ITDS | SPMS

Brain Tumor Detection Using Visual Geometry

Project Description
Supervisor

Brain tumors is one of the most lethal forms of cancer, where early and accurate diagnosis is critical for effective treatment and improved patient outcomes. Manual interpretation of brain MRI scans is time consuming, subjective, and prone to diagnostic errors, highlighting the need for automated detection systems. This research develops a deep learning-based application for brain tumor detection using the VGG19 convolutional neural network architecture. The system leverages transfer learning with a pre-trained VGG19 model, fine-tuned on a Brain Tumor MRI Dataset comprising of 7,023 images across four classes: glioma, meningioma, pituitary tumor and no tumor. Careful pre-processing standardized images to 224×224 pixels with normalization, while data augmentation techniques including rotation (20°), flipping, and shifting (10%), enhanced dataset diversity and model robustness. The methodology included strategic modifications to the VGG19 architecture, adding global average pooling, a 256- unit fully connected layer with ReLU activation, dropout regularization (0.5), and a softmax output layer for multi-class classification. The training protocol used a two-phase approach: initial transfer learning (90 epochs) followed by fine-tuning of the last four layers (10 epochs with 1e-5 learning rate), using Adam optimization and categorical cross- entropy loss. The developed application features a flutter- based front end for user-friendly MRI upload and a Flask back-end for seamless model integration, delivering real-time diagnosis support. Evaluated using accuracy, precision, recall, and F1-score metrics, the system demonstrates significant potential to assist radiologists in reducing diagnostic time while improving accuracy and consistency. This work contributes to advancing AI-assisted medical diagnostics, particularly in resource-constrained healthcare settings where access to specialized expertise is limited.

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.

The main goal of this project is to create an accurate deep learning system to detect brain tumor using VGG19 model.

2024/2025

Oct 12, 2025

DOFFUOUR GERAND AMANKWAH (UEB3210021), AMANQUAH COLLINS TETTEY (UEB3226021), MINSI SHADRACK (UEB3201723), PASCAL ADJEI QUAYE (UEB3230621), OKYEM EMMANUEL (UEB3230421)

BSc Information Technology