Photon-Counting CT Biomarkers for Early Precision Stratification of Coronary Plaque
Supervisors
Dr Alessandro Perelli, School of Cardiovascular and Metabolic Health, University of Glasgow
Dr Richard Bates, School of Physics & Astronomy, University of Glasgow
Prof Michelle Williams, Centre for Cardiovascular Science, University of Edinburgh
Prof Sandosh Padmanabhan, School of Cardiovascular & Metabolic Health, University of Glasgow
Summary
Coronary artery disease remains a leading cause of death, yet current CT angiography chiefly grades luminal stenosis rather than plaque composition, missing many patients with vulnerable but non-obstructive plaque who go on to have heart attacks. This project will develop deep learning methods to unlock the full potential of photon-counting CT (PCCT), a new spectral imaging technology now available in Scotland at the University of Edinburgh, for direct, quantitative characterisation of coronary plaque composition, calcium, lipid and fibrous content at clinically acceptable radiation dose. Physics-guided deep learning material-decomposition models will be developed and validated using preliminary spectral and phase-contrast CT data generated with Medipix3 detector technology at the University of Glasgow, then translated to clinical PCCT data from the SCOT-HEART2 study in Edinburgh. The resulting quantitative imaging biomarkers will be tested for their ability to identify patients at elevated risk of future cardiac events, supporting earlier, more precise patient stratification and prevention. The student will gain training in deep learning, CT physics and detector instrumentation, and clinical cardiovascular imaging, working across a cross-institutional Glasgow and Edinburgh supervisory team combining computational, physics and clinical expertise.
Supervisor(s) for each project will be holding a 30-minute Q&A session during the first two weeks of December.
If you have any questions about a project, you are welcome to attend the relevant session.
If you would like to receive the webinar details, please submit a request via the Webinar Link Request Form.