Scholarlink

Diabetic retinopathy (DR) is a major cause of vision loss, requiring early detection for effective management. This paper presents EyeSight, a non-invasive system that uses pupillometry and an ensemble of deep learning models—ResNet, DenseNet, and EfficientNet—to detect DR. By analyzing pupillary light reflex (PLR) data, EyeSight identifies various DR stages with improved accuracy and sensitivity. The ensemble model enhances performance by leveraging diverse feature extraction capabilities, providing a cost-effective and accessible solution for large-scale DR screening.

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

EyeSight: Integrative AI for Non-invasive Diabetic Retinopathy Detection Using Pupillometry and Ensemble Deep Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • H. Lakshanya,
  • R. Preethi,
  • C. A. Subasini

摘要

Diabetic retinopathy (DR) is a major cause of vision loss, requiring early detection for effective management. This paper presents EyeSight, a non-invasive system that uses pupillometry and an ensemble of deep learning models—ResNet, DenseNet, and EfficientNet—to detect DR. By analyzing pupillary light reflex (PLR) data, EyeSight identifies various DR stages with improved accuracy and sensitivity. The ensemble model enhances performance by leveraging diverse feature extraction capabilities, providing a cost-effective and accessible solution for large-scale DR screening.