Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Dual Branch Deep Learning Network for Detection and Stage Grading of Diabetic Retinopathy

Hossein Shakibania, Sina Raoufi, Behnam Pourafkham, Hassan Khotanlou, Muharram Mansoorizadeh

TL;DR

This paper introduces a deep learning method for the detection and stage grading of diabetic retinopathy, using a single fundus retinal image, offering significant potential to enhance clinical decision-making and patient care.

Abstract

Diabetic retinopathy is a severe complication of diabetes that can lead to permanent blindness if not treated promptly. Early and accurate diagnosis of the disease is essential for successful treatment. This paper introduces a deep learning method for the detection and stage grading of diabetic retinopathy, using a single fundus retinal image. Our model utilizes transfer learning, employing two state-of-the-art pre-trained models as feature extractors and fine-tuning them on a new dataset. The proposed model is trained on a large multi-center dataset, including the APTOS 2019 dataset, obtained from publicly available sources. It achieves remarkable performance in diabetic retinopathy detection and stage classification on the APTOS 2019, outperforming the established literature. For binary classification, the proposed approach achieves an accuracy of 98.50, a sensitivity of 99.46, and a specificity of 97.51. In stage grading, it achieves a quadratic weighted kappa of 93.00, an accuracy of 89.60, a sensitivity of 89.60, and a specificity of 97.72. The proposed approach serves as a reliable screening and stage grading tool for diabetic retinopathy, offering significant potential to enhance clinical decision-making and patient care.

Dual Branch Deep Learning Network for Detection and Stage Grading of Diabetic Retinopathy

TL;DR

This paper introduces a deep learning method for the detection and stage grading of diabetic retinopathy, using a single fundus retinal image, offering significant potential to enhance clinical decision-making and patient care.

Abstract

Diabetic retinopathy is a severe complication of diabetes that can lead to permanent blindness if not treated promptly. Early and accurate diagnosis of the disease is essential for successful treatment. This paper introduces a deep learning method for the detection and stage grading of diabetic retinopathy, using a single fundus retinal image. Our model utilizes transfer learning, employing two state-of-the-art pre-trained models as feature extractors and fine-tuning them on a new dataset. The proposed model is trained on a large multi-center dataset, including the APTOS 2019 dataset, obtained from publicly available sources. It achieves remarkable performance in diabetic retinopathy detection and stage classification on the APTOS 2019, outperforming the established literature. For binary classification, the proposed approach achieves an accuracy of 98.50, a sensitivity of 99.46, and a specificity of 97.51. In stage grading, it achieves a quadratic weighted kappa of 93.00, an accuracy of 89.60, a sensitivity of 89.60, and a specificity of 97.72. The proposed approach serves as a reliable screening and stage grading tool for diabetic retinopathy, offering significant potential to enhance clinical decision-making and patient care.
Paper Structure (25 sections, 7 equations, 13 figures, 5 tables)

This paper contains 25 sections, 7 equations, 13 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Literature review
  3. Binary classification of DR
  4. Multi-class classification of DR
  5. Binary and multi-class classification of DR
  6. Materials and methods
  7. Dataset
  8. Proposed approach
  9. Pre-trained models
  10. ResNet50
  11. Xception
  12. DenseNet121
  13. EfficientNetB0
  14. Preprocessing
  15. Data augmentation
  16. ...and 10 more sections

Figures (13)

  • Figure 1: Four stages of DR: (a) Mild, (b) Moderate, (c) Severe, and (d) PDR obtained from APTOS 2019 dataset.
  • Figure 2: Fundus image with various lesions for DR classification.
  • Figure 3: The distribution of classes in APTOS 2019, IDRiD, and Messidor-2 datasets.
  • Figure 4: Proposed framework for detection and stage grading of diabetic retinopathy.
  • Figure 5: Training and test accuracy of pre-trained models with APTOS 2019 dataset for DR stage grading.
  • ...and 8 more figures