Visualization. Jianguo Zhu : Conceptualization, Formal analysis, Methodology, Resources, Project administration, Supervision, Writing-review & editing. All authors reviewed the analyses and drafts of this manuscript and approved its final version. Funding The authors state that this work has not received any funding. Availability of data and materials All datasets and materials used and/or analyzed during the current study are available from the corresponding authors on any reasonable request. Ethics approval and consent to participate The studies involving human participants were reviewed and approved by the Institutional Review Board and Ethics Committee of the Second Affiliated Hospital of Nanjing Medical University (ethical approval number: 2013KY034). Due to the retrospective nature of the current study, the Ethics Committee of the Second Affiliated Hospital of Nanjing Medical University waived the requirement for written informed consent from each participant. We confirm that all methods were carried out in accordance with relevant guidelines and regulations. Consent for publication Not applicable. Competing interests All authors have no conflicts of interest to declare. References Ng SC, Shi HY, Hamidi N, Underwood FE, Tang W, Benchimol EI, Panaccione R, Ghosh S, Wu JC, Chan FK. Worldwide incidence and prevalence of inflammatory bowel disease in the 21st century: a systematic review of population-based studies. Lancet. 2017;390(10114):2769–78. Maaser C, Sturm A, Vavricka SR, Kucharzik T, Fiorino G, Annese V, Calabrese E, Baumgart DC, Bettenworth D, Borralho Nunes P. ECCO-ESGAR Guideline for Diagnostic Assessment in IBD Part 1: Initial diagnosis, monitoring of known IBD, detection of complications. J Crohn's Colitis. 2019;13(2):144–K164. Sturm A, Maaser C, Calabrese E, Annese V, Fiorino G, Kucharzik T, Vavricka SR, Verstockt B, van Rheenen P, Tolan D. ECCO-ESGAR Guideline for Diagnostic Assessment in IBD Part 2: IBD scores and general principles and technical aspects. J Crohn's Colitis. 2019;13(3):273–84. Mao L, Li Y, Cui B, Lu L, Dou W, Pylypenko D, Zhu J, Li H. Multiparametric MRI for Staging of Bowel Inflammatory Activity in Crohn's Disease with MUSE-IVIM and DCE-MRI: A Preliminary Study. Academic Radiology 2023. Zhu J, Zhang F, Zhou J, Li H. Assessment of therapeutic response in Crohn's disease using quantitative dynamic contrast enhanced MRI (DCE-MRI) parameters: A preliminary study. Medicine 2017, 96(32). Zhu J, Zhang F, Luan Y, Cao P, Liu F, He W, Wang D. Can dynamic contrast-enhanced MRI (DCE-MRI) and diffusion-weighted MRI (DW-MRI) evaluate inflammation disease: a preliminary study of Crohn's disease. Medicine 2016, 95(14). Fernandes SR, Rodrigues RV, Bernardo S, Cortez-Pinto J, Rosa I, da Silva JP, Gonçalves AR, Valente A, Baldaia C, Santos PM. Transmural healing is associated with improved long-term outcomes of patients with Crohn's disease. Inflamm Bowel Dis. 2017;23(8):1403–9. Chavoshi M, Mirshahvalad SA, Kasaeian A, Djalalinia S, Kolahdoozan S, Radmard AR. Diagnostic accuracy of magnetic resonance enterography in the evaluation of colonic abnormalities in Crohn's disease: a systematic review and meta-analysis. Acad Radiol. 2021;28:S192–202. Cipriano LE, Levesque BG, Zaric GS, Loftus EV Jr, Sandborn WJ. Cost-effectiveness of imaging strategies to reduce radiation-induced cancer risk in Crohn's disease. Inflamm Bowel Dis. 2012;18(7):1240–8. de Sousa HT, Brito J, Magro F. New cross-sectional imaging in IBD. Curr Opin Gastroenterol. 2018;34(4):194–207. Gao Y, Zhang B, Zhao D, Li S, Rong C, Sun M, Wu X. Automatic segmentation and radiomics for identification and activity assessment of CTE lesions in Crohn’s disease. Inflamm Bowel Dis 2023:izad285. Lambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, Van Stiphout RG, Granton P, Zegers CM, Gillies R, Boellard R, Dekker A. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer. 2012;48(4):441–6. Ding H, Li J, Jiang K, Gao C, Lu L, Zhang H, Chen H, Gao X, Zhou K, Sun Z. Assessing the inflammatory severity of the terminal ileum in Crohn disease using radiomics based on MRI. BMC Med Imaging. 2022;22(1):118. Liu RX, Li H, Towbin AJ, Ata NA, Smith EA, Tkach JA, Denson LA, He L, Dillman JR. Machine learning diagnosis of small-bowel Crohn disease using T2-weighted MRI radiomic and clinical data. Am J Roentgenol. 2024;222(1):e2329812. Magalhães FC, Lima EM, Carpentieri-Primo P, Barreto MM, Rodrigues RS, Parente DB. Crohn’s disease: review and standardization of nomenclature. Radiologia Brasileira. 2023;56:95–101. Zhu C, Hu J, Wang X, Li C, Gao Y, Li J, Ge Y, Wu X. A novel clinical radiomics nomogram at baseline to predict mucosal healing in Crohn’s disease patients treated with infliximab. Eur Radiol. 2022;32(10):6628–36. Li X, Zhang N, Hu C, Lin Y, Li J, Li Z, Cui E, Shi L, Zhuang X, Li J. CT-based radiomics signature of visceral adipose tissue for prediction of disease progression in patients with Crohn's disease: A multicentre cohort study. EClinicalMedicine 2023, 56. Ruiqing L, Jing Y, Shunli L, Jia K, Zhibo W, Hongping Z, Keyu R, Xiaoming Z, Zhiming W, Weiming Z. A Novel Radiomics Model Integrating Luminal and Mesenteric Features to Predict Mucosal Activity and Surgery Risk in Crohn's Disease Patients: A Multicenter Study. Academic Radiology 2023. Zhang R-n, Huang S-y, Liu R-y, Meng J-x, Zhou J, Chen Z, Fang J-y, Mao R, Li Z-p. Sun C-h: Preoperative computed tomography enterography-based radiomics signature: A potential predictor of postoperative anastomotic recurrence in patients with Crohn’s disease. Eur J Radiol. 2023;162:110766. Tibshirani R. The lasso method for variable selection in the Cox model. Stat Med. 1997;16(4):385–95. Daperno M, D'Haens G, Van Assche G, Baert F, Bulois P, Maunoury V, Sostegni R, Rocca R, Pera A, Gevers A. Development and validation of a new, simplified endoscopic activity score for Crohn's disease: the SES-CD. Gastrointest Endosc. 2004;60(4):505–12. Meral M, Bengi G, Kayahan H, Akarsu M, Soytürk M, Topalak Ö, Akpinar H, Sagol Ö. Is ileocecal valve intubation essential for routine colonoscopic examination? Eur J Gastroenterol Hepatol. 2018;30(4):432–7. Meyers M, McGuire P. Spiral CT demonstration of hypervascularity in Crohn disease:vascular jejunization of the ileum or the comb sign. Abdom Imaging. 1995;20:327–32. Wu Y-W, Tao X-F, Tang Y-H, Hao N-X, Miao F. Quantitative measures of comb sign in Crohn’s disease: correlation with disease activity and laboratory indications. Abdom Imaging. 2012;37:350–8. Tong J, Feng Q, Zhang C, Xu X, Ran Z. CT enterography for evaluation of disease activity in patients with ileocolonic Crohn's disease. BMC Gastroenterol. 2022;22(1):1–10. Lopes S, Andrade P, Afonso J, Cunha R, Rodrigues-Pinto E, Ramos I, Macedo G, Magro F. Monitoring Crohn’s disease activity: endoscopy, fecal markers and computed tomography enterography. Therapeutic Adv Gastroenterol. 2018;11:1756284818769075. Dane B, Kernizan A, O’Donnell T, Petrocelli R, Rabbenou W, Bhattacharya S, Chang S, Megibow A. Crohn’s disease active inflammation assessment with iodine density from dual-energy CT enterography: comparison with endoscopy and conventional interpretation. Abdom Radiol. 2022;47(10):3406–13. Dane B, Sarkar S, Nazarian M, Galitzer H, O’Donnell T, Remzi F, Chang S, Megibow A. Crohn disease active inflammation assessment with iodine density from dual-energy CT enterography: comparison with histopathologic analysis. Radiology. 2021;301(1):144–51. Depeursinge A, Foncubierta-Rodriguez A, Van De Ville D, Müller H. Three-dimensional solid texture analysis in biomedical imaging: review and opportunities. Med Image Anal. 2014;18(1):176–96. Bao D, Zhao Y, Li L, Lin M, Zhu Z, Yuan M, Zhong H, Xu H, Zhao X, Luo D. A MRI-based radiomics model predicting radiation-induced temporal lobe injury in nasopharyngeal carcinoma. Eur Radiol. 2022;32(10):6910–21. Zhang Y, Liu L, Zhang K, Su R, Jia H, Qian L, Dong J. Nomograms Combining Clinical and Imaging Parameters to Predict Recurrence and Disease-free Survival After Concurrent Chemoradiotherapy in Patients With Locally Advanced Cervical Cancer. Acad Radiol. 2023;30(3):499–508. Zheng R, Zhang X, Liu B, Zhang Y, Shen H, Xie X, Li S, Huang G. Comparison of non-radiomics imaging features and radiomics models based on contrast-enhanced ultrasound and Gd-EOB-DTPA-enhanced MRI for predicting microvascular invasion in hepatocellular carcinoma within 5 cm. Eur Radiol 2023:1–11. Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 27 Jan, 2025 Read the published version in BMC Medical Imaging → Version 1 posted Editorial decision: Revision requested 12 Dec, 2024 Reviews received at journal 22 Nov, 2024 Reviewers agreed at journal 18 Nov, 2024 Reviews received at journal 17 Nov, 2024 Reviewers agreed at journal 28 Oct, 2024 Reviews received at journal 23 Jul, 2024 Reviewers agreed at journal 21 Jul, 2024 Reviewers invited by journal 11 Jul, 2024 Editor invited by journal 28 May, 2024 Editor assigned by journal 28 May, 2024 Submission checks completed at journal 28 May, 2024 First submitted to journal 23 May, 2024 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-4465032","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":309569397,"identity":"f9840ec1-1601-410f-8542-b9b49bb7a6df","order_by":0,"name":"Yuping Ma","email":"","orcid":"","institution":"the Second Affiliated Hospital of Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yuping","middleName":"","lastName":"Ma","suffix":""},{"id":309569398,"identity":"70430720-ea3d-4bb6-8fa2-60c8cf2c459a","order_by":1,"name":"Luanxin Zhu","email":"","orcid":"","institution":"Xuzhou Medical University","correspondingAuthor":false,"prefix":"","firstName":"Luanxin","middleName":"","lastName":"Zhu","suffix":""},{"id":309569399,"identity":"1fed123f-91ba-442e-b24c-e8a386489c72","order_by":2,"name":"Bota Cui","email":"","orcid":"","institution":"the Second Affiliated Hospital of Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Bota","middleName":"","lastName":"Cui","suffix":""},{"id":309569400,"identity":"bc2254eb-f1f7-4d0d-a992-bea346c8bf50","order_by":3,"name":"Faming Zhang","email":"","orcid":"","institution":"the Second Affiliated Hospital of Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Faming","middleName":"","lastName":"Zhang","suffix":""},{"id":309569401,"identity":"4d824383-62e5-427a-bf53-88173d87004d","order_by":4,"name":"Haige Li","email":"","orcid":"","institution":"the Second Affiliated Hospital of Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Haige","middleName":"","lastName":"Li","suffix":""},{"id":309569402,"identity":"998d057f-9938-47c1-b20e-88f6c632592f","order_by":5,"name":"Jianguo Zhu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9ElEQVRIiWNgGAWjYDACCQYGgwQwi/kAiAMECURrYUsgXgsU8BhAGQS0yM/uMSh4UHPHbsPxnm8PLHMOM/Cz5xgw/NyBWwvjnDMGBgnHniVvOHN2u4HktsMMkj1vDBh7z+DWwiyRA9TCdjjZ4EbuNgmQFoMbOQbMjG24tbCBtfwDacl5BtZiT0gLD0hLYtthO6AWNogtEgS0SEikFRgk9h1OkDxzzAyoJZ1H4syzgoO9eLTIz0jeZvjj22F7vuPNz6Qlt1nL8bcnb3zwE48WkHdA8ZHYAA4LoEtBQgfwagAqfAAk7EEsxg8ElI6CUTAKRsHIBABTQVDfZv/HJgAAAABJRU5ErkJggg==","orcid":"","institution":"the Second Affiliated Hospital of Nanjing Medical University","correspondingAuthor":true,"prefix":"","firstName":"Jianguo","middleName":"","lastName":"Zhu","suffix":""}],"badges":[],"createdAt":"2024-05-23 07:34:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4465032/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4465032/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12880-025-01560-0","type":"published","date":"2025-01-27T15:57:22+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":58229115,"identity":"8393fb46-b937-438c-9f49-585a529fd3f0","added_by":"auto","created_at":"2024-06-12 19:14:02","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":726788,"visible":true,"origin":"","legend":"\u003cp\u003eFlow diagram of the study population and radiomics workflow.\u003c/p\u003e\n\u003cp\u003eNote：\u003c/p\u003e\n\u003cp\u003eCD = Crohn’s disease\u003c/p\u003e\n\u003cp\u003eLASSO =least absolute shrinkage and selection\u003c/p\u003e\n\u003cp\u003eDCA = decision curve analysis\u003c/p\u003e","description":"","filename":"FIgure1.png","url":"https://assets-eu.researchsquare.com/files/rs-4465032/v1/a55c2b4522d51a3520173357.png"},{"id":58230779,"identity":"0717f2da-9f7c-43d3-b556-ca9592f47035","added_by":"auto","created_at":"2024-06-12 19:22:02","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":472424,"visible":true,"origin":"","legend":"\u003cp\u003eScreening of variables based on Lasso regression.\u003c/p\u003e\n\u003cp\u003e(a) and (b) are Lasso regression for predicting active and inactive disease, (c) and (d) are for mild and moderate-to-moderate activity. (a) and (c) are the variation characteristics of the coefficients of variables; (b) and (d) are the selection process of the optimum value of the parameter λ in the Lasso regression model by 10-fold cross-validation method.\u003c/p\u003e","description":"","filename":"Figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-4465032/v1/a2689205cfabe33abb52e8c5.png"},{"id":58229116,"identity":"eca5010a-b0a1-48f8-96da-050592b29829","added_by":"auto","created_at":"2024-06-12 19:14:03","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":552868,"visible":true,"origin":"","legend":"\u003cp\u003eThe output of three models in distinguishing active from inactive disease.\u003c/p\u003e\n\u003cp\u003e(a-b) ROC of combine-model, radiomics-model and morphology model in the training and testing cohort. (c) Calibration of three models in the testing cohort. (d) Decision curve analysis (DCA) of three model in the testing cohort. (e) Nomogram constructed by morphology radiomics combine model.\u003c/p\u003e","description":"","filename":"Figure3.png","url":"https://assets-eu.researchsquare.com/files/rs-4465032/v1/804538efabadd4a6cd744413.png"},{"id":58229113,"identity":"75ff1e13-3434-42e7-866f-5e6a3457490d","added_by":"auto","created_at":"2024-06-12 19:14:02","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":628089,"visible":true,"origin":"","legend":"\u003cp\u003eThe output of three models in distinguishing mild from moderate-to-severe activity.\u003c/p\u003e\n\u003cp\u003e(a-b) ROC of combine-model, radiomics-model and morphology model in the training and testing cohort. (c) Calibration of three models in the testing cohort. (d) Decision curve analysis (DCA) of three model in the testing cohort. (e) Nomogram constructed by morphology radiomics combine model.\u003c/p\u003e","description":"","filename":"Figure4.png","url":"https://assets-eu.researchsquare.com/files/rs-4465032/v1/a972b37cac7653aa12062a85.png"},{"id":75351265,"identity":"99543e81-f71f-4b2d-a1a0-43c79893d9ca","added_by":"auto","created_at":"2025-02-03 16:08:43","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4106534,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4465032/v1/e8923d2f-dcd8-4974-aab5-6e22aa5e978d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Computed Tomography Enterography-Based Radiomics Nomograms to Predict Inflammatory Activity for Ileocolonic Crohn’s Disease","fulltext":[{"header":"Key Points","content":"\u003col\u003e\n \u003cli\u003eRadiomics features from CTE can predict the inflammatory activity of CD.\u003c/li\u003e\n \u003cli\u003eThe nomograms perform best in the prediction of inflammatory activity.\u003c/li\u003e\n \u003cli\u003eThe radiomics improved radiologists\u0026rsquo; performance in evaluating inflammatory activity.\u003c/li\u003e\n\u003c/ol\u003e"},{"header":"Introduction","content":"\u003cp\u003eCrohn\u0026rsquo;s disease (CD) is a chronic, relapsing and inflammatory disease involving the whole gastrointestinal tract that can impact patient's quality of life and lead to various complications if not properly managed[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Therefore, an accurate and efficient evaluation of activity severity is vitally important in CD monitoring and management[\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThere are multiple well-established scoring criteria to assess disease activity in CD, including Crohn\u0026rsquo;s disease activity index and Harvey-Bradshaw index based on symptoms and physical signs, Crohn\u0026rsquo;s disease endoscopic index of severity and simple endoscopic score for Crohn\u0026rsquo;s disease (SES-CD) according to endoscopic findings, magnetic resonance index of activity (MaRIA), Clermont score and magnetic resonance enterograpgy global score (MEGS) using magnetic resonance enterography[\u003cspan additionalcitationids=\"CR4 CR5\" citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. Among them, endoscopic scoring has been commonly used and considered as the reference standard in many studies. However, endoscopic procedure has some limitations, e.g., invasive, costly, and accompanied by risks of complications[\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. Computed tomography enterography (CTE) is usually the first-choice modality for CD[\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. Compared with MRE, CTE demonstrates a similar specificity and sensitivity in diagnosing CD[\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e], and, moreover, reveals greater feasibility because of shorter imaging time, higher spatial and temporal resolution, fewer artifacts, and lower cost[\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. Radiomics, a well-acknowledged method for high-throughput extraction of quantitative parameters from medical images, can illustrate invisible tissue heterogeneity and has been recently proposed as a promising tool to facilitate the transition to personalized medicine in clinical practice[\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. A few studies reported that the radiomic model based on MRI data predicted CD diagnosis with better performance than MaRIA evaluated by the senior radiologist[\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e, \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]. Moreover, there are some studies using mesenteric or/and intestinal CTE radiomics signatures to predict the therapeutic response, postoperative anastomotic recurrence, fibrosis and disease progression and are more accurate than clinical factors or senior radiologists[\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e, \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e, \u003cspan additionalcitationids=\"CR16 CR17 CR18\" citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. However, there are no validated CD activity scores derived from CTE. Therefore, it is essential to develop a reliable, objective and validated method to identify CTE CD lesions and assess CD activity.\u003c/p\u003e \u003cp\u003eIn this study, we aimed to establish and validate nomograms to predict different CD activity statuses by combining CTE-based radiomics and morphological features.\u003c/p\u003e"},{"header":"Materials and methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003ePatient selection\u003c/h2\u003e \u003cp\u003e This retrospective study was approved by the institutional review board of our hospital (approval number: 2013KY034), and written informed consent from each participant was waived.\u003c/p\u003e \u003cp\u003eWe searched the radiology reports for the term Crohn\u0026rsquo;s disease on CTE scans obtained between January 2017 and June 2023. The inclusion criteria were as follows: (1) established CD diagnosis by conventional clinical, endoscopic and histologic criteria, (2) undergo ileocolonoscopy within two days after CTE, and (3) had not received any new medication between the 2 examinations. The exclusion criteria were as follows: (1) inadequate imaging quality which was unable to segment, for example breathing artifact, (2) not readily identifiable intestinal contour on CTE due to severe perienteric effusion, intestinal adhesion or intestinal peristalsis. Enrolled segments were randomly divided into a training cohort and a testing cohort at a ratio of 7:3. The study flow diagram is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003cem\u003eReference Standard for intestinal inflammatory activity\u003c/em\u003e \u003c/p\u003e \u003cp\u003eThe ileocolonoscopic procedure and evaluation were performed by two gastroenterologists (with 15- and 20-years work experience) without knowledge of CTE results. The ileocolon was divided into 5 segments on ileocolonoscopy and CTE including terminal ileum (the last 20 cm of small bowel proximal to the ileocecal valve), right colon (ileocecal valve, cecum and ascending colon), transverse colon, left colon (descending and sigmoid colon), and rectum[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]. The gastroenterologists scored the ileocolonoscopy findings in consensus for each segment according to SES-CD during endoscopy. The bowel segments were classified by SES-CD as inactive (0\u0026ndash;2), mild (3\u0026ndash;6), or moderate-severe (\u0026ge;\u0026thinsp;7)[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]. Discrepancies between reviewers were resolved by consensus reading. The final results were used for further statistical analyses.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003eComputed tomography enterography examination and CT morphological features by radiologists\u003c/h2\u003e \u003cdiv id=\"Sec5\" class=\"Section3\"\u003e \u003ch2\u003eCTE imaging technique\u003c/h2\u003e \u003cp\u003eCTE examinations were performed on a dual-source dual-energy CT scanner (Somatom Definition, Siemens Healthineers, Forchheim GER) with tube current modulation (Care-Dose 4D), tube voltages of 100 kVp (A tube) and Sn-filtered 140 kVp (B tube). All subjects were scanned in supine position. Fasting for solid food with a time interval of 8 hours prior to CTE scan was requested for each subject. Also, all subjects needed to drink 300 mL of mannitol (2.5%) every 15 min until a total of 1.5 L had been consumed within 60 minutes. Intravenous contrast dosing (Ultravist, Bayer, GA) delivered at 3 mL/s was utilized. Images at axial direction with slice thickness of 1 mm from the diaphragm to pubic symphysis were acquired and sent to the picture archiving and communication system (PACS) (Carestream Health, Inc, Rochester, US). CTE acquisition consisted of the venous phase at 60 seconds after contrast administration.\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003eCTE morphological analysis and model construction\u003c/h2\u003e \u003cp\u003eThere are five qualitative morphological features obtained by evaluating CTE: (1) bowel wall thickness graded with a score of 0 (\u0026lt;\u0026thinsp;3mm), 1 (mild, 3-5mm), 2 (moderate, 5-10mm), or 3 (severe, \u0026gt;\u0026thinsp;10mm), (2) lumen stenosis[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e] characterized as \u0026ge;\u0026thinsp;50% reduction in luminal diameter in comparison with that of the adjacent loop, together with unequivocal upstream dilation of the same loop (\u0026gt;\u0026thinsp;3 cm in caliber) and graded with a score of 0 (none), 1 (present), (3) mural enhancement[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e], 0 (homogenous), 1 (asymmetric), 2 (stratified), (4) comb sign defined by CT features of segmental dilatation of the vasa recta involving a bowel loop[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e], 0 (none), 1 (present), (5) fat infiltration defined as locally and increased inhomogeneous attenuation in the perienteric fat, compared with the perienteric fat adjacent to non-inflamed bowel loops[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e], 0 (none), 1 (present). A radiologist with 20 years of experience in abdominal CT, blinded to the endoscopic results, evaluated these five features and scored.\u003c/p\u003e \u003cp\u003eThe above five morphological features were used as the input of the multiple logistic regression analysis, and then a morphological model (M-score) was built.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003eBowel segmentation and radiomics features extraction\u003c/h2\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e shows the flow chart of our study. CTE venous phase images were used for lesion extraction. The volumes of interest (VOIs) were drawn along the lesion contour on each transverse section until the full lesion was captured excluding the intestinal lumen. A radiologist (reader 1, with 5 years of diagnostic experience in abdominal imaging) manually delineated three-dimensional (3D) VOIs by using an open-source medical imaging software (3D-Slicer, version 5.5.0, \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), and was blinded to the results of ileocolonoscopy.\u003c/p\u003e \u003cp\u003eTo standardize the voxel spacing across the cohort, all CT voxels were resampled to 1\u0026times;1\u0026times;1mm\u003csup\u003e3\u003c/sup\u003e before feature extraction. A fixed bin width of 25 Hounfield units (HU) was used during the calculation of texture features. A total of 851 radiomics features were extracted, including shape, first-order, second-order and wavelet-filter features.\u003c/p\u003e \u003cp\u003eTo evaluate the inter-/intra-observer reproducibility of the extracted features, 30 segments randomly selected from the training cohort were segmented twice over a 4-weeks interval by another radiologist (reader 2, with 5 years\u0026rsquo; working experience in abdominal imaging) with the same procedures. The intraclass correlation coefficients (ICCs) were calculated using a two-way random effects model to determine inter-/intra-observer reliabilities. Only the features with ICC more than 0.75 were included in further analysis.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eRadiomics model and morphological radiomics nomogram construction\u003c/h2\u003e \u003cp\u003eFirstly, pair-wise correlation analysis was performed to remove redundant radiomics features, by using the \u0026ldquo;findCorrelation\u0026rdquo; function in R package \u0026ldquo;caret\u0026rdquo; with the absolute correlation cutoff set at 0.9. Then, least absolute shrinkage and selection (LASSO) logistic regression was adopted to select the most predictive radiomics features from the training cohort[\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. The penalty parameter lambda determining feature selection was chosen by 10-fold cross-validation. Next, a radiomics signature score (Rad-score) was constructed with a linear combination of selected features weighted by their coefficients. A nomogram by combining the M-score and the Rad-score was constructed.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003eStatistical analysis\u003c/h2\u003e \u003cp\u003eAll categorical variables were summarized as number (percent) and compared using the Fisher\u0026rsquo;s exact test. The diagnostic performance of the morphological model, the radiomics model, and the nomogram was evaluated based on the area under the receiver operating characteristic (ROC) curve in both the training cohort and testing cohort. Delong method was employed to test the differences of the area under the ROC curves (AUC) among three models. Calibration curves were applied to evaluate the performance of the nomogram. Decision curve analysis (DCA) was conducted to evaluate the clinical efficacy of the nomogram by quantifying the net benefit at different threshold probabilities across the training and testing cohorts. Statistical analysis was performed using R software (version 4.3.1, \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e\u003ca href=\"https://www.slicer.org\" target=\"_blank\"\u003ewww.r-project.org\u003c/a\u003e\u003c/span\u003e\u003cspan address=\"http://www.r-project.org\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e) with packages \u003cem\u003ecaret\u003c/em\u003e, \u003cem\u003eglmnet\u003c/em\u003e, \u003cem\u003epROC\u003c/em\u003e, \u003cem\u003ereportROC\u003c/em\u003e, \u003cem\u003erms\u003c/em\u003e, \u003cem\u003ermda\u003c/em\u003e and \u003cem\u003esurvival\u003c/em\u003e. A two-sided \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05 was considered significant.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\n\u003ch2\u003ePatient characteristics\u003c/h2\u003e\n\u003cp\u003eA total of 54 patients with 237 bowel segments were included in the study. According to the SES-CD, 237 ileocolonic segments with CD lesions were identified as: inactive (n\u0026thinsp;=\u0026thinsp;158), mild (n\u0026thinsp;=\u0026thinsp;47), and moderate to severe (n\u0026thinsp;=\u0026thinsp;32). The stratified distributions of SES-CD scores were compared between the training and test cohorts (Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e). 166 segments in training cohort and 71 segments in testing cohort were applied for differentiating active from remissive disease, while 55 in training cohort and 24 in testing cohort were used for distinguishing mild from moderate-to-severe active disease.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003ctable id=\"Tab1\" border=\"1\"\u003e\u003ccaption\u003e\n\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\n\u003cdiv class=\"CaptionContent\"\u003e\n\u003cp\u003eComparison of clinical data between training and testing cohort\u003c/p\u003e\n\u003c/div\u003e\n\u003c/caption\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth rowspan=\"2\" align=\"left\"\u003e\u0026nbsp;\u003c/th\u003e\n\u003cth colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003eActive vs. inactive\u003c/p\u003e\n\u003c/th\u003e\n\u003cth colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003eMild vs. moderate-to-severe\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eTraining cohort\u003c/p\u003e\n\u003cp\u003en\u0026thinsp;=\u0026thinsp;166\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eTesting cohort\u003c/p\u003e\n\u003cp\u003en\u0026thinsp;=\u0026thinsp;71\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eTraining cohort\u003c/p\u003e\n\u003cp\u003en\u0026thinsp;=\u0026thinsp;55\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eTesting cohort\u003c/p\u003e\n\u003cp\u003en\u0026thinsp;=\u0026thinsp;24\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eSegments with SES-CD score available\u003c/strong\u003e, n (%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.988\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.689\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eterminal ileum\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e25 (15.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e12 (16.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e11 (20.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e6 (25.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eright colon\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e33 (19.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e14 (19.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e17 (30.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e8 (33.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003etransverse colon\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e32 (19.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e15 (21.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e7 (12.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e2 (8.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eleft colon\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e38 (22.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e15 (21.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e13 (23.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e3 (12.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003erectum\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e38 (22.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e15 (21.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e7 (12.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e5 (20.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eMorphology features\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd colspan=\"4\" align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003ebowel wall thickness, n (%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.462\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.566\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e62 (37.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e25 (35.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1 (1.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1 (4.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e48 (28.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e21 (29.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e7 (12.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e4 (16.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e2\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e30 (18.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e18 (25.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e22 (40.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e12 (50.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e3\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e26 (15.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e7 (9.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e25 (45.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e7 (29.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003elumen stenosis\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.289\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.941\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e133 (80.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e61 (85.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e28 (50.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e12 (50.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e33 (19.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e10 (14.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e27 (49.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e12 (50.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003emural enhancement\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.738\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.632\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e114 (68.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e50 (70.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e16 (29.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e9 (37.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e51 (30.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e20 (28.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e38 (69.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e15 (62.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e2\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1 (0.06)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1 (1.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1 (1.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0 (0)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003ecomb sign\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.030\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.975\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e124 (74.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e53 (74.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e25 (45.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e11 (45.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e42 (25.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e18 (25.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e30 (54.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e13 (54.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003efat infiltration\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.267\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.128\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e102 (61.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e49 (69.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e8 (14.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e7 (29.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e64 (38.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e22 (31.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e47 (85.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e17 (70.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eSES-CD\u003c/strong\u003e, n (%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.160\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.719\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eInactive (0\u0026ndash;2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e106 (63.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e52 (73.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eMild (3\u0026ndash;6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e60 (36.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e19 (26.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e32 (58.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e15 (62.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eModerate-to-severe (\u0026ge;\u0026thinsp;7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e23 (41.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e9 (37.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003ctfoot\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"5\"\u003eNote: SES-CD\u0026thinsp;=\u0026thinsp;simple endoscopic score for Crohn\u0026rsquo;s disease\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tfoot\u003e\n\u003c/table\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\n\u003ch2\u003eDevelopment and validation of models and nomogram for discriminating inactive from active bowel segments\u003c/h2\u003e\n\u003cdiv id=\"Sec13\" class=\"Section3\"\u003e\n\u003ch2\u003eMorphological features selection and M-score1 development\u003c/h2\u003e\n\u003cp\u003eBowel stenosis and comb sign were significantly related to the activity of segments by using multivariate analysis (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). Both morphological features were thus included to build M-score1: -2.197\u0026thinsp;+\u0026thinsp;3.960\u0026times;stenosis\u0026thinsp;+\u0026thinsp;3.407\u0026times;comb sign. The AUC was 0.870 (95% CI: 0.810\u0026ndash;0.930) in the training cohort and 0.747 (95% CI: 0.638\u0026ndash;0.855) in the testing cohort (Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e).\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003cdiv class=\"colspec\" align=\"char\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003ctable id=\"Tab2\" border=\"1\"\u003e\u003ccaption\u003e\n\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\n\u003cdiv class=\"CaptionContent\"\u003e\n\u003cp\u003ePerformance of models for differentiating active from inactive disease\u003c/p\u003e\n\u003c/div\u003e\n\u003c/caption\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003emodels\u003c/p\u003e\n\u003c/th\u003e\n\u003cth colspan=\"4\" align=\"left\"\u003e\n\u003cp\u003eTraining cohort\u003c/p\u003e\n\u003c/th\u003e\n\u003cth colspan=\"4\" align=\"left\"\u003e\n\u003cp\u003eTesting cohort\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eAUC (95%CI)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eAccuracy\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eSensitivity\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eSpecificity\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eAUC (95%CI)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eAccuracy\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eSensitivity\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eSpecificity\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eM-score1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.870(0.810\u0026ndash;0.930)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.892\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.774\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.947\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.747(0.638\u0026ndash;0.855)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.775\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.577\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.889\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eRad-score1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.857(0.797\u0026ndash;0.918)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.771\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.830\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.743\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.828(0.720\u0026ndash;0.937)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.789\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.769\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.800\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eCombine-model1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.944(0.905\u0026ndash;0.982)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.916\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.868\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.938\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.834(0.728\u0026ndash;0.940)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.803\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.692\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.867\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec14\" class=\"Section2\"\u003e\n\u003ch2\u003eRadiomics features selection and Rad-score1 development\u003c/h2\u003e\n\u003cp\u003eThere were 851 radiomics features extracted from the venous CT images per segment. A total of 830 features with inter-/intra-observer ICCs of \u0026ge;\u0026thinsp;0.75 were retained as factors for developing the radiomics model. Further reduction of pair-wise correlations led to 494 independent features. After LASSO logistic regression from the training cohort (Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e), three radiomics features with non-zero coefficients were selected to distinguish inactive from active segments. The Rad-score1 (inactive vs. active) was calculated by the following formula: -0.8875\u0026thinsp;+\u0026thinsp;0.9790\u0026times;wavelet-LLL-firstorder-Energy\u0026thinsp;+\u0026thinsp;0.6177\u0026times;wavelet-HLL-glszm-SizeZoneNonUniformity\u0026thinsp;+\u0026thinsp;0.6542\u0026times;original-firstorder-Median. The AUC was 0.857 (95% CI: 0.797\u0026ndash;0.918) in the training cohort and 0.828 (95% CI: 0.720\u0026ndash;0.917) in the testing cohort (Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e) for differentiating active from inactive bowel segments.\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eAlthough M-score1 performed better than Rad-score1 in differentiating activities in training cohort, Delong test showed that there was no significant difference between the two models (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05).\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec15\" class=\"Section2\"\u003e\n\u003ch2\u003eDevelopment and validation of combine-model1 and nomogram\u003c/h2\u003e\n\u003cp\u003eFinally, we combined the M-score1 and Rad-scor1 to construct the combine-model1: 0.4841\u0026thinsp;+\u0026thinsp;0.7422\u0026times;M-score1\u0026thinsp;+\u0026thinsp;0.8732\u0026times;Rad-score1. The prediction performance of combine-model1 achieved the optimal efficacy in bowel segments with an AUC, accuracy, sensibility and specificity of 0.834 (95% CI: 0.728\u0026ndash;0.940), 0.803, 0.692, 0.867 in the testing cohort respectively (Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e). Either in training cohort or in testing cohort, the AUC of combine-model1 performed better than M-score1 (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05) (Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e). A nomogram based on the combine-model1 was built to visualize the results (Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e). The calibration curve of the nomogram revealed good predictive accuracy between the actual probability and predicted probability. The DCA demonstrated a highly positive net benefit of the nomogram within a certain range (Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eDevelopment and validation of models and nomogram for discriminating mild active from moderate-to-severe active bowel segments\u003c/em\u003e\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec16\" class=\"Section2\"\u003e\n\u003ch2\u003eConstruction of three models\u003c/h2\u003e\n\u003cp\u003eWe used the same modelling process aforementioned for distinguishing mild active from moderate-to-severe active bowel segments. The M-score2 (mild vs. moderate-to-severe) was calculated as following: -1.1787\u0026thinsp;+\u0026thinsp;1.0916\u0026times;comb sign. There was one radiomics feature included in Rad-score 2 after LASSO logistic regression from the training cohort: -1.2670\u0026thinsp;+\u0026thinsp;1.3048\u0026times;wavelet-HLL-glszm-SizeZoneNonUniformity. Then, the combine-model2 was constructed with the linear combination of the M-score2 and the Rad-model2 as following: -1.9143\u0026thinsp;+\u0026thinsp;1.0340\u0026times;M-score2\u0026thinsp;+\u0026thinsp;1.3627\u0026times;Rad-score2, and the nomogram for differentiating mild activity from moderate-to-severe activity was plotted based on the combine-model2 (Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e).\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec17\" class=\"Section2\"\u003e\n\u003ch2\u003ePerformance comparison\u003c/h2\u003e\n\u003cp\u003eTable\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e summarized the AUC, accuracy, sensibility and specificity. The combine-model2 showed a favorable performance with AUC of 0.817 (95% CI: 0.676\u0026ndash;0.958) and 0.781 (95% CI: 0.611\u0026ndash;0.951) in the training and testing cohort, respectively. Moreover, Delong test revealed that the difference of predictive performance was statistically significant between combine-model2 and M-model2 or Rad-score2 (both, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05, Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e).\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003ctable id=\"Tab4\" border=\"1\"\u003e\u003ccaption\u003e\n\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\n\u003cdiv class=\"CaptionContent\"\u003e\n\u003cp\u003ePerformance of models for distinguishing mild from moderate-to-severe activity\u003c/p\u003e\n\u003c/div\u003e\n\u003c/caption\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003emodels\u003c/p\u003e\n\u003c/th\u003e\n\u003cth colspan=\"4\" align=\"left\"\u003e\n\u003cp\u003eTraining cohort\u003c/p\u003e\n\u003c/th\u003e\n\u003cth colspan=\"4\" align=\"left\"\u003e\n\u003cp\u003eTesting cohort\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eAUC (95%CI)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eAccuracy\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eSensitivity\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eSpecificity\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eAUC (95%CI)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eAccuracy\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eSensitivity\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eSpecificity\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eM-score2\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.701(0.554\u0026ndash;0.847)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.692\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.765\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.636\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.627(0.474\u0026ndash;0.780)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.600\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.733\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.520\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eRad-score2\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.755(0.590\u0026ndash;0.921)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.795\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.588\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.955\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.757(0.585\u0026ndash;0.930)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.825\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.533\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1.000\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eCombine-model2\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.817(0.676\u0026ndash;0.958)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.795\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.706\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.864\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.781(0.611\u0026ndash;0.951)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.825\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.600\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.960\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003cdiv class=\"colspec\" align=\"char\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003ctable id=\"Tab3\" border=\"1\"\u003e\u003ccaption\u003e\n\u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\n\u003cdiv class=\"CaptionContent\"\u003e\n\u003cp\u003eThe comparison among the three different models\u003c/p\u003e\n\u003c/div\u003e\n\u003c/caption\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth rowspan=\"2\" align=\"left\"\u003e\u0026nbsp;\u003c/th\u003e\n\u003cth colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003eActive vs. inactive\u003c/p\u003e\n\u003c/th\u003e\n\u003cth colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003eMild vs. moderate-to-severe\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eTraining cohort\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eTesting cohort\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eTraining cohort\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eTesting cohort\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eM-score versus combine\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.002\u003csup\u003e※\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.028\u003csup\u003e※\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.040\u003csup\u003e※\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.033\u003csup\u003e※\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eRad versus combine\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.001\u003csup\u003e※\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.841\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.042\u003csup\u003e※\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.055\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eRad versus M-score\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.755\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.171\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.631\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.647\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003ctfoot\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"5\"\u003e\u003csup\u003e※\u003c/sup\u003eDelong test\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tfoot\u003e\n\u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec18\" class=\"Section2\"\u003e\n\u003ch2\u003eCalibration and clinical utility of models\u003c/h2\u003e\n\u003cp\u003eCalibration plots and DCA of three models in the testing cohort for distinguishing mild activity from moderate-to-severe activity were shown in Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e.\u003c/p\u003e\n\u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eWe used CTE images to develop and validate a radiomics-based nomogram for identifying the activity of CD lesions. Our study demonstrated that in both the training and testing cohorts, the nomogram combined by imaging morphological features and radiomics features could accurately distinguish the activity severity and act better than either single radiomics model or imaging morphological model. Furthermore, DCA confirmed its clinical effect.\u003c/p\u003e \u003cp\u003eCD has a variable clinical course, with alternating periods of disease activity and remission[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]. Hence, it is essential to accurately and timely distinguish the activity of CD to help clinicians choose the appropriate treatments. The SES-CD score is the most reliable and easy-to-use endoscopic scoring tool for CD[\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. However, failure to intubate the ileum is a major challenge when using the SES-CD as a primary outcome in clinical trials[\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. CTE is an imaging method that can evaluate not only the whole gastrointestinal tract involvement but also the extra-intestinal complications noninvasively.\u003c/p\u003e \u003cp\u003eOur study researched the imaging morphological features. Multi-logistic analysis indicated that stenosis and comb sign were significant correlated. Stenosis is the most often seen in patients with active inflammation, although fibrosis and inflammation are often both present[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]. Comb sign results from increased blood supply and drainage of a small bowel segment[\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. Wu et al [\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]reported that quantitative comb sign results are robust in predicting CD activity with the accuracy rate of 80% at venous stage. A simplified CT enterography index of activity combined with mural thickness, mural stratification and comb sign revealed high and significant correlation with CD activity[\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e], with the AUC of 0.901, where our combined model is better than this (AUC\u0026thinsp;=\u0026thinsp;0.944). In addition, Lopes et al[\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e] found that endoscopic remission at 1-year follow up significantly correlated with improvement in mural hyperenhancement, mesenteric fat densification, comb sign, and strictures in CTE. Those results also proved our morphological models were robust.\u003c/p\u003e \u003cp\u003eWe included 851 radiomics features. Based on the results of multivariate analysis, we built the radiomics model, including: original-firstorder-Median, wavelet-LLL-firstorder-Energy, wavelet-HLL-glszm-SizeZoneNonUniformity. \u0026ldquo;Median\u0026rdquo; represents the median gray level intensity within the ROI. Previous studies confirmed that the mean normalized iodine density is highly sensitive and specific for endoscopic active inflammation in CD patients[\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e, \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e]. It suggests that the gray level intensity is related to the activity of bowel segments, which is consistent with our results. The two other features were Wavelet-filter features, Prior researches have concluded that it may reveal the heterogeneity of ROI and suggested a poor prognosis[\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. Ding et al [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]also reported that a MR radiomics model included five Wavelet-filter features can evaluate the inflammatory severity and was comparable to MaRIA evaluated by a senior radiologist. As radiomics researches in many other diseases[\u003cspan additionalcitationids=\"CR31\" citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e], we constructed the nomogram by combining both morphological and radiomics features, which achieved the best predictive ability both in training cohorts and testing cohorts.\u003c/p\u003e \u003cp\u003eTo the best of our knowledge, few studies have been conducted to develop a radiomics model based on CTE imaging for assessing the disease activity. We also develop different models to discriminate not only active from inactive but also mild active from moderate-to-severe active diseases.\u003c/p\u003e \u003cp\u003eIt should be recognized that our study has several limitations. Firstly, this study was retrospective in nature, which needs further evaluation to validate these results. Secondly, the number of patients was small. We need to test multi-center and more patients to validate the accuracy of these models in future. Finally, we employed 3D segmentation technology manually in the colon and ileocecal regions, which elapsed more time than those of 2D segmentation. It is essential to develop a high-throughput method for automatic extraction of a large number of quantitative imaging features from medical images in the future.\u003c/p\u003e \u003cp\u003eIn conclusion, the combined model based on CTE radiomics and morphological features was built for the discrimination of mucosal activity measured by SES-CD. The nomogram is of satisfactory ability in clinical utility in differentiating different levels of activities in patients with CD.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cdiv class=\"DefinitionList\"\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e3D\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eThree-dimensional\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eAUC\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eArea under the ROC curve\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eCD\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eCrohn\u0026rsquo;s Disease\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eCTE\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eComputed tomography enterography\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eDCA\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eDecision curve analysis\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eROC\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eReceiver operating characteristic\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eVOI\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eVolume of interest\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eSES-CD\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eSimple endoscopic score for Crohn\u0026rsquo;s disease\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003c/div\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNo.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors\u0026rsquo; contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll authors played an important role in this research. Specific contributions are listed as follows: \u003cstrong\u003eYuping Ma\u003c/strong\u003e: Data curation, Software, Writing-original draft. \u003cstrong\u003eLuanxin Zhu\u003c/strong\u003e: Data curation, Software, Writing-original draft. \u003cstrong\u003eBota Cui\u003c/strong\u003e: Data curation. \u003cstrong\u003eFaming Zhang\u003c/strong\u003e: Data curation. Writing-review \u0026amp; editing. \u003cstrong\u003eHaige Li\u003c/strong\u003e: Validation, Visualization. \u003cstrong\u003eJianguo Zhu\u003c/strong\u003e: Conceptualization, Formal analysis, Methodology, Resources, Project administration, Supervision, Writing-review \u0026amp; editing. All authors reviewed the analyses and drafts of this manuscript and approved its final version.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors state that this work has not received any funding.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAvailability of data and materials\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll datasets and materials used and/or analyzed during the current study are available from the corresponding authors on any reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe studies involving human participants were reviewed and approved by the Institutional Review Board and Ethics Committee of the Second Affiliated Hospital of Nanjing Medical University (ethical approval number:\u0026nbsp;2013KY034). Due\u0026nbsp;to\u0026nbsp;the\u0026nbsp;retrospective\u0026nbsp;nature\u0026nbsp;of\u0026nbsp;the current study, the Ethics Committee of the Second Affiliated Hospital of Nanjing Medical University\u0026nbsp;waived the requirement for written informed consent from each participant. We confirm that all methods were carried out in accordance with relevant guidelines and regulations.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll authors have no conflicts of interest to declare.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eNg SC, Shi HY, Hamidi N, Underwood FE, Tang W, Benchimol EI, Panaccione R, Ghosh S, Wu JC, Chan FK. Worldwide incidence and prevalence of inflammatory bowel disease in the 21st century: a systematic review of population-based studies. Lancet. 2017;390(10114):2769\u0026ndash;78.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMaaser C, Sturm A, Vavricka SR, Kucharzik T, Fiorino G, Annese V, Calabrese E, Baumgart DC, Bettenworth D, Borralho Nunes P. ECCO-ESGAR Guideline for Diagnostic Assessment in IBD Part 1: Initial diagnosis, monitoring of known IBD, detection of complications. J Crohn's Colitis. 2019;13(2):144\u0026ndash;K164.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSturm A, Maaser C, Calabrese E, Annese V, Fiorino G, Kucharzik T, Vavricka SR, Verstockt B, van Rheenen P, Tolan D. ECCO-ESGAR Guideline for Diagnostic Assessment in IBD Part 2: IBD scores and general principles and technical aspects. J Crohn's Colitis. 2019;13(3):273\u0026ndash;84.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMao L, Li Y, Cui B, Lu L, Dou W, Pylypenko D, Zhu J, Li H. Multiparametric MRI for Staging of Bowel Inflammatory Activity in Crohn's Disease with MUSE-IVIM and DCE-MRI: A Preliminary Study. \u003cem\u003eAcademic Radiology\u003c/em\u003e 2023.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhu J, Zhang F, Zhou J, Li H. Assessment of therapeutic response in Crohn's disease using quantitative dynamic contrast enhanced MRI (DCE-MRI) parameters: A preliminary study. Medicine 2017, 96(32).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhu J, Zhang F, Luan Y, Cao P, Liu F, He W, Wang D. Can dynamic contrast-enhanced MRI (DCE-MRI) and diffusion-weighted MRI (DW-MRI) evaluate inflammation disease: a preliminary study of Crohn's disease. Medicine 2016, 95(14).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFernandes SR, Rodrigues RV, Bernardo S, Cortez-Pinto J, Rosa I, da Silva JP, Gon\u0026ccedil;alves AR, Valente A, Baldaia C, Santos PM. Transmural healing is associated with improved long-term outcomes of patients with Crohn's disease. Inflamm Bowel Dis. 2017;23(8):1403\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChavoshi M, Mirshahvalad SA, Kasaeian A, Djalalinia S, Kolahdoozan S, Radmard AR. Diagnostic accuracy of magnetic resonance enterography in the evaluation of colonic abnormalities in Crohn's disease: a systematic review and meta-analysis. Acad Radiol. 2021;28:S192\u0026ndash;202.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCipriano LE, Levesque BG, Zaric GS, Loftus EV Jr, Sandborn WJ. Cost-effectiveness of imaging strategies to reduce radiation-induced cancer risk in Crohn's disease. Inflamm Bowel Dis. 2012;18(7):1240\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ede Sousa HT, Brito J, Magro F. New cross-sectional imaging in IBD. Curr Opin Gastroenterol. 2018;34(4):194\u0026ndash;207.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGao Y, Zhang B, Zhao D, Li S, Rong C, Sun M, Wu X. Automatic segmentation and radiomics for identification and activity assessment of CTE lesions in Crohn\u0026rsquo;s disease. Inflamm Bowel Dis 2023:izad285.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, Van Stiphout RG, Granton P, Zegers CM, Gillies R, Boellard R, Dekker A. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer. 2012;48(4):441\u0026ndash;6.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDing H, Li J, Jiang K, Gao C, Lu L, Zhang H, Chen H, Gao X, Zhou K, Sun Z. Assessing the inflammatory severity of the terminal ileum in Crohn disease using radiomics based on MRI. BMC Med Imaging. 2022;22(1):118.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiu RX, Li H, Towbin AJ, Ata NA, Smith EA, Tkach JA, Denson LA, He L, Dillman JR. Machine learning diagnosis of small-bowel Crohn disease using T2-weighted MRI radiomic and clinical data. Am J Roentgenol. 2024;222(1):e2329812.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMagalh\u0026atilde;es FC, Lima EM, Carpentieri-Primo P, Barreto MM, Rodrigues RS, Parente DB. Crohn\u0026rsquo;s disease: review and standardization of nomenclature. Radiologia Brasileira. 2023;56:95\u0026ndash;101.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhu C, Hu J, Wang X, Li C, Gao Y, Li J, Ge Y, Wu X. A novel clinical radiomics nomogram at baseline to predict mucosal healing in Crohn\u0026rsquo;s disease patients treated with infliximab. Eur Radiol. 2022;32(10):6628\u0026ndash;36.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi X, Zhang N, Hu C, Lin Y, Li J, Li Z, Cui E, Shi L, Zhuang X, Li J. CT-based radiomics signature of visceral adipose tissue for prediction of disease progression in patients with Crohn's disease: A multicentre cohort study. EClinicalMedicine 2023, 56.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRuiqing L, Jing Y, Shunli L, Jia K, Zhibo W, Hongping Z, Keyu R, Xiaoming Z, Zhiming W, Weiming Z. A Novel Radiomics Model Integrating Luminal and Mesenteric Features to Predict Mucosal Activity and Surgery Risk in Crohn's Disease Patients: A Multicenter Study. \u003cem\u003eAcademic Radiology\u003c/em\u003e 2023.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang R-n, Huang S-y, Liu R-y, Meng J-x, Zhou J, Chen Z, Fang J-y, Mao R, Li Z-p. Sun C-h: Preoperative computed tomography enterography-based radiomics signature: A potential predictor of postoperative anastomotic recurrence in patients with Crohn\u0026rsquo;s disease. Eur J Radiol. 2023;162:110766.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTibshirani R. The lasso method for variable selection in the Cox model. Stat Med. 1997;16(4):385\u0026ndash;95.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDaperno M, D'Haens G, Van Assche G, Baert F, Bulois P, Maunoury V, Sostegni R, Rocca R, Pera A, Gevers A. Development and validation of a new, simplified endoscopic activity score for Crohn's disease: the SES-CD. Gastrointest Endosc. 2004;60(4):505\u0026ndash;12.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMeral M, Bengi G, Kayahan H, Akarsu M, Soyt\u0026uuml;rk M, Topalak \u0026Ouml;, Akpinar H, Sagol \u0026Ouml;. Is ileocecal valve intubation essential for routine colonoscopic examination? Eur J Gastroenterol Hepatol. 2018;30(4):432\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMeyers M, McGuire P. Spiral CT demonstration of hypervascularity in Crohn disease:vascular jejunization of the ileum or the comb sign. Abdom Imaging. 1995;20:327\u0026ndash;32.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWu Y-W, Tao X-F, Tang Y-H, Hao N-X, Miao F. Quantitative measures of comb sign in Crohn\u0026rsquo;s disease: correlation with disease activity and laboratory indications. Abdom Imaging. 2012;37:350\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTong J, Feng Q, Zhang C, Xu X, Ran Z. CT enterography for evaluation of disease activity in patients with ileocolonic Crohn's disease. BMC Gastroenterol. 2022;22(1):1\u0026ndash;10.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLopes S, Andrade P, Afonso J, Cunha R, Rodrigues-Pinto E, Ramos I, Macedo G, Magro F. Monitoring Crohn\u0026rsquo;s disease activity: endoscopy, fecal markers and computed tomography enterography. Therapeutic Adv Gastroenterol. 2018;11:1756284818769075.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDane B, Kernizan A, O\u0026rsquo;Donnell T, Petrocelli R, Rabbenou W, Bhattacharya S, Chang S, Megibow A. Crohn\u0026rsquo;s disease active inflammation assessment with iodine density from dual-energy CT enterography: comparison with endoscopy and conventional interpretation. Abdom Radiol. 2022;47(10):3406\u0026ndash;13.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDane B, Sarkar S, Nazarian M, Galitzer H, O\u0026rsquo;Donnell T, Remzi F, Chang S, Megibow A. Crohn disease active inflammation assessment with iodine density from dual-energy CT enterography: comparison with histopathologic analysis. Radiology. 2021;301(1):144\u0026ndash;51.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDepeursinge A, Foncubierta-Rodriguez A, Van De Ville D, M\u0026uuml;ller H. Three-dimensional solid texture analysis in biomedical imaging: review and opportunities. Med Image Anal. 2014;18(1):176\u0026ndash;96.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBao D, Zhao Y, Li L, Lin M, Zhu Z, Yuan M, Zhong H, Xu H, Zhao X, Luo D. A MRI-based radiomics model predicting radiation-induced temporal lobe injury in nasopharyngeal carcinoma. Eur Radiol. 2022;32(10):6910\u0026ndash;21.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang Y, Liu L, Zhang K, Su R, Jia H, Qian L, Dong J. Nomograms Combining Clinical and Imaging Parameters to Predict Recurrence and Disease-free Survival After Concurrent Chemoradiotherapy in Patients With Locally Advanced Cervical Cancer. Acad Radiol. 2023;30(3):499\u0026ndash;508.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZheng R, Zhang X, Liu B, Zhang Y, Shen H, Xie X, Li S, Huang G. Comparison of non-radiomics imaging features and radiomics models based on contrast-enhanced ultrasound and Gd-EOB-DTPA-enhanced MRI for predicting microvascular invasion in hepatocellular carcinoma within 5 cm. Eur Radiol 2023:1\u0026ndash;11.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":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":"Crohn’s disease, computed tomography enterography, radiomics, inflammatory activity","lastPublishedDoi":"10.21203/rs.3.rs-4465032/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4465032/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cem\u003e\u003cstrong\u003eObjectives\u003c/strong\u003e\u003c/em\u003eTo develop and validate nomograms, derived from morphological features, and computed tomography enterography (CTE) -based radiomics, for evaluating inflammatory activity in patients with ileocolonic Crohn’s disease (CD).\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e\u003cstrong\u003eMethods\u003c/strong\u003e\u003c/em\u003eA total of 54 CD patients (237 bowel segments) with clinically confirmed CD were retrospectively reviewed. The simple endoscopic score for Crohn’s disease (SES-CD) was used as a reference standard to quantify the degree of mucosal inflammation and evaluate the disease severity. Radiomics and image morphological features were extracted in the training cohort, and then a morphological model (M-score) and a radiomics model (Rad-score) were built respectively. A combined nomogram was further generated by incorporating M-score and Rad-score. Predictive values of each model were assessed using receiver operating characteristic (ROC) curve analysis. Calibration curve and decision curve analysis (DCA) were employed to evaluate the accuracy and clinical applicability of the nomogram in the testing cohort.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e\u003cstrong\u003eResults\u003c/strong\u003e\u003c/em\u003eThe area under the ROC curve (AUC) of the nomogram, based on the stenosis, comb sign and Rad-score, was 0.834 [95% confidence interval (CI): 0.728–0.940] for distinguishing active from remissive disease. Moreover, the nomogram built using comb sign and Rad-score also achieved satisfied AUC [0.781 (95%CI: 0.611–0.951)] in distinguishing mild activity from moderate-to-severe activity. The calibration curve and DCA confirmed the accuracy and clinical utility of both nomograms.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e\u003cstrong\u003eConclusions \u003c/strong\u003e\u003c/em\u003eNomograms constructed by combining CTE-based radiomics and morphological features might be a useful supporting tool for grading inflammatory activity, aiding clinical decision-making for the management of CD.\u003c/p\u003e","manuscriptTitle":"Computed Tomography Enterography-Based Radiomics Nomograms to Predict Inflammatory Activity for Ileocolonic Crohn’s Disease","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-12 19:13:57","doi":"10.21203/rs.3.rs-4465032/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-12-12T07:51:15+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-23T03:45:15+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"180587170332839588641944006782516036976","date":"2024-11-18T09:17:28+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-17T22:40:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"138543849962157723782299606925959070408","date":"2024-10-28T09:43:22+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-07-23T09:19:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"229013885384947962993683473297961496080","date":"2024-07-21T20:15:51+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-07-11T08:19:53+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-05-28T08:42:42+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-05-28T08:40:37+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-05-28T08:40:36+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Imaging","date":"2024-05-23T07:32:52+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":"cbcbf4d4-7919-4254-bce2-8eea7c9d245d","owner":[],"postedDate":"June 12th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-02-03T16:01:39+00:00","versionOfRecord":{"articleIdentity":"rs-4465032","link":"https://doi.org/10.1186/s12880-025-01560-0","journal":{"identity":"bmc-medical-imaging","isVorOnly":false,"title":"BMC Medical Imaging"},"publishedOn":"2025-01-27 15:57:22","publishedOnDateReadable":"January 27th, 2025"},"versionCreatedAt":"2024-06-12 19:13:57","video":"","vorDoi":"10.1186/s12880-025-01560-0","vorDoiUrl":"https://doi.org/10.1186/s12880-025-01560-0","workflowStages":[]},"version":"v1","identity":"rs-4465032","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4465032","identity":"rs-4465032","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}