Saved in:
Bibliographic Details
Main Authors: Boulaabi, Meher, Gader, Takwa Ben Aïcha, Echi, Afef Kacem, Bouraoui, Zied
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.15317
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916701480681472
author Boulaabi, Meher
Gader, Takwa Ben Aïcha
Echi, Afef Kacem
Bouraoui, Zied
author_facet Boulaabi, Meher
Gader, Takwa Ben Aïcha
Echi, Afef Kacem
Bouraoui, Zied
contents Diabetic retinopathy (DR) is a leading cause of blindness worldwide, underscoring the importance of early detection for effective treatment. However, automated DR classification remains challenging due to variations in image quality, class imbalance, and pixel-level similarities that hinder model training. To address these issues, we propose a robust preprocessing pipeline incorporating image cropping, Contrast-Limited Adaptive Histogram Equalization (CLAHE), and targeted data augmentation to improve model generalization and resilience. Our approach leverages the Swin Transformer, which utilizes hierarchical token processing and shifted window attention to efficiently capture fine-grained features while maintaining linear computational complexity. We validate our method on the Aptos and IDRiD datasets for multi-class DR classification, achieving accuracy rates of 89.65% and 97.40%, respectively. These results demonstrate the effectiveness of our model, particularly in detecting early-stage DR, highlighting its potential for improving automated retinal screening in clinical settings.
format Preprint
id arxiv_https___arxiv_org_abs_2504_15317
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing DR Classification with Swin Transformer and Shifted Window Attention
Boulaabi, Meher
Gader, Takwa Ben Aïcha
Echi, Afef Kacem
Bouraoui, Zied
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Diabetic retinopathy (DR) is a leading cause of blindness worldwide, underscoring the importance of early detection for effective treatment. However, automated DR classification remains challenging due to variations in image quality, class imbalance, and pixel-level similarities that hinder model training. To address these issues, we propose a robust preprocessing pipeline incorporating image cropping, Contrast-Limited Adaptive Histogram Equalization (CLAHE), and targeted data augmentation to improve model generalization and resilience. Our approach leverages the Swin Transformer, which utilizes hierarchical token processing and shifted window attention to efficiently capture fine-grained features while maintaining linear computational complexity. We validate our method on the Aptos and IDRiD datasets for multi-class DR classification, achieving accuracy rates of 89.65% and 97.40%, respectively. These results demonstrate the effectiveness of our model, particularly in detecting early-stage DR, highlighting its potential for improving automated retinal screening in clinical settings.
title Enhancing DR Classification with Swin Transformer and Shifted Window Attention
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.15317