Automated Detection of Microaneurysmsusing Probabilistic Cascaded Neural Network

Jeyapriya J (Vellore Institute of Technology)
K S Umadevi (Vellore Institute of Technology)
R Jagadeesh Kannan (Vellore Institute of Technology)

Indonesian Journal of Electrical Engineering and Computer Science
Vol 11, No 3: September 2018

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.