FindAPhD Weekly PhD Newsletter | JOIN NOW FindAPhD Weekly PhD Newsletter | JOIN NOW

Early non-invasive detection of coronary microvascular disease using AI-based multiparameter analysis and computational simulation

   Centre for Intelligent Healthcare

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Prof Dingding Zheng, Prof Yi Su, Dr Haipeng Liu  No more applications being accepted  Competition Funded PhD Project (Students Worldwide)

About the Project

Coventry University is inviting applications from suitably-qualified graduates for a fully-funded PhD studentship. The successful candidate will join the project ‘Early non-invasive detection of coronary microvascular disease using AI-based multiparameter analysis and computational simulation’ led by Prof Dingchang Zheng (physiological measurement and AI algorithms) and Dr Haipeng Liu (Computational fluid dynamics and biosignal processing) at Coventry University. 

The Coronary MicroVascular Disease (CMVD) has been confirmed as a major underlying mechanism of myocardial ischemia in patients with suspected coronary artery disease (SCAD). Currently, the reliable detection of CMVD depends on the evaluation of index of microcirculatory resistance (IMR), which is invasively measured using a pressure-temperature guidewire in a coronary artery. The measurement of IMR is difficult, costly, and often performed on symptomatic patients of SCAD. Considering the prevalence of SCAD and the invasive nature of guidewire measurement, there is an urgent clinical need to provide a non-invasive method to achieve the early detection of CMVD.

To achieve the early detection of CMVD, patient-specific dynamic computational fluid dynamics (CFD) simulation, myocardial contrast echocardiography (MCE), and multichannel electrocardiogram (ECG) have been investigated recently. The hemodynamic parameters extracted by these methods are related with the coronary microcirculation status. However, only one technology was used in most of these pilot studies, and the results are not quantitative, which makes it difficult to achieve the reliable detection of CMVD.

In this PhD project, we aim to develop a novel AI-based method to achieve early, reliable, and non-invasive detection of CMVD using multi-parameter analysis and computational simulation.

Firstly, different hemodynamic parameters will be derived non-invasively from dynamic analysis of MCE images, patient-specific CFD simulation, and the processing of multichannel ECG signals.

 Secondly, based on the clinical observation data (e.g., IMR measurement), a machine learning model will be developed and trained to detect CMVD using non-invasive hemodynamic parameters.

Finally, the machine learning model will be validated on new clinical datasets to achieve the early, reliable, and non-invasive detection of CMVD in different populations.

We are looking for a highly motivated candidate who has a strong interest in developing innovative healthcare technologies and has a broad understanding of cardiac physiology.

The PhD project requires working with clinicians, biomedical engineers, and computer scientists at different stages along the development pathway – and will lead to high-quality publications. It will involve clinical data collection and analysis, and a variety of computing work (including cardiac image processing, computational modelling, AI, and statistical analysis).

Coventry University and A*STAR jointly offer this fully-funded PhD studentship to UK/EU and international students as part of the A*STAR Research Attachment Programme. 

The successful candidate will enrol at Coventry University, UK as their home institution and will spend up to 2 years at the Institute of High Performance Computing (IHPC) of A*STAR.

A typical 4-year pattern of attendance is shown below although the concrete plan would be developed in response to the proposed research design and with the mutual agreement of the supervision team. 

Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs