Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep Learning-Based Detection of Referable Diabetic Retinopathy and Macular Edema Using Ultra-Widefield Fundus Imaging

Philippe Zhang, Pierre-Henri Conze, Mathieu Lamard, Gwenolé Quellec, Mostafa El Habib Daho

TL;DR

Results indicate that deep learning can significantly aid in the automated analysis of UWF images, potentially improving the efficiency and accuracy of DR and DME detection in clinical settings.

Abstract

Diabetic retinopathy and diabetic macular edema are significant complications of diabetes that can lead to vision loss. Early detection through ultra-widefield fundus imaging enhances patient outcomes but presents challenges in image quality and analysis scale. This paper introduces deep learning solutions for automated UWF image analysis within the framework of the MICCAI 2024 UWF4DR challenge. We detail methods and results across three tasks: image quality assessment, detection of referable DR, and identification of DME. Employing advanced convolutional neural network architectures such as EfficientNet and ResNet, along with preprocessing and augmentation strategies, our models demonstrate robust performance in these tasks. Results indicate that deep learning can significantly aid in the automated analysis of UWF images, potentially improving the efficiency and accuracy of DR and DME detection in clinical settings.

Deep Learning-Based Detection of Referable Diabetic Retinopathy and Macular Edema Using Ultra-Widefield Fundus Imaging

TL;DR

Results indicate that deep learning can significantly aid in the automated analysis of UWF images, potentially improving the efficiency and accuracy of DR and DME detection in clinical settings.

Abstract

Diabetic retinopathy and diabetic macular edema are significant complications of diabetes that can lead to vision loss. Early detection through ultra-widefield fundus imaging enhances patient outcomes but presents challenges in image quality and analysis scale. This paper introduces deep learning solutions for automated UWF image analysis within the framework of the MICCAI 2024 UWF4DR challenge. We detail methods and results across three tasks: image quality assessment, detection of referable DR, and identification of DME. Employing advanced convolutional neural network architectures such as EfficientNet and ResNet, along with preprocessing and augmentation strategies, our models demonstrate robust performance in these tasks. Results indicate that deep learning can significantly aid in the automated analysis of UWF images, potentially improving the efficiency and accuracy of DR and DME detection in clinical settings.
Paper Structure (28 sections, 2 figures, 3 tables)

This paper contains 28 sections, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Task 1: Image Quality Assessment
  3. Dataset
  4. Materials and Methods
  5. Preprocessing
  6. Model Architecture
  7. Training
  8. Ensemble Prediction
  9. Results and Discussion
  10. Discussion
  11. Task 2: Identification of Referable Diabetic Retinopathy
  12. Dataset
  13. Materials and Methods
  14. Preprocessing
  15. Model Architecture
  16. ...and 13 more sections

Figures (2)

  • Figure 1: Samples from the quality assessment dataset: (A) good quality, (B) bad quality.
  • Figure 4: Examples from the RDR dataset: (A) Images with referable DR, (B) Images without referable DR, (1) Images from the UWF4DR dataset, (2) Image from the DeepDRiD dataset.