Artificial Intelligence for Quantifying Cumulative Small Bowel Disease Severity on CT-Enterography in Crohn's Disease.

Abstract

Assessing the cumulative degree of bowel injury in ileal Crohn's disease (CD) is difficult. We aimed to develop machine learning (ML) methodologies for automated estimation of cumulative ileal injury on CT-enterography (CTE) to help predict future bowel surgery. Adults with ileal CD using biologic therapy at a tertiary care center underwent ML analysis of CTE scans. Two fellowship trained radiologists graded bowel injury severity at granular spatial increments along the ileum (1cm), called mini-segments. ML segmentation methods were trained on radiologist grading with predicted severity then spatially mapped to the ileum. Cumulative injury was calculated as the sum (S-CIDSS) and mean of severity grades along the ileum. Multivariate models of future small bowel resection were compared cumulative ileum injury metrics and traditional bowel measures, adjusting for laboratory values, medications, and prior surgery at the time of CTE. In 229 CTEs, 8424 mini-segments underwent analysis. Agreement between ML and radiologists injury grading was strong (κ=0.80, 95%CI 0.79-0.81) and similar to inter-radiologist agreement (κ=0.87, 95%CI 0.85-0.88). S-CIDSS (46.6 vs. 30.4, P=0.0007) and mean cumulative injury grade scores (1.80 vs. 1.42, P<0.0001) were greater in CD biologic users that went to future surgery. Models using cumulative spatial metrics (AUC=0.76) outperformed models using conventional bowel measures, laboratory values, and medical history (AUC=0.62) for predicting future surgery in biologic users. Automated cumulative ileal injury scores show promise for improving prediction of outcomes in small bowel CD. Beyond replicating expert judgement, spatial enterography analysis can augment the personalization of bowel assessment in CD.