Open AccessImproving the Curvelet Saliency and Deep Convolutional Neural Networks for Diabetic Retinopathy Classification in Fundus Images
Author(s) -
Vo Thi Hong Tuyet,
Nguyen Thanh Binh,
D. T. Tin
Publication year - 2022
Publication title -
engineering, technology and applied science research/engineering, technology and applied science research
Language(s) - English
Resource type - Journals
eISSN - 2241-4487
pISSN - 1792-8036
DOI - 10.48084/etasr.4679
Subject(s) - artificial intelligence , convolutional neural network , fundus (uterus) , computer science , diabetic retinopathy , curvelet , pattern recognition (psychology) , segmentation , jaccard index , pixel , computer vision , retinal , ophthalmology , medicine , wavelet , wavelet transform , diabetes mellitus , endocrinology
Retinal vessel images give a wide range of the abnormal pixels of patients. Therefore, classifying the diseases depending on fundus images is a popular approach. This paper proposes a new method to classify diabetic retinopathy in retinal blood vessel images based on curvelet saliency for segmentation. Our approach includes three periods: pre-processing of the quality of input images, calculating the saliency map based on curvelet coefficients, and classifying VGG16. To evaluate the results of the proposed method STARE and HRF datasets are used for testing with the Jaccard Index. The accuracy of the proposed method is about 98.42% and 97.96% with STARE and HRF datasets respectively.