Year: 2022
Type: preprint
Abstract: Eyesight is one of the most vital senses. In the year 2021, about 2.2 billion people will have vision impairment. Amongst them, 93 million were due to cataracts. In this paper, we have merged different image processing techniques and deep learning networks to diagnose and differentiate between various types of cataracts. The conventional Convolution Neural Network (CNN), in conjunction with support vector machines (SVM), classifies nuclear, cortical spoking, and capsular cataract eyes. The proposed method was successful in accurately classifying the two classes with an accuracy of 85.71%, while for a three-class classification, 83.33% was the maximum accuracy achieved.
Source: Research Square
Authors: Tanjemoon Ankur, Md Kamrul Hasan Foysal, Peter Ho, Jo Woon Chong, Bipasha Kundu
Institutions: Texas Tech University, Rochester Institute of Technology
Language: English
Topic: Retinal Imaging and Analysis
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W4302024740