ITDS | SPMS

BRAIN STROKE PREDICTION USING CONVOLUTIONAL NEURAL NETWORK

Project Description
Supervisor

ABSTRACT Brain stroke is a leading cause of death and long-term disability worldwide, making early detection and accurate diagnosis critical for improving patient outcomes. Recent advancements in machine learning, particularly in Convolutional Neural Networks (CNNs), have demonstrated significant potential in medical image analysis, offering a powerful tool for predicting and diagnosing strokes. This study focuses on developing a CNN-based model for brain stroke prediction using medical imaging data such as CT scans and MRI images. The study starts with thorough data preprocessing, which includes addressing missing values, cleaning up data, identifying outliers, and normalising imaging data. CNN's convolutional layers are used in feature engineering to automatically extract important features from the medical pictures, such as texture, edge detection, and brain structure. The purpose of exploratory data analysis (EDA) was to remove potential biases like data imbalance and ensure data quality by gaining insights into the distribution and properties of the dataset. To improve generalisation, data augmentation methods including picture rotation, flipping, and scaling were used, and the model was trained by backpropagation and stochastic gradient descent (SGD), two optimisation techniques. Metrics including Mean Squared Error (MSE), R2 Score, and Accuracy were used to assess the model's performance; the CNN performed well in stroke prediction. This study demonstrates the efficacy of CNNs in brain stroke prediction and underscores the transformative potential of AI in medical diagnostics. Future work should focus on collecting larger and more diverse datasets, improving image quality, and integrating multimodal data to enhance the CNN's predictive accuracy. Additionally, developing interpretable AI models is crucial for ensuring the adoption of AI-based diagnostic tools in clinical settings, where transparency and trust are paramount.

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.