A deep learning model for classification of diabetic retinopathy in eye fundus images based on retinal lesion detection

Melissa DelaPava, Hernán Ríos, Francisco J. Rodríguez, Oscar J. Perdomo, Fabio A. González

Resultado de la investigación: Capítulo en Libro/Reporte/ConferenciaContribución a la conferencia

Resumen

Diabetic retinopathy (DR) is the result of a complication of diabetes affecting the retina. It can cause blindness, if left undiagnosed and untreated. An ophthalmologist performs the diagnosis by screening each patient and analyzing the retinal lesions via ocular imaging. In practice, such analysis is time-consuming and cumbersome to perform. This paper presents a model for automatic DR classification on eye fundus images. The approach identifies the main ocular lesions related to DR and subsequently diagnoses the illness. The proposed method follows the same workflow as the clinicians, providing information that can be interpreted clinically to support the prediction. A subset of the kaggle EyePACS and the Messidor-2 datasets, labeled with ocular lesions, is made publicly available. The kaggle EyePACS subset is used as training set and the Messidor-2 as a test set for lesions and DR classification models. For DR diagnosis, our model has an area-under-the-curve, sensitivity, and specificity of 0:948, 0:886, and 0:875, respectively, which competes with state-of-the-art approaches.

Idioma originalInglés estadounidense
Título de la publicación alojada17th International Symposium on Medical Information Processing and Analysis
EditoresEduardo Romero, Eduardo Tavares Costa, Jorge Brieva, Leticia Rittner, Marius George Linguraru, Natasha Lepore
EditorialSPIE
ISBN (versión digital)9781510650527
DOI
EstadoPublicada - 2021
Evento17th International Symposium on Medical Information Processing and Analysis - Campinas, Brasil
Duración: nov. 17 2021nov. 19 2021

Serie de la publicación

NombreProceedings of SPIE - The International Society for Optical Engineering
Volumen12088
ISSN (versión impresa)0277-786X
ISSN (versión digital)1996-756X

Conferencia

Conferencia17th International Symposium on Medical Information Processing and Analysis
País/TerritorioBrasil
CiudadCampinas
Período11/17/2111/19/21

Áreas temáticas de ASJC Scopus

  • Materiales electrónicos, ópticos y magnéticos
  • Física de la materia condensada
  • Informática aplicada
  • Matemáticas aplicadas
  • Ingeniería eléctrica y electrónica

Huella

Profundice en los temas de investigación de 'A deep learning model for classification of diabetic retinopathy in eye fundus images based on retinal lesion detection'. En conjunto forman una huella única.

Citar esto