Bowel wall MRI T1 relaxation estimates for assessment of intestinal inflammation in pediatric Crohn's disease

Machine Learning Diagnosis of Small-Bowel Crohn Disease Using T2-Weighted MRI Radiomic and Clinical Data

BACKGROUND. Radiologists have variable diagnostic performance and considerable interreader variability when interpreting MR enterography (MRE) examinations for suspected Crohn disease (CD). OBJECTIVE. The purposes of this study were to develop a machine learning method for predicting ileal CD by use of radiomic features of ileal wall and mesenteric fat from noncontrast T2-weighted MRI and to compare the performance of the method with that of expert radiologists. METHODS. This single-institution study included retrospectively identified patients who underwent MRE for suspected ileal CD from January 1, 2020, to January 31, 2021, and prospectively enrolled participants (patients with newly diagnosed ileal CD or healthy control participants) from December 2018 to October 2021. Using axial T2-weighted SSFSE images, a radiologist selected two slices showing greatest terminal ileal wall thickening. Four ROIs were segmented, and radiomic features were extracted from each ROI. After feature selection, support-vector machine models were trained to classify the presence of ileal CD. Three fellowship-trained pediatric abdominal radiologists independently classified the presence of ileal CD on SSFSE images. The reference standard was clinical diagnosis of ileal CD based on endoscopy and biopsy results. Radiomic-only, clinical-only, and radiomic-clinical ensemble models were trained and evaluated by nested cross-validation. RESULTS. The study included 135 participants (67 female, 68 male; mean age, 15.2 ± 3.2 years); 70 were diagnosed with ileal CD. The three radiologists had accuracies of 83.7% (113/135), 88.1% (119/135), and 86.7% (117/135) for diagnosing CD; consensus accuracy was 88.1%. Interradiologist agreement was substantial (κ = 0.78). The best-performing ROI was bowel core (AUC, 0.95; accuracy, 89.6%); other ROIs had worse performance (whole-bowel AUC, 0.86; fat-core AUC, 0.70; whole-fat AUC, 0.73). For the clinical-only model, AUC was 0.85 and accuracy was 80.0%. The ensemble model combining bowel-core radiomic and clinical models had AUC of 0.98 and accuracy of 93.5%. The bowel-core radiomic-only model had significantly greater accuracy than radiologist 1 (p = .009) and radiologist 2 (p = .02) but not radiologist 3 (p > .99) or the radiologists in consensus (p = .05). The ensemble model had greater accuracy than the radiologists in consensus (p = .02). CONCLUSION. A radiomic machine learning model predicted CD diagnosis with better performance than two of three expert radiologists. Model performance improved when radiomic data were ensembled with clinical data. CLINICAL IMPACT. Deployment of a radiomic-based model including T2-weighted MRI data could decrease interradiologist variability and increase diagnostic accuracy for pediatric CD.

The Simplified MR Index of Activity Score in Pediatric Small-Bowel Crohn Disease: An Interreader Agreement and Responsiveness Study

BACKGROUND. The simplified MR index of activity (MaRIA) score is used to assess the severity of small-bowel inflammation without use of IV contrast material. OBJECTIVE. The purposes of this study were to assess interreader agreement on the use of simplified MaRIA scores for evaluation of the inflammatory activity of terminal ileal Crohn disease in children and young adults and to assess whether simplified MaRIA scores change after biologic medical therapy. METHODS. This analysis was ancillary to a previously reported primary prospective research investigation. The study included 20 children and young adults with newly diagnosed ileal Crohn disease and 15 healthy control participants who underwent research small-bowel MRI examinations between December 2018 and October 2021. The participants with Crohn disease underwent baseline MRI and MRI 6 weeks and 6 months after beginning anti-tumor necrosis factor α-treatment as well as weighted pediatric Crohn disease activity index (wPCDAI) and C-reactive protein (CRP) assessment on the day of each examination. Control participants underwent one MRI examination. Four pediatric radiologists independently assigned simplified MaRIA scores using axial and coronal T2-weighted SSFSE images. Median simplified MaRIA score among readers was computed. Interreader agreement was assessed with Fleiss kappa coefficients and intra-class correlation coefficient (ICC). Analysis included the Mann-Whitney U test, Friedman test, and Spearman rank correlation. RESULTS. Simplified MaRIA scores (across time points and study groups) had substantial interreader agreement (κ = 0.65 [95% CI, 0.56-0.74]; ICC, 0.71 [95% CI, 0.63-0.78]). Median scores were higher in participants with Crohn disease at baseline than in healthy control participants (3.5 [IQR, 2.5-4.9] vs 0.5 [IQR, 0-2.0]; p < .001). Scores decreased after medical treatment in participants with Crohn disease (p = .005). The median score was 3.5 (IQR, 2.5-4.9) at baseline, 2.3 (IQR, 1.6-3.9) at 6 weeks, and 2.0 (IQR, 0.5-2.5) at 6 months. In participants with Crohn disease, median scores had significant correlations with wPCDAI (ρ = 0.46 [95% CI, 0.18-0.64]; p < .001) and CRP level (ρ = 0.48 [95% CI, 0.27-0.65]; p < .001). CONCLUSION. Radiologists had substantial agreement in use of simplified MaRIA scores to assess intestinal inflammation in ileal Crohn disease. Scores changed over time after medical therapy. CLINICAL IMPACT. The results support the simplified MaRIA score as an objective MRI-based clinical measure of intestinal inflammation in children and young adults with Crohn disease.