Abstract
BACKGROUND AND AIM: Intestinal ultrasound (IUS) potentially spares patients from repeated endoscopies under sedation and eliminates the need for alternative imaging modalities like magnetic resonance enterography and computed tomography enterography scans. However, interpreting IUS images is challenging for physicians due to the time-intensive process of identifying markers indicative of inflammatory bowel disease (IBD). This study aims for fully automating the analysis of pediatric IBD to distinguish between abnormal and normal cases. METHODS: We used data set of 260 pediatric patients, consisting of 4565 IUS images with 1478 abnormal and 3087 normal cases. Meticulous annotation of the region between the lumen/mucosa and the muscularis/serosa interfaces in a subset of 612 images were performed. An artificial intelligence (AI) algorithm was trained to delineate the region between these interfaces. The boundaries of these regions were extracted, and the average bowel wall thickness (BWT) was calculated and analyzed using cutoff values ranging between 1.5 and 3 mm. RESULTS: This study showed promising segmentation performance in accurately identifying the lumen/mucosa and muscularis/serosa interfaces. In a separate test set of 3953 images, the classification performance at the 2mm BWT cutoff showed the highest sensitivity of 90.29% and a specificity of 93.70%. The AI method showed strong agreement, with an interclass correlation of 0.942 (95% CI: 0.938-0.946), compared to manual clinical measurements. CONCLUSIONS: This study demonstrates an AI approach to automate the analysis of pediatric IBD IUS images, providing a reliable tool for early detection, precise characterization, and monitoring of the disease.