New Generation Express View: An Artificial Intelligence Software Effectively Reduces Capsule Endoscopy Reading Times

Abstract

BACKGROUND: Reading capsule endoscopy (CE) is time-consuming. The Express View (EV) (IntroMedic, Seoul, Korea) software was designed to shorten CE video reading. Our primary aim was to evaluate the diagnostic accuracy of EV in detecting significant small-bowel (SB) lesions. We also compared the reading times with EV mode and standard reading (SR). METHODS: 126 patients with suspected SB bleeding and/or suspected neoplasia were prospectively enrolled and underwent SB CE (MiroCam®1200, IntroMedic, Seoul, Korea). CE evaluation was performed in standard and EV mode. In case of discrepancies between SR and EV readings, a consensus was reached after reviewing the video segments and the findings were re-classified. RESULTS: The completion rate of SB CE in our cohort was 86.5% and no retention occurred. The per-patient analysis of sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of EV compared to SR were 86%, 86%, 90%, 81%, and 86%, respectively, before consensus. After consensus, they increased to 97%, 100%, 100%, 96%, and 98%, respectively. The median reading time with SR and EV was 71 min (range 26–340) and 13 min (range 3–85), respectively (p < 0.001). CONCLUSIONS: The new-generation EV shows high diagnostic accuracy and significantly reduces CE reading times.

Deep Learning and Minimally Invasive Endoscopy: Automatic Classification of Pleomorphic Gastric Lesions in Capsule Endoscopy

“…However, CE (particularly CCE) is a time and resource-consuming examination with a large number of image frames produced, which is a disadvantage against conventional endoscopy evaluation. Furthermore, despite numerous studies about CNN models in small bowel and colon evaluation by WCE ( 9 , 15 ), there are no published articles about CNN models for gastric evaluation in WCE. Therefore, implementation of a specific gastric CNN, associated with small bowel and colon CNN, is important for increasing the diagnostic yield and cost-effectiveness of WCE-based panendoscopy, giving it an advantage over conventional endoscopy by providing simultaneous evaluation of the full length of the GI tract in a minimally invasive single examination.…”

“…CE dependence of the peristaltic movements can be a challenge when implementing this technology in the clinical setting. Besides, CE is a time-consuming examination, with reading times for a single examination ranging from 30 to 120 minutes ( 9 ).…”

Capsule endoscopy and panendoscopy: A journey to the future of gastrointestinal endoscopy

“…The OMOM CC TM integrates a new feature for artificial intelligence (AI) assisted diagnosis. If this is properly validated, it might overcome a current limitation of PCE, which is its time-consuming reading, reaching on average up to 120 min[ 8 ]. This will allow a faster examination, without compromising diagnostic accuracy.…”