Endoscopy 2021; 53(09): 932-936
DOI: 10.1055/a-1301-3841
Innovations and brief communications

A neural network-based algorithm for assessing the cleanliness of small bowel during capsule endoscopy

1  Sorbonne University, Center for Digestive Endoscopy, Saint Antoine Hospital, APHP, Paris, France
2  ETIS, Université de Cergy-Pontoise, ENSEA, CNRS, Cergy-Pontoise, France
,
Marc Souchaud
2  ETIS, Université de Cergy-Pontoise, ENSEA, CNRS, Cergy-Pontoise, France
,
Guy Houist
3  Gastroenterology Department, Centre Hospitalier Sud Francilien, Corbeil-Essonnes, France
,
Jean-Philippe Le Mouel
4  Gastroenterology, Amiens University Hospital, Université de Picardie Jules Verne, Amiens, France
,
Jean-Christophe Saurin
5  Gastroenterology and Endoscopy Unit, Edouard Herriot Hospital, Lyon, France
,
Franck Cholet
6  Endoscopy Unit, CHU La Cavale Blanche, Brest, France
,
Gabriel Rahmi
7  Department of Gastroenterology and Digestive Endoscopy, Georges-Pompidou European Hospital, APHP, Paris, France
,
Chloé Leandri
8  Gastroenterology Department, Cochin Hospital, APHP, Paris, France
,
Aymeric Histace*
2  ETIS, Université de Cergy-Pontoise, ENSEA, CNRS, Cergy-Pontoise, France
,
Xavier Dray*
1  Sorbonne University, Center for Digestive Endoscopy, Saint Antoine Hospital, APHP, Paris, France
2  ETIS, Université de Cergy-Pontoise, ENSEA, CNRS, Cergy-Pontoise, France
› Author Affiliations

Abstract

Background Cleanliness scores in small-bowel capsule endoscopy (SBCE) have poor reproducibility. The aim of this study was to evaluate a neural network-based algorithm for automated assessment of small-bowel cleanliness during capsule endoscopy.

Methods 600 normal third-generation SBCE still frames were categorized as “adequate” or “inadequate” in terms of cleanliness by three expert readers, according to a 10-point scale, and served as a training database. Then, 156 third-generation SBCE recordings were categorized in a consensual manner as “adequate” or “inadequate” in terms of cleanliness; this testing database was split into two independent 78-video subsets for the tuning and evaluation of the algorithm, respectively.

Results Using a threshold of 79 % “adequate” still frames per video to achieve the best performance, the algorithm yielded a sensitivity of 90.3 %, specificity of 83.3 %, and accuracy of 89.7 %. The reproducibility was perfect. The mean calculation time per video was 3 (standard deviation 1) minutes.

Conclusion This neural network-based algorithm allowing automatic assessment of small-bowel cleanliness during capsule endoscopy was highly sensitive and paves the way for automated, standardized SBCE reports.

* These authors contributed equally.




Publication History

Received: 14 June 2020

Accepted: 30 October 2020

Publication Date:
02 November 2020 (online)

© 2020. Thieme. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany