Cataract Eye Prediction using Machine Learning

Abstract

Humans, being visually oriented, witness the happenings in the surroundings with the help of eyes. In the current scenario, blindness, and visual impairment has become a major and ubiquitous health problem. Although new technologies are rapidly progressing, visual impairment remains a noteworthy problem for worldwide healthcare systems. One of such problems is Cataract. Cataracts causing poor vision may also result in an increased risk of falling and depression. Earlier, it was usual among old age people, but now childhood cataract has become an important cause of blindness and severe visual impairment in children. Existing studies have been done mostly on Fundus image datasets for automatic detection of cataract and grading using a predefined feature set. The challenge is to detect cataract using the normal lens images at an early stage thus allowing people to test for cataract themselves. This would rather ensure that people belonging to remote areas need not reach out to ophthalmologists, just to check whether the person is facing a cataract problem or not. This paper uses CNN models taking normal lens image input for detection of cataract problems.