Transforming Ophthalmic Diagnosis: A Deep Learning Approach for Accurate Eye Disease Classification

The accurate classification of eye diseases is crucial for timely intervention and effective management, yet it remains as a challenging task in healthcare. Existing methodologies, such as traditional handcrafted feature extraction and deep learning approaches, have shown the potential but are limited by their inability to fully capture the complexity and diversity of eye diseases. This study addresses these limitations through the development of a novel deep learning-based model for automated eye disease classification. Leveraging the ResNet150 architecture from Resnet152v2 and regularization techniques, the proposed model aims to improve accuracy and generalization capabilities. Quantitative evaluation demonstrates the model’s proficiency, achieving impressive accuracy rates of 99.61% on the training set, 93.84% on the validation set, and 93.60% on the test set. By overcoming the shortcomings of existing methodologies, the proposed model offers a promising solution for accurate and efficient eye disease classification, with implications for enhancing patient care and healthcare delivery.