RT info:eu-repo/semantics/article
T1 Entropy rate superpixel classification for automatic red lesion detection in fundus images
A1 Romero Oraa, Roberto
A1 Jiménez García, Jorge
A1 García Gadañón, María
A1 López Gálvez, María Isabel
A1 Oraá Pérez, Javier
A1 Hornero Sánchez, Roberto
K1 Diabetic retinopathy
K1 Retinopatía diabética
K1 Entropy
K1 Entropía
AB Diabetic retinopathy (DR) is the main cause of blindness in the working-age population in developed countries. Digital color fundus images can be analyzed to detect lesions for large-scale screening. Thereby, automated systems can be helpful in the diagnosis of this disease. The aim of this study was to develop a method to automatically detect red lesions (RLs) in retinal images, including hemorrhages and microaneurysms. These signs are the earliest indicators of DR. Firstly, we performed a novel preprocessing stage to normalize the inter-image and intra-image appearance and enhance the retinal structures. Secondly, the Entropy Rate Superpixel method was used to segment the potential RL candidates. Then, we reduced superpixel candidates by combining inaccurately fragmented regions within structures. Finally, we classified the superpixels using a multilayer perceptron neural network. The used database contained 564 fundus images. The DB was randomly divided into a training set and a test set. Results on the test set were measured using two different criteria. With a pixel-based criterion, we obtained a sensitivity of 81.43% and a positive predictive value of 86.59%. Using an image-based criterion, we reached 84.04% sensitivity, 85.00% specificity and 84.45% accuracy. The algorithm was also evaluated on the DiaretDB1 database. The proposed method could help specialists in the detection of RLs in diabetic patients.
PB MDPI
SN 1099-4300
YR 2019
FD 2019
LK https://uvadoc.uva.es/handle/10324/56010
UL https://uvadoc.uva.es/handle/10324/56010
LA eng
NO Entropy, 2019, vol. 21, n. 4, 417
NO Producción Científica
DS UVaDOC
RD 22-nov-2024