Scholarlink

Background <p>Diabetic retinopathy (DR) is a critical complication of diabetes, leading to global vision impairment. Early detection and precise classification of DR are essential for effective intervention and improved patient care. However, early-stage DR often shows few symptoms, making early identification and treatment challenging.</p> Objective <p>Manual diagnosis of DR from fundus images is time-consuming, costly, and prone to misdiagnosis compared to computer-aided diagnosis systems.</p> Methods <p>This paper presents the development and evaluation of advanced deep learning models for the detection and classification of DR using both binary and multiclass classification approaches.</p> Results <p>We employed deep learning techniques on fundus image datasets to perform both 2-class and 5-class classifications. The models were trained and tested with the support of ophthalmologist surgeons at the Eye Hospital of Biskra, Algeria.</p> Conclusions <p>The results demonstrated significant efficacy, garnering positive feedback from hospital physicians. Our proposed model achieves 98.7% accuracy for 2-class classification and 96.2% accuracy for 5-class classification in recognizing and classifying the severity levels of DR, including no DR, mild DR, moderate DR, severe DR and proliferative DR.</p>

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

Deep learning for early detection and classification of diabetic retinopathy using fundus images

  • 期刊论文

  • 发表日期：

    2025年7月10日

查看全文
  • Ahmed Aloui,
  • Meftah Zouai,
  • Fayez Bouhitem,
  • Okba Kazar

摘要

Background

Diabetic retinopathy (DR) is a critical complication of diabetes, leading to global vision impairment. Early detection and precise classification of DR are essential for effective intervention and improved patient care. However, early-stage DR often shows few symptoms, making early identification and treatment challenging.

Objective

Manual diagnosis of DR from fundus images is time-consuming, costly, and prone to misdiagnosis compared to computer-aided diagnosis systems.

Methods

This paper presents the development and evaluation of advanced deep learning models for the detection and classification of DR using both binary and multiclass classification approaches.

Results

We employed deep learning techniques on fundus image datasets to perform both 2-class and 5-class classifications. The models were trained and tested with the support of ophthalmologist surgeons at the Eye Hospital of Biskra, Algeria.

Conclusions

The results demonstrated significant efficacy, garnering positive feedback from hospital physicians. Our proposed model achieves 98.7% accuracy for 2-class classification and 96.2% accuracy for 5-class classification in recognizing and classifying the severity levels of DR, including no DR, mild DR, moderate DR, severe DR and proliferative DR.