According to multiple authoritative authorities, including the World Health
Organization, vision-related impairments and disorders are becoming a
significant issue. According to a recent report, one of the leading causes of
irreversible blindness in persons over the age of 50 is delayed cataract
treatment. A cataract is a cloudy spot in the eye's lens that causes visual
loss. Cataracts often develop slowly and consequently result in difficulty in
driving, reading, and even recognizing faces. This necessitates the development
of rapid and dependable diagnosis and treatment solutions for ocular illnesses.
Previously, such visual illness diagnosis were done manually, which was
time-consuming and prone to human mistake. However, as technology advances,
automated, computer-based methods that decrease both time and human labor while
producing trustworthy results are now accessible. In this study, we developed a
CNN-LSTM-based model architecture with the goal of creating a low-cost
diagnostic system that can classify normal and cataractous cases of ocular
disease from fundus images. The proposed model was trained on the publicly
available ODIR dataset, which included fundus images of patients' left and
right eyes. The suggested architecture outperformed previous systems with a
state-of-the-art 97.53% accuracy.

本研究利用 CNN-LSTM 模型结构从眼底图像中诊断出正常或白内障眼病例，该模型在 ODIR 数据集上测试的准确率高达 97.53％，由此有望为眼科疾病的诊断提供快速和可靠的解决方案。