A convolutional neural network for bleeding detection in capsule endoscopy using real clinical data.
Machine learning
bleeding detection
capsule endoscopy
convolutional neural networks
small bowel
Journal
Minimally invasive therapy & allied technologies : MITAT : official journal of the Society for Minimally Invasive Therapy
ISSN: 1365-2931
Titre abrégé: Minim Invasive Ther Allied Technol
Pays: England
ID NLM: 9612996
Informations de publication
Date de publication:
28 Aug 2023
28 Aug 2023
Historique:
medline:
29
8
2023
pubmed:
29
8
2023
entrez:
28
8
2023
Statut:
aheadofprint
Résumé
The goal of the present study was to develop a convolutional neural network for the detection of bleedings in capsule endoscopy videos using realistic clinical data from one single-centre. Capsule endoscopy videos from all 133 patients (79 male, 54 female; mean The overall accuracy of the model for the detection of bleedings was 90.6% [95%CI: 89.4%-91.7%], with a sensitivity of 89.4% [95%CI: 87.6%-91.2%] and a specificity of 91.7% [95%CI: 90.1%-93.2%]. Our results show that neural networks can detect bleedings in capsule endoscopy videos under realistic, clinical conditions with an accuracy of 90.6%, potentially reducing reading time per capsule and helping to improve diagnostic accuracy.
Sections du résumé
BACKGROUND
UNASSIGNED
The goal of the present study was to develop a convolutional neural network for the detection of bleedings in capsule endoscopy videos using realistic clinical data from one single-centre.
METHODS
UNASSIGNED
Capsule endoscopy videos from all 133 patients (79 male, 54 female; mean
RESULTS
UNASSIGNED
The overall accuracy of the model for the detection of bleedings was 90.6% [95%CI: 89.4%-91.7%], with a sensitivity of 89.4% [95%CI: 87.6%-91.2%] and a specificity of 91.7% [95%CI: 90.1%-93.2%].
CONCLUSION
UNASSIGNED
Our results show that neural networks can detect bleedings in capsule endoscopy videos under realistic, clinical conditions with an accuracy of 90.6%, potentially reducing reading time per capsule and helping to improve diagnostic accuracy.
Identifiants
pubmed: 37640056
doi: 10.1080/13645706.2023.2250445
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM