Project description
Myocardial fibrosis and epicardial fat are important structural biomarkers associated with atrial fibrillation progression and cardiomyopathy. This project will develop machine learning models (e.g., UNet, Vision Transformer) to automatically segment and quantify fibrosis or epicardial fat from cardiac MRI. Students will preprocess labelled MRI datasets, train and optimise segmentation models, and evaluate reproducibility and clinical interpretability. Results will be contextualised against clinical characteristics such as AF burden and ventricular function. Outcome: A deployable ML pipeline for automated structural biomarker extraction, contributing directly to patient-specific modelling and AF-induced cardiomyopathy research.
Supervisors research focus
Computational cardiology, data science, signal processing, machine learning, biomedical engineering, biophysics
Note: You need to register interest in projects from different supervisors (not a number of projects with the one supervisor).
You must also contact each supervisor directly to discuss both the project details and your suitability to undertake the project.