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

Journal: BMJ open gastroenterology
Published Date:

Abstract

OBJECTIVE: Capsule endoscopy (CE) is pivotal for evaluation of small bowel disease. Obscure gastrointestinal bleeding most often originates from the small bowel. CE frequently identifies a wide range of lesions with different bleeding potentials in these patients. However, reading CE examinations is a time-consuming task. Convolutional neural networks (CNNs) are highly efficient artificial intelligence tools for image analysis. This study aims to develop a CNN-based model for identification and differentiation of multiple small bowel lesions with distinct haemorrhagic potential using CE images.

Authors

  • Miguel José Mascarenhas Saraiva
    Department of Gastroenterology, Hospital São João, Porto, Portugal miguelmascarenhassaraiva@gmail.com.
  • João Afonso
    Department of Gastroenterology, São João University Hospital, Porto, Portugal.
  • Tiago Ribeiro
    Department of Gastroenterology, São João University Hospital, Porto, Portugal.
  • João Ferreira
    Department of Mechanical Engineering, Faculty of Engineering of the University of Porto, Porto, Portugal.
  • Hélder Cardoso
    Department of Gastroenterology, São João University Hospital, Porto, Portugal.
  • Ana Patricia Andrade
    Department of Gastroenterology, Hospital São João, Porto, Portugal.
  • Marco Parente
    Department of Mechanical Engineering, Faculty of Engineering of the University of Porto, Porto, Portugal.
  • Renato Natal
    Department of Mechanical Engineering, Faculty of Engineering of the University of Porto, Porto, Portugal.
  • Miguel Mascarenhas Saraiva
    Department of Gastroenterology, São João University Hospital, Porto, Portugal.
  • Guilherme Macedo
    Department of Gastroenterology, São João University Hospital, Porto, Portugal.