MVLA-Net:A Multi-View Lesion Attention Network for Advanced Diagnosis and Grading of Diabetic Retinopathy  

作　　者：Tariq Mahmood Tanzila Saba Faten S.Alamri Alishba Tahir Noor Ayesha 

机构地区：[1]Artificial Intelligence and Data Analytics(AIDA)Lab,College of Computer&Information Sciences,Prince Sultan University,Riyadh,11586,Saudi Arabia [2]Faculty of Information Sciences,University of Education,Vehari Campus,Vehari,61100,Pakistan [3]Department of Mathematical Sciences,College of Science,Princess Nourah bint Abdulrahman University,Riyadh,84428,Saudi Arabia [4]Shifa College of Medicine,Shifa Tameer-E-Millat University,Islamabad,44000,Pakistan [5]Center of Excellence in Cyber Security(CYBEX),Prince Sultan University,Riyadh,11586,Saudi Arabia

出　　处：《Computers, Materials & Continua》2025年第4期1173-1193,共21页计算机、材料和连续体(英文)

基　　金：funded by Princess Nourah bint Abdulrahman University and Researchers Supporting Project number(PNURSP2025R346);Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.

摘　　要：Innovation in learning algorithms has made retinal vessel segmentation and automatic grading tech-niques crucial for clinical diagnosis and prevention of diabetic retinopathy.The traditional methods struggle with accuracy and reliability due to multi-scale variations in retinal blood vessels and the complex pathological relationship in fundus images associated with diabetic retinopathy.While the single-modal diabetic retinopathy grading network addresses class imbalance challenges and lesion representation in fundus image data,dual-modal diabetic retinopathy grading methods offer superior performance.However,the scarcity of dual-modal data and the lack of effective feature fusion methods limit their potential due to multi-scale variations.This paper addresses these issues by focusing on multi-scale retinal vessel segmentation,dual feature fusion,data augmentation,and attention-based grading.The proposed model aims to improve comprehensive segmentation for retinal images with varying vessel thicknesses.It employs a dual-branch parallel architecture that integrates a transformer encoder with a convolutional neural network encoder to extract local and global information for synergistic saliency learning.Besides that,the model uses residual structures and attention modules to extract critical lesions,enhancing the accuracy and reliability of diabetic retinopathy grading.To evaluate the efficacy of the proposed approach,this study compared it with other pre-trained publicly open models,ResNet152V2,ConvNext,Efficient Net,DenseNet,and Swin Transform,with the same developmental parameters.All models achieved approximately 85%accuracy with the same image preparation method.However,the proposed approach outperforms and optimizes existing models by achieving an accuracy of 99.17%,99.04%,and 99.24%,on Kaggle APTOS19,IDRiD,and EyePACS datasets,respectively.These results support the model’s utility in helping ophthalmologists diagnose diabetic retinopathy more rapidly and accurately.

关 键 词：Diabetic retinopathy grading retinal vessel segmentation dual-modal deep learning attention mecha-nism health risks 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]