Next Article in Journal
Shear-Compression Failure Condition of Key Strata Under Elastic Support During Periodic Breakage
Previous Article in Journal
BIM-Based Approach for Low-Voltage Line Design and Further Operation
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

An Accurate and Efficient Diabetic Retinopathy Diagnosis Method via Depthwise Separable Convolution and Multi-View Attention Mechanism

School of Artificial Intelligence, Capital University of Economics and Business, 121 Zhangjialukou, Fengtai District, Beijing 100070, China
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Appl. Sci. 2025, 15(17), 9298; https://doi.org/10.3390/app15179298
Submission received: 15 July 2025 / Revised: 21 August 2025 / Accepted: 21 August 2025 / Published: 24 August 2025

Abstract

Diabetic retinopathy (DR), a critical ocular disease that can lead to blindness, demands early and accurate diagnosis to prevent vision loss. Current automated DR diagnosis methods face two core challenges: first, subtle early lesions such as microaneurysms are often missed due to insufficient feature extraction; second, there is a persistent trade-off between model accuracy and efficiency—lightweight architectures often sacrifice precision for real-time performance, while high-accuracy models are computationally expensive and difficult to deploy on resource-constrained edge devices. To address these issues, this study presents a novel deep learning framework integrating depthwise separable convolution and a multi-view attention mechanism (MVAM) for efficient DR diagnosis using retinal images. The framework employs multi-scale feature fusion via parallel 3 × 3 and 5 × 5 convolutions to capture lesions of varying sizes and incorporates Gabor filters to enhance vascular texture and directional lesion modeling, improving sensitivity to early structural abnormalities while reducing computational costs. Experimental results on both the diabetic retinopathy (DR) dataset and ocular disease (OD) dataset demonstrate the superiority of the proposed method: it achieves a high accuracy of 0.9697 on the DR dataset and 0.9669 on the OD dataset, outperforming traditional methods such as CNN_eye, VGG, and UNet by more than 1 percentage point. Moreover, its training time is only half that of U-Net (on DR dataset) and VGG (on OD dataset), highlighting its potential for clinical DR screening.
Keywords: diabetic retinopathy; multi-scale feature fusion; attention mechanism diabetic retinopathy; multi-scale feature fusion; attention mechanism

Share and Cite

MDPI and ACS Style

Yang, Q.; Wei, Y.; Liu, F.; Wu, Z. An Accurate and Efficient Diabetic Retinopathy Diagnosis Method via Depthwise Separable Convolution and Multi-View Attention Mechanism. Appl. Sci. 2025, 15, 9298. https://doi.org/10.3390/app15179298

AMA Style

Yang Q, Wei Y, Liu F, Wu Z. An Accurate and Efficient Diabetic Retinopathy Diagnosis Method via Depthwise Separable Convolution and Multi-View Attention Mechanism. Applied Sciences. 2025; 15(17):9298. https://doi.org/10.3390/app15179298

Chicago/Turabian Style

Yang, Qing, Ying Wei, Fei Liu, and Zhuang Wu. 2025. "An Accurate and Efficient Diabetic Retinopathy Diagnosis Method via Depthwise Separable Convolution and Multi-View Attention Mechanism" Applied Sciences 15, no. 17: 9298. https://doi.org/10.3390/app15179298

APA Style

Yang, Q., Wei, Y., Liu, F., & Wu, Z. (2025). An Accurate and Efficient Diabetic Retinopathy Diagnosis Method via Depthwise Separable Convolution and Multi-View Attention Mechanism. Applied Sciences, 15(17), 9298. https://doi.org/10.3390/app15179298

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop