Deep learning in negative small‐bowel capsule endoscopy improves small‐bowel lesion detection and diagnostic yield

Abstract

Background/AimsAlthough several studies have shown the usefulness of artificial intelligence to identify abnormalities in small bowel capsule endoscopy (SBCE) images, few studies have proven its actual clinical usefulness. Thus, the aim of this study was to examine whether meaningful findings could be obtained when negative SBCE videos were re‐analyzed with a deep convolutional neural network (CNN) model.MethodsClinical data of patients who received SBCE for suspected small bowel bleeding at two academic hospitals between February 2018 and July 2020 were retrospectively collected. All SBCE videos read as negative were re‐analyzed with the CNN algorithm developed in our previous study. Meaningful findings such as angioectasias and ulcers were finally decided after reviewing CNN‐selected images by two gastroenterologists.ResultsAmong 202 SBCE videos, 103 (51.0%) were read as negative by human. Meaningful findings were detected in 63 (61.2%) of these 103 videos after re‐analyzing them with the CNN model. There were 79 red spots or angioectasias in 40 videos and 66 erosions or ulcers in 35 videos. After re‐analysis, diagnosis was changed for 10 (10.3%) patients who had initially negative SBCE results. During a mean follow‐up of 16.5 months, rebleeding occurred in 19 (18.4%) patients. Rebleeding rate was 23.6% (13/55) for patients with meaningful findings and 16.1% (5/31) for patients without meaningful findings (P = 0.411).ConclusionsOur CNN algorithm detected meaningful findings in negative SBCE videos that were missed by humans. The use of deep CNN for SBCE image reading is expected to compensate for human error.