Portal de investigação
Deep Learning and Minimally Invasive Endoscopy: Automatic Classification of Pleomorphic Gastric Lesions in Capsule Endoscopy
Data de publicação:
Autores da FMUP
Participantes de fora da FMUP
- Mascarenhas, Miguel
- Mendes, Francisco
- Ribeiro, Tiago
- Afonso, Joao
- Cardoso, Pedro
- Martins, Miguel
- Cardoso, Helder
- Andrade, Patricia
- Ferreira, Joao
- Saraiva, Miguel Mascarenhas
Unidades de investigação
Abstract
INTRODUCTION: Capsule endoscopy (CE) is a minimally invasive examination for evaluating the gastrointestinal tract. However, its diagnostic yield for detecting gastric lesions is suboptimal. Convolutional neural networks (CNNs) are artificial intelligence models with great performance for image analysis. Nonetheless, their role in gastric evaluation by wireless CE (WCE) has not been explored. METHODS: Our group developed a CNN-based algorithm for the automatic classification of pleomorphic gastric lesions, including vascular lesions (angiectasia, varices, and red spots), protruding lesions, ulcers, and erosions. A total of 12,918 gastric images from 3 different CE devices (PillCam Crohn's; PillCam SB3; OMOM HD CE system) were used from the construction of the CNN: 1,407 from protruding lesions; 994 from ulcers and erosions; 822 from vascular lesions; and 2,851 from hematic residues and the remaining images from normal mucosa. The images were divided into a training (split for three-fold cross-validation) and validation data set. The model's output was compared with a consensus classification by 2 WCE-experienced gastroenterologists. The network's performance was evaluated by its sensitivity, specificity, accuracy, positive predictive value and negative predictive value, and area under the precision-recall curve. RESULTS: The trained CNN had a 97.4% sensitivity; 95.9% specificity; and positive predictive value and negative predictive value of 95.0% and 97.8%, respectively, for gastric lesions, with 96.6% overall accuracy. The CNN had an image processing time of 115 images per second. DISCUSSION: Our group developed, for the first time, a CNN capable of automatically detecting pleomorphic gastric lesions in both small bowel and colon CE devices.
Dados da publicação
- ISSN/ISSNe:
- 2155-384X, 2155-384X
- Tipo:
- Article
- Páginas:
- 609-
- Link para outro recurso:
- www.scopus.com
Clinical and Translational Gastroenterology Nature Publishing Group
Citações Recebidas na Web of Science: 6
Citações Recebidas na Scopus: 4
Documentos
- Não há documentos
Filiações
Keywords
- artificial intelligence; capsule endoscopy; deep learning
Proyectos asociados
The contribution of endoscopic ultrasound and biomarkers in the management of pancreatic adenocarcinoma and its precursor lesions.
Investigador Principal: Manuel Guilherme Gonçalves Macedo
Estudo Clínico Académico . 2023
Noninvasive serum biomarkers of portal hypertension in liver cirrhosis
Investigador Principal: Manuel Guilherme Gonçalves Macedo
Estudo Clínico Académico . 2023
Otimização do rendimento da colangiopancreatografia retrógrada endoscópica na avaliação das estenoses pancreato-biliares indeterminadas
Investigador Principal: Manuel Guilherme Gonçalves Macedo
Estudo Clínico Académico . 2023
Endoscopic Treatment Of Upper Gastrointestinal Postsurgical Leaks
Investigador Principal: Manuel Guilherme Gonçalves Macedo
Estudo Clínico Académico . 2023
Citar a publicação
Mascarenhas M,Mendes F,Ribeiro T,Afonso J,Cardoso P,Martins M,Cardoso H,Andrade P,Ferreira J,Saraiva MM,Macedo G. Deep Learning and Minimally Invasive Endoscopy: Automatic Classification of Pleomorphic Gastric Lesions in Capsule Endoscopy. Clin Transl Gastroenterol. 2023. 14. (10):p. 609-609. IF:3,600. (2).
