A neural network-based algorithm for assessing the cleanliness of small bowel during capsule endoscopy.
Journal
Endoscopy
ISSN: 1438-8812
Titre abrégé: Endoscopy
Pays: Germany
ID NLM: 0215166
Informations de publication
Date de publication:
09 2021
09 2021
Historique:
aheadofprint:
30
10
2020
pubmed:
3
11
2020
medline:
14
9
2021
entrez:
2
11
2020
Statut:
ppublish
Résumé
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. 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. 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. 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.
Sections du résumé
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.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
932-936Informations de copyright
Thieme. All rights reserved.
Déclaration de conflit d'intérêts
Xavier Dray, Romain Leenhardt, and Aymeric Histace are cofounders and shareholders of Augmented Endoscopy. Xavier Dray has acted as a consultant for Boston Scientific and Norgine, and has presented lectures for Fujifilm, Medtronic, and Pentax. Romain Leenhardt has presented lectures for Abbvie. All other authors declare that they have no conflicts of interest.