<![CDATA[Cataract is a condition in which the lens inside the eye becomes cloudy, resulting in blurred or hazy vision. RSAW treats around 800 cataract patients every month, served by seven cataract ophthalmologists. The limited number of doctors and different levels of expertise can affect the duration of the initial screening time. Therefore, a system is needed that can support doctors in the cataract diagnosis process. Convolutional Neural Network (CNN) is a type of neural network specifically designed to process image or video data. CNN is a type of deep learning model that can train systems using large amounts of data and integrate the feature extraction process with classification. This study aims to develop and evaluate the performance of a CNN-based cataract detection system as a tool for early diagnosis in cataract patients at RSAW. The CNN model was trained using an eye image dataset consisting of 1120 images of cataract and non-cataract patients. The CNN architecture used was VGG16, chosen for its ability to extract relevant features. The evaluation results show that the system is able to detect cataracts with an accuracy of 96.43%, This system has the potential to increase the efficiency of the screening process and reduce the workload of doctors, thereby improving the quality of eye health services.]]>
Copyrights © 2025
