Development of a Novel Hybrid Bio Medical Image Processing Algorithm For The Detection Of Infectious Diseases In Human Eyes Using Ai-Ml Embedded Concepts

DOI: https://doie.org/10.0913/Jbse.2024214514

Mahesh B Neelagar, Dr Vishwanath P

Keywords:

CNN, AlexNet, Glaucoma Disease, training, testing, performance

Abstract:

Glaucoma is a leading cause of irreversible blindness worldwide, often progressing unnoticed until significant vision loss occurs. Early detection is critical for preventing its advancement, but conventional diagnostic methods are time-consuming and require specialized expertise. In this study, we propose a deep learning-based approach for glaucoma detection using Convolutional Neural Networks (CNN) and AlexNet. The models were trained and evaluated on a dataset containing retinal fundus images categorized into "Glaucoma Positive" and "Glaucoma Negative." Both the CNN and AlexNet architectures were designed to automatically extract and learn features relevant to glaucoma from the images. The performance of these models was assessed using standard evaluation metrics such as accuracy, sensitivity, specificity, and the area under the Receiver Operating Characteristic (ROC) curve. Results indicated that both models achieved promising classification performance, with the AlexNet-based approach slightly outperforming the standard CNN in terms of accuracy and sensitivity, due to its deeper architecture and pre-trained features. This study demonstrates the potential of leveraging deep learning techniques for automated glaucoma detection, providing an efficient, accurate, and scalable solution that could aid clinicians in early diagnosis and treatment planning. Further research is recommended to refine these models and validate their effectiveness on larger, more diverse datasets

PDF