EdgeSVDNet: 5G-Enabled Detection and Classification of Vision-Threatening Diabetic Retinopathy in Retinal Fundus Images

• DOI: 10.3390/electronics12194094
• Publication Date: 2023-10-02T08:28:08Z
• Authors: Anas Bilal; Xiaowen Liu; Talha Imtiaz Baig; Haixia Long; Muhammad Shafiq
• Keywords: Transformative Learning; Margin (machine learning); Fundus (uterus)

The rise of vision-threatening diabetic retinopathy (VTDR) underscores the imperative for advanced and efficient early detection mechanisms. With integration Internet Things (IoT) 5G technologies, there is transformative potential VTDR diagnosis, facilitating real-time processing burgeoning volume fundus images (FIs). Combined with artificial intelligence (AI), this offers a robust platform managing vast healthcare datasets achieving unparalleled disease precision. Our study introduces novel AI-driven framework that integrates multiple models through majority voting. This comprehensive approach encompasses pre-processing, data augmentation, feature extraction using hybrid convolutional neural network-singular value decomposition (CNN-SVD) model, classification an enhanced SVM-RBF combined decision tree (DT) K-nearest neighbor (KNN). Validated on IDRiD dataset, our model boasts accuracy 99.89%, sensitivity 84.40%, specificity 100%, marking significant improvement over traditional method. convergence IoT, 5G, AI technologies herald era in healthcare, ensuring timely accurate diagnoses, especially geographically underserved regions.