Deep-attention feature fusion network for automated diagnosis of diabetic retinopathy using fundus photographs

Author Identifier

Afsah Saleem: https://orcid.org/0000-0001-7240-0837

Arooba Maqsood: https://orcid.org/0009-0001-0853-9268

Syed Zulqarnain Gilani: https://orcid.org/0000-0002-7448-2327

Document Type

Conference Proceeding

Publication Title

Proceedings - 2024 25th International Conference on Digital Image Computing: Techniques and Applications, DICTA 2024

First Page

485

Last Page

492

Publisher

IEEE

School

Centre for Artificial Intelligence and Machine Learning (CAIML)

Funders

Raine Medical Research Foundation

Comments

Saleem, A., Sulman, M., Maqsood, A., Bashir, S., & Gilani, S. Z. (2024, November). Deep-attention feature fusion network for automated diagnosis of diabetic retinopathy using fundus photographs. In 2024 International Conference on Digital Image Computing: Techniques and Applications (DICTA) (pp. 485-492). IEEE. https://doi.org/10.1109/DICTA63115.2024.00077

Abstract

Diabetic Retinopathy (DR) is a leading cause of global blindness, affecting millions of individuals with diabetes. Early detection and precise classification of DR is essential for timely intervention and effective treatment, significantly reducing the risk of severe vision loss. The diagnosis of DR often relies on retinal fundus images, yet the manual assessment by trained ophthalmologists remains laborious, time-consuming, and subject to subjective interpretation. In this work, we frame diabetic retinopathy grading as a classification problem and develop a deep attention feature fusion network to diagnose DR using fundus photographs. The proposed framework initially extracts convolutional feature maps from multiple CNN models, each trained to capture different aspects of retinal images. These feature maps are then fused using simple yet effective convolutional attention to extract the most salient and localized features from the fused feature map. We conducted experiments using the large publicly available APTOS dataset. To evaluate our results, we performed an ablation study to assess the effectiveness of deep feature fusion and attention-based feature fusion. Our findings demonstrate that the proposed framework significantly enhances overall DR stage classification performance, achieving an average accuracy of 87% and markedly improving the performance of minority classes.

DOI

10.1109/DICTA63115.2024.00077

Access Rights

subscription content

Link to Full Text

Share

 
COinS