4Automatic Retinopathic Diabetic Detection: Data Analyses, Approaches and Assessment Measures Using Deep Learning

Rinesh S.1*, Mahdi Ismael Omar1, Thamaraiselvi K.2, V. Karthick3 and Vigneshwar Manoharan4

1Department of Computer Science, Jigjiga University, Somali Region, Ethiopia

2Department of Computer Science, Malla Reddy College of Engineering, Hyderabad, Telangana, India

3Department of Computer Science and Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, Tamil Nadu, India

4R & D and Academic Initiatives, Cybase Technologies, Coimbatore, Tamil Nadu, India

Abstract

The major cause of vision loss and blindness, diabetic retinal disease, affects millions of individuals globally. Although optical coherence tomography and fluorescein angiography are two well-known screening methods for identifying diseases, most people are unaware of them and do not have them performed when they should. The prevention of eyesight loss, which results from untreated diabetes mellitus among patients for an extended length of time, is greatly aided by early disease detection. The diabetic retinopathy dataset has been subjected to a number of machine learning and deep learning algorithms for classification and disease prediction, however most of them overlooked the element of data preprocessing and dimensionality reduction, leading to biased findings. A dataset on diabetes retinopathy was used in the current investigation; it was obtained ...

Get Handbook of Computational Sciences now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.