Scholarlink

Eye diseases have become a serious global issue, especially in developing countries where access to technology and financial resources is limited. These conditions vary in their causes, symptoms, and severity, but many share the common threat of irreversible vision loss if not diagnosed promptly. Accurate diagnosis of eye diseases is essential for preventing irreversible vision damage. The study explains the potential of Convolutional Neural Networks (CNNs) for the classification of eye diseases like diabetic retinopathy (DR), cataracts and glaucoma using AlexNet, Vgg, GoogleNet, RelayNet. This study established an architecture RetiLayNet and the findings reveal that the RetiLayNet architecture got a commendable performance, with an accuracy of 85.95%, a precision of 89.89%, and a recall of 83.17%. This research could greatly advance ophthalmology by utilizing AI to enhance the identification and classification of eye conditions, which in turn could help lower the worldwide incidence of vision impairment.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Automated Diagnosis of Eye Diseases Using Convolutional Neural Networks: A Study of CNN Architectures with Emphasis on the Enhanced RetiLayNet for Early Detection of Vision Impairment

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • C. A. Aparna,
  • B. R. Manju

摘要

Eye diseases have become a serious global issue, especially in developing countries where access to technology and financial resources is limited. These conditions vary in their causes, symptoms, and severity, but many share the common threat of irreversible vision loss if not diagnosed promptly. Accurate diagnosis of eye diseases is essential for preventing irreversible vision damage. The study explains the potential of Convolutional Neural Networks (CNNs) for the classification of eye diseases like diabetic retinopathy (DR), cataracts and glaucoma using AlexNet, Vgg, GoogleNet, RelayNet. This study established an architecture RetiLayNet and the findings reveal that the RetiLayNet architecture got a commendable performance, with an accuracy of 85.95%, a precision of 89.89%, and a recall of 83.17%. This research could greatly advance ophthalmology by utilizing AI to enhance the identification and classification of eye conditions, which in turn could help lower the worldwide incidence of vision impairment.