RT Journal Article
T1 Deep Residual Transfer Learning for Automatic Diabetic Retinopathy Grading.
A1 Martínez-Murcia, Francisco Jesús
A1 Ortiz-García, Andrés
A1 Ramírez-Aguilar, Francisco Javier
A1 Górriz-Sáez, Juan Manuel
A1 Cruz, Ricardo
K1 Retinopatía diabética
K1 Redes neuronales (Informática)
K1 Diagnóstico por imagen
K1 Sistemas autoorganizativos
AB Evaluation and diagnosis of retina pathology is usually made via the analysis of different image modalities that allow to explore its structure. The most popular retina image method is retinography, a technique that displays the fundus of the eye, including the retina and other structures. Retinography is the most common imaging method to diagnose retina diseases such as Diabetic Retinopathy (DB) or Macular Edema (ME). However, retinography evaluation to score the image according to the disease grade presents difficulties due to differences in contrast, brightness and the presence of artifacts. Therefore, it is mainly done via manual analysis; a time consuming task that requires a trained clinician to examine and evaluate the images. In this paper, we present a computer aided diagnosis tool that takes advantage of the performance provided by deep learning architectures for image analysis. Our proposal is based on a deep residual convolutional neural network for extracting discriminatory features with no prior complex image transformations to enhance the image quality or to highlight specific structures. Moreover, we used the transfer learning paradigm to reuse layers from deep neural networks previously trained on the ImageNet dataset, under the hypothesis that first layers capture abstract features than can be reused for different problems. Experiments using different convolutional architectures have been carried out and their performance has been evaluated on the MESSIDOR database using cross-validation. Best results were found using a ResNet50-based architecture, showing an AUC of 0.93 for grades 0 + 1, AUC of 0.81 for grade 2 and AUC of 0.92 for grade 3 labelling, as well as AUCs higher than 0.97 when considering a binary classification problem (grades 0 vs 3).
PB Elsevier
YR 2021
FD 2021-09-10
LK https://hdl.handle.net/10630/28094
UL https://hdl.handle.net/10630/28094
LA eng
NO Martinez-Murcia, Francisco & Ortiz, Andrés & Ramírez, Javier & Gorriz, Juan & Cruz, Ricardo. (2020). Deep residual transfer learning for automatic diagnosis and grading of diabetic retinopathy. Neurocomputing. 452. 10.1016/j.neucom.2020.04.148.
NO This work was partly supported by the MINECO/FEDER under TEC2015-64718-R, RTI2018-098913-B-I00,PSI2015-65848-R and PGC2018-098813-B-C32 projects. We gratefully acknowledge the support of NVIDIA Cor poration with the donation of one of the GPUs used for this research. Work by F.J.M.M. was supported by theMICINN “Juan de la Cierva - Formacion” Fellowship.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 20 ene 2026