Login / Signup

Deep learning and capsule endoscopy: automatic identification and differentiation of small bowel lesions with distinct haemorrhagic potential using a convolutional neural network.

Miguel Mascarenhas SaraivaJoão AfonsoTiago RibeiroJoão FerreiraHelder CardosoAna Patricia AndradeMarco ParenteRenato NatalMiguel Mascarenhas SaraivaGuilherme Macedo
Published in: BMJ open gastroenterology (2021)
We developed and tested a CNN-based model for automatic detection of multiple types of small bowel lesions and classification of the respective bleeding potential. This system may improve the diagnostic yield of CE for these lesions and overall CE efficiency.
Keyphrases
  • small bowel
  • deep learning
  • convolutional neural network
  • artificial intelligence
  • machine learning
  • atrial fibrillation
  • energy transfer
  • loop mediated isothermal amplification
  • sensitive detection