Wireless Capsule Endoscopy with AI-Assisted Lesion Detection: Diagnostic Accuracy Assessment

Authors

DOI:

https://doi.org/10.5281/zenodo.22642738

Keywords:

wireless capsule endoscopy, artificial intelligence lesion detection, convolutional neural network, small bowel bleeding, diagnostic accuracy

Abstract

Background: Wireless capsule endoscopy has become a first-line investigation for suspected small-bowel bleeding, Crohn's disease, and polyposis surveillance, but interpretation of the tens of thousands of frames each study generates is time-consuming and subject to interobserver variability. Objective: This narrative review synthesizes published literature on capsule endoscopy imaging technology and on deep-learning algorithms developed to automate detection of small-bowel and colonic lesions, focusing on reported diagnostic accuracy. Methods: We reviewed engineering studies of capsule device architecture and mucosal-quality assessment, convolutional neural network algorithms trained to detect erosions, ulcerations, blood content, protruding lesions, angiectasia, and Crohn's disease ulcers, and prospective multicentre studies comparing AI-assisted with standard human reading. Findings: Retrospective validation studies report area-under-the-curve values generally between 0.91 and 0.96 and lesion-specific sensitivities frequently exceeding 90%, while the two largest prospective multicentre studies to date show that AI-assisted reading reduces total reading time by approximately 85-92% while matching or exceeding the lesion-detection performance of unassisted expert readers. Conclusions: AI-assisted lesion detection in capsule endoscopy has reached a level of retrospective and prospective diagnostic accuracy that supports its expanding clinical use, though further open benchmark datasets and outcome-linked trials are needed to guide broader adoption.

References

Iddan G, Meron G, Glukhovsky A, Swain P (2000) Wireless capsule endoscopy. Nature, 405(6785):417, DOI:10.1038/35013140.

Iakovidis DK, Koulaouzidis A (2015) Software for enhanced video capsule endoscopy: challenges for essential progress. Nature Reviews Gastroenterology & Hepatology, 12(3):172-186, DOI:10.1038/nrgastro.2015.13.

Gilabert P, Vitria J, Laiz P, Malagelada C, Watson A, Wenzek H, Segui S (2022) Artificial intelligence to improve polyp detection and screening time in colon capsule endoscopy. Frontiers in Medicine, 9:1000726, DOI:10.3389/fmed.2022.1000726.

Nam JH, Hwang Y, Oh DJ, Park J, Kim KB, Jung MK, Lim YJ (2021) Development of a deep learning-based software for calculating cleansing score in small bowel capsule endoscopy. Scientific Reports, 11:4417, DOI:10.1038/s41598-021-81686-7.

Histace A, Dray X, Leenhardt R, Souchaud M, Houist G, Le Mouel JP, Saurin JC, Cholet F, Rahmi G, Leandri C (2020) A neural network-based algorithm for assessing the cleanliness of small bowel during capsule endoscopy. Endoscopy, 53(9):932-936, DOI:10.1055/a-1301-3841.

Ding Z, Shi H, Zhang H, Meng L, Fan M, Han C, Zhang K, Ming F, Xie X, Liu H, Liu J, Lin R, Hou X (2019) Gastroenterologist-Level Identification of Small-Bowel Diseases and Normal Variants by Capsule Endoscopy Using a Deep-Learning Model. Gastroenterology, 157(4):1044-1054.e5, DOI:10.1053/j.gastro.2019.06.025.

Aoki T, Yamada A, Aoyama K, Saito H, Tsuboi A, Nakada A, Niikura R, Fujishiro M, Oka S, Ishihara S, Matsuda T, Tanaka S, Koike K, Tada T (2019) Automatic detection of erosions and ulcerations in wireless capsule endoscopy images based on a deep convolutional neural network. Gastrointestinal Endoscopy, 89(2):357-363.e2, DOI:10.1016/j.gie.2018.10.027.

Aoki T, Yamada A, Kato Y, Saito H, Tsuboi A, Nakada A, Niikura R, Fujishiro M, Oka S, Ishihara S, Matsuda T, Nakahori M, Tanaka S, Koike K, Tada T (2020) Automatic detection of blood content in capsule endoscopy images based on a deep convolutional neural network. Journal of Gastroenterology and Hepatology, 35(7):1196-1200, DOI:10.1111/jgh.14941.

Saito H, Aoki T, Aoyama K, Kato Y, Tsuboi A, Yamada A, Fujishiro M, Oka S, Ishihara S, Matsuda T, Nakahori M, Tanaka S, Koike K, Tada T (2020) Automatic detection and classification of protruding lesions in wireless capsule endoscopy images based on a deep convolutional neural network. Gastrointestinal Endoscopy, 92(1):144-151.e1, DOI:10.1016/j.gie.2020.01.054.

Otani K, Nakada A, Kurose Y, Niikura R, Yamada A, Aoki T, Nakanishi H, Doyama H, Hasatani K, Sumiyoshi T, Kitsuregawa M, Harada T, Koike K (2020) Automatic detection of different types of small-bowel lesions on capsule endoscopy images using a newly developed deep convolutional neural network. Endoscopy, 52(9):786-791, DOI:10.1055/a-1167-8157.

Leenhardt R, Vasseur P, Li C, Saurin JC, Rahmi G, Cholet F, Becq A, Marteau P, Histace A, Dray X, Sacher-Huvelin S, Mesli F, Leandri C, Nion-Larmurier I, Lecleire S, Gerard R, Duburque C, Vanbiervliet G, Amiot X, Le Mouel JP, Delvaux M, Jacob P, Simon-Shane C, Romain O (2019) A neural network algorithm for detection of GI angiectasia during small-bowel capsule endoscopy. Gastrointestinal Endoscopy, 89(1):189-194, DOI:10.1016/j.gie.2018.06.036.

He JY, Wu X, Jiang YG, Peng Q, Jain R (2018) Hookworm Detection in Wireless Capsule Endoscopy Images With Deep Learning. IEEE Transactions on Image Processing, 27(5):2379-2392, DOI:10.1109/TIP.2018.2801119.

Klang E, Barash Y, Margalit RY, Soffer S, Shimon O, Albshesh A, Ben-Horin S, Amitai MM, Eliakim R, Kopylov U (2020) Deep learning algorithms for automated detection of Crohn's disease ulcers by video capsule endoscopy. Gastrointestinal Endoscopy, 91(3):606-613.e2, DOI:10.1016/j.gie.2019.11.012.

Mascarenhas M, Afonso J, Ribeiro T, Cardoso H, Andrade P, Ferreira JPS, Mascarenhas Saraiva M, Macedo G (2022) Performance of a Deep Learning System for Automatic Diagnosis of Protruding Lesions in Colon Capsule Endoscopy. Diagnostics, 12(6):1445, DOI:10.3390/diagnostics12061445.

Yamada A, Niikura R, Otani K, Aoki T, Koike K (2020) Automatic detection of colorectal neoplasia in wireless colon capsule endoscopic images using a deep convolutional neural network. Endoscopy, 53(8):832-836, DOI:10.1055/a-1266-1066.

Soffer S, Klang E, Shimon O, Nachmias N, Eliakim R, Ben-Horin S, Kopylov U, Barash Y (2020) Deep learning for wireless capsule endoscopy: a systematic review and meta-analysis. Gastrointestinal Endoscopy, 92(4):831-839.e8, DOI:10.1016/j.gie.2020.04.039.

Spada C, Piccirelli S, Hassan C, Ferrari C, Toth E, Gonzalez-Suarez B, Keuchel M, McAlindon M, Finta A, Rosztoczy A, Dray X, Salvi D, Riccioni ME, Benamouzig R, Chattree A, Humphries A, Saurin JC, Despott EJ, Murino A, Wurm Johansson G, Giordano A, Baltes P, Sidhu R, Szalai M, Helle K, Nemeth A, Nowak T, Lin R, Costamagna G (2024) AI-assisted capsule endoscopy reading in suspected small bowel bleeding: a multicentre prospective study. The Lancet Digital Health, 6(5):e345-e353, DOI:10.1016/S2589-7500(24)00048-7.

Giordano A, Escapa M, Urpi-Ferreruela M, Casanova G, Fernandez-Esparrach G, Gines A, Llach J, Gonzalez-Suarez B (2023) Diagnostic accuracy of artificial intelligence-aided capsule endoscopy (TOP100) in overt small bowel bleeding. Surgical Endoscopy, 37(10):7658-7666, DOI:10.1007/s00464-023-10273-w.

Smedsrud PH, Thambawita V, Hicks SA, Gjestang H, Nedrejord OO, Naess E, Borgli H, Jha D, Berstad TJD, Eskeland SL, Lux M, Espeland H, Petlund A, Nguyen DTD, Garcia-Ceja E, Johansen D, Schmidt PT, Toth E, Hammer HL, de Lange T, Riegler MA, Halvorsen P (2021) Kvasir-Capsule, a video capsule endoscopy dataset. Scientific Data, 8:142, DOI:10.1038/s41597-021-00920-z.

Sahafi A, Koulaouzidis A, Naemi A (2026) Artificial Intelligence in Gastrointestinal Wireless Capsule Endoscopy: A Systematic Literature Review and Meta-Analysis. Diagnostics, 16(9):1269, DOI:10.3390/diagnostics16091269.

Trasolini R, Byrne MF (2021) Artificial intelligence and deep learning for small bowel capsule endoscopy. Digestive Endoscopy, 33(2):290-297, DOI:10.1111/den.13896.

Downloads

Published

2026-06-26