Wolf Social Leader Optimized BiLSTM for Diabetic Retinopathy Detection and Grading

Diabetic retinopathy (DR) is a common complication of diabetes mellitus and a major cause of preventable vision loss worldwide. Early detection and grading of DR are crucial for timely intervention and effective treatment. The latest advancement in artificial intelligent, especially in machine learning could help in detecting and grading DR by processing fundus images. Although numerous machine learning and deep learning approaches have been proposed for DR detection, many existing models suffer from limitations such as overfitting and high computational complexity. In addition, several models exhibit insufficient robustness and poor generalization when dealing with complex and heterogeneous fundus images, particularly in capturing subtle texture-based features. To address these challenges, this study proposes a novel Wolf Social Leader algorithm-enabled Bi-directional Long Short-Term Memory (WS-BiLSTM) model for accurate DR detection and grading. The proposed approach integrates weighted shape-based texture patterns and statistical feature extraction to selectively emphasize subtle texture-based features while suppressing irrelevant information, thereby mitigating overfitting. In addition, ResNet-101 is used to extract informative deep representations from fundus images, enhancing feature richness and classification accuracy. The Wolf Social Leader (WSL) algorithm is incorporated to optimize the model hyperparameters by emulating efficient social 1 dynamics and cooperative hunting strategies, resulting in faster convergence and reduced computational cost. Experimental results demonstrate that the proposed WS-BiLSTM model achieves superior detection performance, attaining accuracy, sensitivity, and specificity of 96.32%, 97.21%, and 95.42%, respectively, thereby outperforming several existing models. These results demonstrate the potential of the proposed approach to support clinicians by enabling more accurate and reliable decision-making, thereby contributing to earlier diagnosis and improved patient outcomes.