Enhancing radiologist's detection: an imaging-based grading system for differentiating Crohn's disease from ulcerative colitis.

Abstract

Delayed diagnosis of inflammatory bowel disease (IBD) is common, there is still no effective imaging system to distinguish Crohn's Disease (CD) and Ulcerative Colitis (UC) patients. This multicenter retrospective study included IBD patients at three centers between January 2012 and May 2022. The intestinal and perianal imaging signs were evaluated. Visceral fat information from CT images was extracted, including the ratio of visceral to subcutaneous fat volume (VSR), fat distribution, and attenuation values. The valuable indicators were screened out in the derivation cohort by binary logistic regression and receiver working curve (ROC) analysis to construct an imaging report and data system for IBD (IBD-RADS), which was tested in the validation cohort. The derivation cohort included 606 patients (365 CD, 241 UC), and the validation cohort included 155 patients (97 CD, 58 UC). Asymmetric enhancement (AE) (OR = 87.75 [28.69, 268.4]; P < 0.001), perianal fistula (OR = 4.968 [1.807, 13.66]; P = 0.002) and VSR (OR = 1.571 [1.087, 2.280]; P = 0.04) were independent predictors of CD. VSR improved the efficiency of imaging signs (AUC: 0.929 vs. 0.901; P < 0.001), with a threshold greater than 0.97 defined as visceral fat predominance (VFP). In IBD-RADS, AE was the major criterion, VFP and perianal fistula were auxiliary criteria, and intestinal fistula, limited small bowel disease, and skip distribution were special favoring items as their 100% specificity. Grade 3 to 5 correctly classified most CD patients (derivation: 96.5% (352/365), validation: 98.0% (95/97)), and 98% of those were eventually diagnosed with CD (derivation: 97.8% (352/360), validation: 98.0% (95/97)). IBD-RADS can help radiologists distinguish between CD and UC in patients with suspected IBD.