Open AccessAutomated Detection of Microaneurysmsusing Probabilistic Cascaded Neural Network
Author(s) -
J Jeyapriya,
K. S. Umadevi,
R. Jagadeesh Kannan
Publication year - 2018
Publication title -
indonesian journal of electrical engineering and computer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.241
H-Index - 17
eISSN - 2502-4760
pISSN - 2502-4752
DOI - 10.11591/ijeecs.v11.i3.pp1083-1093
Subject(s) - fundus (uterus) , probabilistic logic , artificial intelligence , computer science , convolution (computer science) , convolutional neural network , artificial neural network , computer vision , pattern recognition (psychology) , retinal , human eye , diabetic retinopathy , feature extraction , optometry , ophthalmology , medicine , diabetes mellitus , endocrinology
The diagnosing features for Diabetic Retinopathy (DR) comprises of features occurring in and around the regions of blood vessel zone which will result into exudes, hemorrhages, microaneurysms and generation of textures on the albumen region of eye balls. In this study we presenta probabilistic convolution neural network based algorithms, utilized for the extraction of such features from the retinal images of patient’s eyeballs. The classifications proficiency of various DR systems is tabulated and examined. The majority of the reported systems are profoundly advanced regarding the analyzed fundus images is catching up to the human ophthalmologist’s characterization capacities.