Light-weight Deep Learning Model for Cataract Detection using Novel Activation Function

Abstract

In cataracts, the natural lens behind the iris and pupil is cloudy, which causes light passing through it to be distorted or blocked, causing blurry or dim vision. About 50% of all cases of blindness worldwide is caused by cataract, according to WHO and the National Library of Medicine. A timely diagnosis of cataracts can help prevent vision loss and other disease-related complications. Several recent developments in machine learning have significantly impacted medical science. However, most existing approaches for cataract detection are based on traditional machine learning techniques. There have been a few attempts to use deep learning in recent years; the models have delivered decent outcomes but require much computational power. Reducing ophthalmologists' time can improve patient outcomes, increase access to care, lower costs, address workforce shortages, and improve healthcare efficiency. It allows ophthalmologists to see more patients and provide more accurate, timely diagnoses and treatments. Using lightweight deep learning algorithms, this paper proposes a solution that delivers rapid and precise results without requiring high-end hardware. A novel activation function is also proposed that significantly improved the performance. The proposed model is a lightweight one that achieved 95.8% accuracy using only 16,874 parameters. © 2023 IEEE.