Cataract Classification and Gradation From Retinal Fundus Image Using Ensemble Learning Algorithm

Abstract

Visual impairment, such as cataract, if not detected and treated early, might lead to blindness. Cataract detection still takes a long time and is quite subjective, depending on ophthalmologist's preference. To expedite cataract screening procedure, an automated cataract detection system should be developed. Fundus image analysis for automatic categorization and grading of cataracts has the potential to reduce the burden of competent ophthalmologists while also assisting cataract patients in learning about their diseases and getting treatment suggestions. The optic disc and blood vessel data play a significant role in the detection and grading of cataracts. Normal, mild, moderate, and severe cataract stages are differentiated based on texture, colour, size, and contrast. Classification and severity rating are carried out using random forest classifier, an ensemble machine-learning method. The accuracy discovered is equivalent to prior study in the literature. This study is expected to help doctors detect cataracts early and prevent cataract-related suffering.