Artificial intelligence, capsule endoscopy, databases, and the Sword of Damocles

We read with interest the editorial by Hassan et al [1] entitled “AI everywhere in endoscopy, not only for detection and characterization,” prompted by the recent paper of Hansen et al. on “Novel artificial intelligence (AI)-driven software significantly shortens the time required for annotation in computer vision projects” [2]. As Hassan et al. point out, unlike classic machine learning methods (MLM), the new kid on the block’s (i. e., deep learning [DL]) main advantage is its capability to automatically extract image features so that computers can use them to characterize their content [3]. This, essentially, means that the accuracy of this unsupervised approach depends primarily on the aptness and quality of the training data provided.

Publication History

Article published online:
12 November 2021

• References

• 1 Hassan C, Mori Y, Antonelli G. AI everywhere in endoscopy, not only for detection and characterization. Endosc Int Open 2021; 9: E627-E628
• 2 Hansen US, Landau E, Patel M. et al. Novel artificial intelligence-driven software significantly shortens the time required for annotation in computer vision projects. Endosc Int Open 2021; 9: E621-E626
• 3 Dray X, Iakovidis D, Houdeville C. et al. Artificial intelligence in small bowel capsule endoscopy – current status, challenges and future promise. J Gastroenterol Hepatol 2021; 36: 12-19
• 4 Koulaouzidis A, Iakovidis DK, Yung DE. et al. KID Project: an internet-based digital video atlas of capsule endoscopy for research purposes. Endosc Int Open 2017; 5: E477-E483
• 5 Leenhardt R, Li C, Le Mouel JP. et al. CAD-CAP: a 25,000-image database serving the development of artificial intelligence for capsule endoscopy. Endosc Int Open 2020; 8: E415-E420
• 6 Smedsrud PH, Thambawita V, Hicks SA. et al. Kvasir-Capsule, a video capsule endoscopy dataset. Scientific Data 2021; 8: 142 https://www.nature.com/articles/s41597-021-00920-z
• 7 Dray X, Koulaouzidis A. Panenteric capsule endoscopy; a new soldier at the forefront of lower gastrointestinal bleeding workup and…beyond!. Eur J Gastroenterol Hepatol 2021; DOI: 10.1097/MEG.0000000000002085.
• 8 Dray X, Houist G, Le Mouel JP. et al. Prospective evaluation of third-generation small bowel capsule endoscopy videos by independent readers demonstrates poor reproducibility of cleanliness classifications. Clin Res Hepatol Gastroenterol 2021; 45: 101612
• 9 Leenhardt R, Souchaud M, Houist G. et al. A neural network-based algorithm for assessing the cleanliness of small bowel during capsule endoscopy. Endoscopy 2020; DOI: 10.1055/a-1301-3841.
• 10 Leenhardt R, Koulaouzidis A, McNamara D. et al. A guide for assessing the clinical relevance of findings in small bowel capsule endoscopy: analysis of 8064 answers of international experts to an illustrated script questionnaire. Clin Res Hepatol Gastroenterol 2021; 45: 101637
• 11 Koulaouzidis A, Toth E. Image database, AI and capsule endoscopy; the bets are on. Endosc Int Open 2020; 8: E421-E422