Our research aims to understand the physiology of vascular function and blood flow to translate findings into clinical understanding and applications for diseases treatment. Our major focus is the characterisation of the pathophysiological processes of coronary artery disease. We use a combination of powerful image processing techniques, computational and mathematical modelling of to patient-specific clinical data. Personalised modelling pipelines are developed to help early disease diagnose, and improve treatment strategies through outcome prediction of interventions. We closely collaborate with clinicians. For a full list of publications please click here.
Just like we come in all different sizes and shapes, our arteries do too. Our team accounts such individual differences by developing the largest database of coronary artery population vessel shape and flow to date. This can then provide insights into higher risk for some.
Many different stent designs are currently on the world-wide market. However it is not clear which design is the best. Multi-object design considerations can reveal some of the trade-offs in current design concepts.
Stent implants are not always easy. Some patient’s vessels are challenging to stent and for some lesions there is still no consensus on what the best stenting strategy may be. Our team is currently investigating these knowledge gaps.
Everyone is different yet seldomly this is accounted in medicine. We aim to increase understanding of individual differences and how these may effect cardiovascular health.
Deep learning for risk prediction
Deep learning is the most powerful machine learning subset especially for our medical image processing. Using the large database available, we aim to identify early disease markers.