Page 28 - Read Online

George et al. Mini-invasive Surg 2024;8:4 Mini-invasive Surgery
DOI: 10.20517/2574-1225.2023.102

Review Open Access

Artificial intelligence in capsule endoscopy:

development status and future expectations

2
1,4
1,2
1
Ashwin A. George , Jin Lin Tan , Joshua G. Kovoor , Alvin Lee , Brandon Stretton 1,2,4 , Aashray K.
1,3
1,2
1
Gupta , Stephen Bacchi , Biju George , Rajvinder Singh 1,2
1
Adelaide Medical School, University of Adelaide, Adelaide 5005, Australia.
2
Department of Gastroenterology, Lyell McEwin Hospital, Adelaide 5112, Australia.
3
Division of Medicine, Queen Elizabeth Hospital, Adelaide 5011, Australia.
4
Department of Gastroenterology, Royal Adelaide Hospital, Adelaide 5000, Australia.
Correspondence to: Prof. Rajvinder Singh, Adelaide Medical School, University of Adelaide, 250 North Terrace, Adelaide 5005,
Australia. E-mail: rajvinder.singh@sa.gov.au
How to cite this article: George AA, Tan JL, Kovoor JG, Lee A, Stretton B, Gupta AK, Bacchi S, George B, Singh R. Artificial
intelligence in capsule endoscopy: development status and future expectations. Mini-invasive Surg 2024;8:4. https://dx.doi.org/
10.20517/2574-1225.2023.102
Received: 23 Aug 2023 First Decision: 14 Dec 2023 Revised: 18 Feb 2024 Accepted: 28 Feb 2024 Published: 18 Mar 2024
Academic Editors: Jean François Rey, Giulio Belli, Michel Gagner Copy Editor: Pei-Yun Wang Production Editor: Pei-Yun
Wang

Abstract
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

© The Author(s) 2024. Open Access This article is licensed under a Creative Commons Attribution 4.0
International License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, sharing,
adaptation, distribution and reproduction in any medium or format, for any purpose, even commercially, as
long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and
indicate if changes were made.

www.oaepublish.com/mis