Aymeric Histace1, Xavier Dray2,1, Romain Leenhardt2,1, Marc Souchaud1, Guy Houist3, Jean-Philippe Le Mouel4, Jean-Christophe Saurin5, Franck Cholet6, Gabriel Rahmi7, Chloé Leandri8. 1. ETIS, Université de Cergy-Pontoise, ENSEA, CNRS, Cergy-Pontoise, France. 2. Sorbonne University, Center for Digestive Endoscopy, Saint Antoine Hospital, APHP, Paris, France. 3. Gastroenterology Department, Centre Hospitalier Sud Francilien, Corbeil-Essonnes, France. 4. Gastroenterology, Amiens University Hospital, Université de Picardie Jules Verne, Amiens, France. 5. Gastroenterology and Endoscopy Unit, Edouard Herriot Hospital, Lyon, France. 6. Endoscopy Unit, CHU La Cavale Blanche, Brest, France. 7. Department of Gastroenterology and Digestive Endoscopy, Georges-Pompidou European Hospital, APHP, Paris, France. 8. Gastroenterology Department, Cochin Hospital, APHP, Paris, France.
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. Thieme. All rights reserved.
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. Thieme. All rights reserved.