Machine Learning on Cataracts Classification Using SqueezeNet

Cataracts is a serious eye disease, affecting over 20 million people worldwide. It is the clouding of the lens, which blocks the light to go through the lens and project on the retina [1]. As a result, the nerve cannot transfer the whole image to the brain, leading to blindness. A vast majority of cataracts patients are people who are over 50 years old. To classify different areas of cataracts in lens, we use supervised training of convolutional neural network to train 420 images of cataracts on the lens taken from slit-lamps. The experiment can make the future of classifying cataracts more easily and ophthalmologists can apply operations to different categories of cataracts within a shorter time to cure patients with cataracts. For those people in the countryside, even not so experienced doctors can take the photo of lens and use the program to classify cataracts correctly.