Artificial intelligence and capsule endoscopy: automatic detection of enteric protruding lesions using a convolutional neural network

Artificial intelligence in capsule endoscopy: development status and future expectations

In this review, we aim to illustrate the state-of-the-art artificial intelligence (AI) applications in the field of capsule endoscopy. AI has made significant strides in gastrointestinal imaging, particularly in capsule endoscopy - a non-invasive procedure for capturing gastrointestinal tract images. However, manual analysis of capsule endoscopy videos is labour-intensive and error-prone, prompting the development of automated computational algorithms and AI models. While currently serving as a supplementary observer, AI has the capacity to evolve into an autonomous, integrated reading system, potentially significantly reducing capsule reading time while surpassing human accuracy. We searched Embase, Pubmed, Medline, and Cochrane databases from inception to 06 Jul 2023 for studies investigating the use of AI for capsule endoscopy and screened retrieved records for eligibility. Quantitative and qualitative data were extracted and synthesised to identify current themes. In the search, 824 articles were collected, and 291 duplicates and 31 abstracts were deleted. After a double-screening process and full-text review, 106 publications were included in the review. Themes pertaining to AI for capsule endoscopy included active gastrointestinal bleeding, erosions and ulcers, vascular lesions and angiodysplasias, polyps and tumours, inflammatory bowel disease, coeliac disease, hookworms, bowel prep assessment, and multiple lesion detection. This review provides current insights into the impact of AI on capsule endoscopy as of 2023. AI holds the potential for faster and precise readings and the prospect of autonomous image analysis. However, careful consideration of diagnostic requirements and potential challenges is crucial. The untapped potential within vision transformer technology hints at further evolution and even greater patient benefit.

Efficacy-safety profile of the video capsule endoscopy in the study of the small bowel: experience over 100 consecutive procedures

Video capsule endoscopy (VCE) is currently considered the first-line study in the evaluation of the small bowel (SB). Retrospective study including consecutive patients from 2010 to 2021 in two referral endoscopic centers in Peru, who underwent VCE. Inclusion criteria were patients with middle gastrointestinal bleeding, chronic diarrhea and unexplained chronic abdominal pain (endoscopic studies prior to VCE: normal). We mainly used Pillcam SB VCE (Given Imaging, Israel) SB2 and SB3 generations.