Deep multi-view feature fusion with data augmentation for improved diabetic retinopathy classification

Journal of Intelligent Systems, Journal Year: 2025, Volume and Issue: 34(1)

Published: Jan. 1, 2025

Abstract Diabetic retinopathy (DR) is a leading cause of blindness worldwide, necessitating early detection to prevent severe visual impairment. Despite numerous proposed classification techniques, challenges persist due the high parameter count deep learning algorithms, imbalanced datasets, and limited performance. This study introduces novel framework for DR that leverages multi-view features, multilinear whitened principal component analysis, tensor exponential discriminant synthetic minority oversampling technique, random forest. We evaluated this architecture using APTOS dataset under standard protocol. The results demonstrate our significantly improves accuracy, surpassing existing methods. Our contributions highlight promising approach enhancing

Language: Английский

Automated Screening for Ocular Abnormalities: Leveraging Data Augmentation for Improved Diagnostic Accuracy

Communications in computer and information science, Journal Year: 2024, Volume and Issue: unknown, P. 65 - 78

Published: Jan. 1, 2024

Language: Английский