Identification of Ulcers and Erosions by the Novel Pillcam™ Crohn’s Capsule Using a Convolutional Neural Network: A Multicentre Pilot Study

Abstract

Background and aims Capsule endoscopy is a central element in the management of patients with suspected or known Crohn’s disease. In 2017, PillCam™ Crohn’s Capsule was introduced and demonstrated greater accuracy in the evaluation of extension of disease in these patients. Artificial Intelligence is expected to enhance the diagnostic accuracy of capsule endoscopy. This study aims to develop an AI algorithm for the automatic detection of ulcers and erosions of the small intestine and colon in PillCam™ Crohn’s Capsule images. Methods A total of 8085 PillCam™ Crohn’s Capsule images were extracted between 2017-2020, constituted by 2855 images of ulcers and 1975 erosions; the remaining images showed normal enteric and colonic mucosa. This pool of images was subsequently split into training and validation datasets. The performance of the network was subsequently assessed in an independent test set. Results The model had an overall sensitivity and specificity of 90.0% and 96.0%, respectively. The precision and accuracy of this model were 97.1% and 92.4%, respectively. Particularly, the algorithm detected ulcers with a sensitivity of 83% and specificity of 98%, and erosions with sensitivity and specificity of 91% and 93%, respectively. Conclusion A deep learning model capable of automatically detecting ulcers and erosions in PillCam™ Crohn’s Capsule images was developed for the first time. These findings pave the way for the development of automatic systems for detection of clinically significant lesions, optimizing diagnostic performance and efficiency of monitoring Crohn’s disease activity.

Deep Learning and Device-Assisted Enteroscopy: Automatic Detection of Gastrointestinal Angioectasia

“…In the last decade, we assisted the development of AI systems for application to several diagnostic modalities. Studies on the implementation of CNNs to several endoscopic modalities produced promising results [11][12][13][14][15]. In this retrospective study, we developed a pioneer deep learning algorithm for automatic detection of gastrointestinal angioectasia, with high sensitivity, specificity and overall accuracy.…”

“…The application of artificial intelligence (AI) algorithms for the automatic analysis of endoscopic images has been the focus of intensive research. Indeed, several systems were developed for implementation in EGD, colonoscopy and CE [9][10][11]. Deep learning systems, and particularly convolutional neural networks, allow the analysis of large image datasets with high performance.…”

Artificial Endoscopy and Inflammatory Bowel Disease: Welcome to the Future

“…DL methods for autonomous detection and classification of CD lesions have also been applied to panenteric capsule endoscopy system that is now available allowing simultaneous investigation of the small bowel and colon. AI technology has increased the diagnostic yield and reduced interobserver variability in this integrated procedure [56,57].…”

Review: Colon Capsule Endoscopy in Inflammatory Bowel Disease

“…However, although the PCE is conceivably an appropriate endoscopic method for mapping and grading established CD, further studies are needed to support its role in a ‘treat-to-target’ strategy for disease management and monitoring [ 43 ]. In addition, preliminary research on the role of AI for the detection of erosions and ulcers using the PillCam Crohn’s capsule has shown promising results, and may not only improve accuracy, but also reduce reading times and this area merits further investigation [ 44 ].…”