A Multi-Scale Soft-Thresholding Attention Network for Diabetic Retinopathy Recognition
Applied Sciences · 08.01.2026 · 16 (2) · 685
DOI: 10.3390/app16020685 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 08.01.2026. Verfasst von Xin Ma und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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.
Zitieren
APA
Ma, X., Sui, L., Chen, R., Maeda, T., & Cao, J. (2026). A Multi-Scale Soft-Thresholding Attention Network for Diabetic Retinopathy Recognition. Applied Sciences, 16(2), 685. https://doi.org/10.3390/app16020685
Vancouver
Ma X, Sui L, Chen R, Maeda T, Cao J. A Multi-Scale Soft-Thresholding Attention Network for Diabetic Retinopathy Recognition. Applied Sciences. 2026;16(2):685. doi:10.3390/app16020685
BibTeX
@article{Ma2026,
author = {Ma, Xin and Sui, Linfeng and Chen, Ruixuan and Maeda, Taiyo and Cao, Jianting},
title = {A Multi-Scale Soft-Thresholding Attention Network for Diabetic Retinopathy Recognition},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {2},
pages = {685},
doi = {10.3390/app16020685}
}
EUVIMED