Diabetic retinopathy image classification method based on GreenBen data augmentation

TL;DR

This paper introduces GreenBen, a novel data augmentation technique for diabetic retinopathy image classification, which enhances model accuracy by improving data quality and incorporating joint DR and DME classification using multi-task learning.

Contribution

The paper presents GreenBen, a new data augmentation method based on green channel enhancement, and a joint classification framework for DR and DME using multi-task learning and attention modules.

Findings

GreenBen significantly improves classification accuracy by 10%.

The method achieves state-of-the-art results on three datasets.

GreenBen enhances both ResNet50 and Swin Transformer models.

Abstract

For the diagnosis of diabetes retinopathy (DR) images, this paper proposes a classification method based on artificial intelligence. The core lies in a new data augmentation method, GreenBen, which first extracts the green channel grayscale image from the retinal image and then performs Ben enhancement. Considering that diabetes macular edema (DME) is a complication closely related to DR, this paper constructs a joint classification framework of DR and DME based on multi task learning and attention module, and uses GreenBen to enhance its data to reduce the difference of DR images and improve the accuracy of model classification. We conducted extensive experiments on three publicly available datasets, and our method achieved the best results. For GreenBen, whether based on the ResNet50 network or the Swin Transformer network, whether for individual classification or joint DME classification, compared with other data augmentation methods, GreenBen achieved stable and significant improvements in DR classification results, with an accuracy increase of 10%.