ITDS | SPMS

DESIGN AND IMPLEMENTATION OF A MEDICAL IMAGES SEGMENTATION SYSTEM USING UNET (CONVLUTIONAL NEURAL NETWORKS)

Project Description
Supervisor

Medical image segmentation plays a crucial role in the accurate diagnosis and treatment planning of brain tumors and lung cancer. This project entails a web application system using U-Net, a convolutional neural network architecture renowned for its effectiveness in biomedical image segmentation tasks. The system aims to automate and enhance the segmentation process, thereby assisting healthcare professionals in analyzing magnetic resonance imaging (MRI) and computed tomography (CT) scans with improved precision and efficiency. Through the development of a user-friendly web interface, medical practitioners can upload, process, and visualize segmented images conveniently. The integration of U-Net into this web-based application demonstrates promising advancements in medical imaging technology, offering potential benefits in early diagnosis, treatment planning, and therapeutic monitoring for patients affected by brain tumors and lung cancer. The performance of the system was evaluated using various evaluation metrics, including accuracy and loss. The model performance evaluation confirms its potential as a valuable tool for healthcare practitioners in the early detection and diagnosis of skin cancer. This work contribution is mainly in the development of an web application that uses UNet for early detection of diseases. The proposed system is expected to significantly reduce healthcare costs and improve accuracy and yield faster diagnosis results compared to the traditional method.

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.

To develop a system that can segment brain tumor and lung cancer medical images to assist doctors in diagnosing processes

2023/2024

Feb 12, 2026

EBENEZER ASIEDU (UEB3221420) ESTHER SAWYER (UEB3201820), EMMANUEL ANTWI (UEB3266922), DERRICK BAAH AGYEI (UEB3267122), ELIJAH DAYON ABU (UEB3269022), HENRY BEDU-ADDO (UEB3262422)

BSc Information Technology