A convolutional neural network for bleeding detection in capsule endoscopy using real clinical data.

Dorothee TurckThomas DratschLorenz SchröderFlorian LorenzJohanna DinterMartin BürgerLars SchiffmannPhilipp KasperGabriel AlloTobias GoeserSeung-Hun ChonDirk Nierhoff

Published in: Minimally invasive therapy & allied technologies : MITAT : official journal of the Society for Minimally Invasive Therapy (2023)

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.

Keyphrases

convolutional neural network
neural network
deep learning
small bowel
electronic health record
machine learning
working memory
data analysis