Scholarlink

Diabetic retinopathy (DR) can lead to blindness by damaging the retina’s blood vessels and neurons. Early detection is crucial, but manual analysis of retinal fundus images by ophthalmologists is time-consuming and expensive. An automated system utilizing artificial intelligence (AI) proves to be more efficient and accurate in DR detection. The proposed model compares image enhancement algorithms (AHE and CLAHE) and incorporates GAN data augmentation for improved training. It integrates the DenseNet-201 deep learning model and a regression model for evaluation, demonstrating enhanced efficiency and accuracy, contributing to improved outcomes and reduced healthcare burden.

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

Diabetic Retinopathy Diagnosis Using Image Processing and Deep Learning Methods

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • V. Divya Raj,
  • Addepalli Sai Sriyam,
  • Akurathi Meghana,
  • Harshini Vutukuri,
  • Sandhya Thota

摘要

Diabetic retinopathy (DR) can lead to blindness by damaging the retina’s blood vessels and neurons. Early detection is crucial, but manual analysis of retinal fundus images by ophthalmologists is time-consuming and expensive. An automated system utilizing artificial intelligence (AI) proves to be more efficient and accurate in DR detection. The proposed model compares image enhancement algorithms (AHE and CLAHE) and incorporates GAN data augmentation for improved training. It integrates the DenseNet-201 deep learning model and a regression model for evaluation, demonstrating enhanced efficiency and accuracy, contributing to improved outcomes and reduced healthcare burden.