SwinECAT: A Transformer-based fundus disease classification model with Shifted Window Attention and Efficient Channel Attention

TL;DR

SwinECAT is a novel transformer-based model that combines Shifted Window Attention and Efficient Channel Attention to improve accuracy in classifying nine types of fundus diseases from images, addressing challenges of small lesions and subtle differences.

Contribution

This paper introduces SwinECAT, a new model that enhances fundus disease classification by integrating Swin Transformer and ECA attention, expanding to nine categories and achieving state-of-the-art results.

Findings

Achieves 88.29% accuracy on EDID dataset

Outperforms baseline Swin Transformer and other models

Sets new benchmark for 9-category fundus classification

Abstract

In recent years, artificial intelligence has been increasingly applied in the field of medical imaging. Among these applications, fundus image analysis presents special challenges, including small lesion areas in certain fundus diseases and subtle inter-disease differences, which can lead to reduced prediction accuracy and overfitting in the models. To address these challenges, this paper proposes the Transformer-based model SwinECAT, which combines the Shifted Window (Swin) Attention with the Efficient Channel Attention (ECA) Attention. SwinECAT leverages the Swin Attention mechanism in the Swin Transformer backbone to effectively capture local spatial structures and long-range dependencies within fundus images. The lightweight ECA mechanism is incorporated to guide the SwinECAT's attention toward critical feature channels, enabling more discriminative feature representation. In contrast to previous studies that typically classify fundus images into 4 to 6 categories, this work expands fundus disease classification to 9 distinct types, thereby enhancing the granularity of diagnosis. We evaluate our method on the Eye Disease Image Dataset (EDID) containing 16,140 fundus images for 9-category classification. Experimental results demonstrate that SwinECAT achieves 88.29\% accuracy, with weighted F1-score of 0.88 and macro F1-score of 0.90. The classification results of our proposed model SwinECAT significantly outperform the baseline Swin Transformer and multiple compared baseline models. To our knowledge, this represents the highest reported performance for 9-category classification on this public dataset.