Deep learning based lesions detection and severity grading of small bowel Crohn's disease ulcers on double-balloon endoscopy images

Double-balloon endoscopy (DBE) is widely used in diagnosing small bowel Crohn's disease (CD). However, CD misdiagnosis frequently occurs if inexperienced endoscopists cannot accurately detect the lesions. The CD evaluation may also be inaccurate and less objective due to the subjectivity of endoscopists. Our study aims to utilize artificial intelligence (AI) to accurately detect and objectively assess small bowel CD for more refined disease management. We collected 28155 small bowel DBE images from 628 patients between January 2018 and December 2022. Four expert gastroenterologists labeled the images, and at least two endoscopists made the final decision with an agreement. A state-of-the-art deep learning model EfficientNet-b5 was trained to detect CD lesions and evaluate CD ulcers. The detection included lesions of ulcer, non-inflammatory stenosis, and inflammatory stenosis. Ulcer grading had ulcerated surface, ulcer size, and ulcer depth. A comparison of AI model performance with endoscopists was performed. The EfficientNet-b5 achieved high accuracies of 96.3% (95% CI, 95.7%-96.7%), 95.7% (95% CI, 95.1%-96.2%), and 96.7% (95% CI, 96.2%-97.2%) for the detection of ulcers, non-inflammatory stenosis, and inflammatory stenosis, respectively. In ulcer grading, the EfficientNet-b5 exhibited average accuracies of 87.3% (95% CI, 84.6%-89.6%) for grading the ulcerated surface, 87.8% (95% CI, 85.0%-90.2%) for grading the size of ulcers, and 85.2% (95% CI, 83.2%-87.0%) for the ulcer depth assessment. The EfficientNet-b5 achieved high accuracy in detecting CD lesions and grading CD ulcers. The AI model can provide expert-level accuracy and objective evaluation of small bowel CD to optimize the clinical treatment plans.