A Multi-Scale Soft-Thresholding Attention Network for Diabetic Retinopathy Recognition
Source abstract
Abstract
Diabetic retinopathy (DR) is a major cause of preventable vision loss, and its early detection is essential for timely clinical intervention. However, existing deep learning-based DR recognition methods still face two fundamental challenges: substantial lesion-scale variability and significant background noise in retinal fundus images. To address these issues, we propose a lightweight framework named Multi-Scale Soft-Thresholding Attention Network (MSA-Net). The model integrates three components: (1) parallel multi-scale convolutional branches to capture lesions of different spatial sizes; (2) a soft-thresholding attention module to suppress noise-dominated responses; and (3) hierarchical feature fusion to enhance cross-layer representation consistency. A squeeze-and-excitation module is further incorporated for channel recalibration. On the APTOS 2019 dataset, MSA-Net achieves 97.54% accuracy and 0.991 AUC-ROC for binary DR recognition. We further evaluate five-class DR grading on APTOS2019 with 5-fold stratified cross-validation, achieving 82.71 ± 1.25% accuracy and 0.8937 ± 0.0142 QWK, indicating stable performance for ordinal severity classification. With only 4.54 M parameters, MSA-Net remains lightweight and suitable for deployment in resource-constrained DR screening environments.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Retinal Imaging and Analysis · Retinal Diseases and Treatments · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Graduate School of Engineering, Saitama Institute of Technology, Fukaya 369-0203, Saitama, Japan
School of Mechanical and Electrical Engineering, Soochow University, No. 8 Jixue Road, Xiangcheng District, Suzhou 215137, China
RIKEN Center for Advanced Intelligence Project (AIP), Chuo-ku 103-0027, Tokyo, Japan
References (25)
Show source-provided references
1. Global prevalence of diabetic retinopathy and projection of burden through 2045: Systematic review and meta-analysis10.1016/j.ophtha.2021.04.027 ↗
2. Global prevalence and major risk factors of diabetic retinopathy10.2337/dc11-1909 ↗
3. The worldwide epidemic of diabetic retinopathy10.4103/0301-4738.100542 ↗
4. Risk factors and prevalence of diabetic retinopathy: A protocol for meta-analysis10.1097/MD.0000000000022695 ↗
5. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs10.1001/jama.2016.17216 ↗
6. Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning10.1167/iovs.16-19964 ↗
7. Tan, M., and Le, Q. (2019, January 9–15). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA.
8. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
9. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
10. Convolutional neural networks for diabetic retinopathy10.1016/j.procs.2016.07.014 ↗
11. Yu, F., and Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions. arXiv.
12. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
13. Spatial pyramid pooling in deep convolutional networks for visual recognition10.1109/TPAMI.2015.2389824 ↗
14. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298965 ↗
15. Sun, K., Zhao, Y., Jiang, B., Cheng, T., Xiao, B., Liu, D., Mu, Y., Wang, X., Liu, W., and Wang, J. (2019). High-resolution representations for labeling pixels and regions. arXiv.
16. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs10.1109/TPAMI.2017.2699184 ↗
17. De-noising by soft-thresholding10.1109/18.382009 ↗
18. Automatic severity classification of diabetic retinopathy based on densenet and convolutional block attention module10.1109/ACCESS.2022.3165193 ↗
19. Effective diabetic retinopathy classification with siamese neural network: A strategy for small dataset challenges10.1109/ACCESS.2024.3510556 ↗
20. Pakdelmoez, S., Omidikia, S., Seyyedsalehi, S.A., and Seyyedsalehi, S.Z. (2024). Controllable retinal image synthesis using conditional StyleGAN and latent space manipulation for improved diagnosis and grading of diabetic retinopathy. arXiv.
21. Hu, J., Shen, L., and Sun, G. (2018, January 18–23). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
22. Deep residual shrinkage networks for fault diagnosis10.1109/TII.2019.2943898 ↗
23. Lin, G., Milan, A., Shen, C., and Reid, I. (2017, January 21–26). Refinenet: Multi-path refinement networks for high-resolution semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.549 ↗
24. Liu, S., Qi, L., Qin, H., Shi, J., and Jia, J. (2018, January 18–23). Path aggregation network for instance segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00913 ↗
25. Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., and Kainz, B. (2018). Attention u-net: Learning where to look for the pancreas. arXiv.