GLAUCOMA DETECTION AND PREDICTION USING CONVOLUTIONAL NEURAL

Project Abstract

For the past decades, individuals, families, communities, societies, nations, and in fact continents have battled with eye diseases specifically glaucoma. In the year 2023, the World Health Organization reported that 2.2 billion individuals suffer from glaucoma, resulting to vision deterioration and sometimes total blindness. Glaucoma traces is common within Asian descends and African descends. Ghana, as reported by Dr. James Addy, the Ghana Head of Eye Care Unit of the Ghana Health Service, in the year 2018, states that a total of 1275 health personnels are eye care practitioners with 5 only specializing in glaucoma. Additionally, the global economic burden of glaucoma reaches $3 trillion, and the artificial intelligence is less integrated into medical diagnosis. This, study aims to explore the operability of the artificial intelligence in medical diagnosis specifically glaucoma, integrating machine learning to detect and predict glaucomatous images, and evaluating the potential benefits of AI in health care in general. Using a well representative fundus image, cleaned and preprocessed a model was developed for the detection and prediction of glaucomatous images, continuously refining the model until an efficient model was realized. The model finally had an accuracy of 98% with subtle bias in some images with some outlier features. These results emphasize and prove the effectiveness of artificial intelligence in the health centers, aiding rapid diagnosis, reducing the burden of health practitioners, and lowering the cost of medical treatment.

Research Area

Machine Learning: Machine Learning (ML) research in Computer Science and Information Technology focuses on the development of algorithms and models that enable computers to learn from data and improve their performance over time without being explicitly programmed. It is a subset of Artificial Intelligence that uses statistical techniques to give machines the ability to learn patterns, make decisions, and predict outcomes based on data. Supervised learning, a key area of ML research, involves training models on labeled data, where the input-output relationships are predefined. This method is widely used for tasks such as classification (e.g., spam detection) and regression (e.g., predicting house prices). Unsupervised learning, on the other hand, involves finding hidden patterns in data without predefined labels, with clustering and association being typical applications in areas such as customer segmentation and anomaly detection. Reinforcement learning is another area of ML that focuses on teaching agents to make decisions by interacting with their environment and receiving feedback in the form of rewards or penalties. It is often applied in robotics, game playing, and autonomous systems, where continuous learning and adaptation are required.

Project Main Objective

• To develop and evaluate a machine learning-based convolutional neural network model capable of automatically detecting and predicting glaucoma from retinal fundus images.

Academic Year

2024/2025

Date Uploaded

Feb 3, 2026

Group Members

MUHAMMED RABIU, KABORE ABDUL-AZIZ, BOAHEN MICHAEL, ERIC AIKINS, ADU ALBERT OHENE KUSI

Program Of Study

BSc Information Technology