Your browser doesn't support javascript.
loading
Using a Deep Learning Model to Address Interobserver Variability in the Evaluation of Ulcerative Colitis (UC) Severity.
Kim, Jeong-Heon; Choe, A Reum; Park, Yehyun; Song, Eun-Mi; Byun, Ju-Ran; Cho, Min-Sun; Yoo, Youngeun; Lee, Rena; Kim, Jin-Sung; Ahn, So-Hyun; Jung, Sung-Ae.
Afiliación
  • Kim JH; Department of Medicine, Yonsei University College of Medicine, Seoul 03722, Republic of Korea.
  • Choe AR; Medical Physics and Biomedical Engineering Lab (MPBEL), Yonsei University College of Medicine, Seoul 03722, Republic of Korea.
  • Park Y; Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul 03722, Republic of Korea.
  • Song EM; Department of Internal Medicine, Ewha Womans University College of Medicine, Seoul 03760, Republic of Korea.
  • Byun JR; Department of Internal Medicine, Ewha Womans University College of Medicine, Seoul 03760, Republic of Korea.
  • Cho MS; Department of Internal Medicine, Ewha Womans University College of Medicine, Seoul 03760, Republic of Korea.
  • Yoo Y; Department of Internal Medicine, Ewha Womans University College of Medicine, Seoul 03760, Republic of Korea.
  • Lee R; Department of Pathology, Ewha Womans University College of Medicine, Seoul 03760, Republic of Korea.
  • Kim JS; Department of Pathology, Ewha Womans University College of Medicine, Seoul 03760, Republic of Korea.
  • Ahn SH; Department of Bioengineering, Ewha Womans University College of Medicine, Seoul 03760, Republic of Korea.
  • Jung SA; Department of Medicine, Yonsei University College of Medicine, Seoul 03722, Republic of Korea.
J Pers Med ; 13(11)2023 Nov 08.
Article en En | MEDLINE | ID: mdl-38003899
The use of endoscopic images for the accurate assessment of ulcerative colitis (UC) severity is crucial to determining appropriate treatment. However, experts may interpret these images differently, leading to inconsistent diagnoses. This study aims to address the issue by introducing a standardization method based on deep learning. We collected 254 rectal endoscopic images from 115 patients with UC, and five experts in endoscopic image interpretation assigned classification labels based on the Ulcerative Colitis Endoscopic Index of Severity (UCEIS) scoring system. Interobserver variance analysis of the five experts yielded an intraclass correlation coefficient of 0.8431 for UCEIS scores and a kappa coefficient of 0.4916 when the UCEIS scores were transformed into UC severity measures. To establish a consensus, we created a model that considered only the images and labels on which more than half of the experts agreed. This consensus model achieved an accuracy of 0.94 when tested with 50 images. Compared with models trained from individual expert labels, the consensus model demonstrated the most reliable prediction results.
Palabras clave

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: J Pers Med Año: 2023 Tipo del documento: Article Pais de publicación: Suiza

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: J Pers Med Año: 2023 Tipo del documento: Article Pais de publicación: Suiza