PhD Studentship: Super-Resolution of 4D Flow MRI for Cardiovascular Disease using Machine Learning
The University of Manchester
Application deadline: 25.09.26 This 3.5 year project is funded by the Department of Mechanical and Aerospace Engineering. Tuition fees will be paid (at home rate) and you will receive a tax-free stipend set at the UKRI rate (£21,805 for 2026/27 academic year. The start date is October 2026 or January 2027. We recommend that you apply early as the advert may be removed before the deadline. Phase-contrast magnetic resonance imaging (Flow MRI) is a powerful and non-invasive imaging technique that measures blood flo...
Application deadline: 25.09.26 This 3.5 year project is funded by the Department of Mechanical and Aerospace Engineering. Tuition fees will be paid (at home rate) and you will receive a tax-free stipend set at the UKRI rate (£21,805 for 2026/27 academic year. The start date is October 2026 or January 2027. We recommend that you apply early as the advert may be removed before the deadline. Phase-contrast magnetic resonance imaging (Flow MRI) is a powerful and non-invasive imaging technique that measures blood flo...
Opportunity details
Application deadline: 25.09.26 This 3.5 year project is funded by the Department of Mechanical and Aerospace Engineering. Tuition fees will be paid (at home rate) and you will receive a tax-free stipend set at the UKRI rate (£21,805 for 2026/27 academic year. The start date is October 2026 or January 2027. We recommend that you apply early as the advert may be removed before the deadline. Phase-contrast magnetic resonance imaging (Flow MRI) is a powerful and non-invasive imaging technique that measures blood flow in time and space. It provides vital insights into key metrics for cardiovascular disease diagnosis and management, such as velocity, wall shear stress, and turbulence. However, its clinical application is currently severely limited by high noise (low signal-to-noise ratio) and low spatial and temporal resolution. This project aims to overcome these critical limitations by applying advanced machine learning techniques to denoise and improve spatial resolutions. You will run high-fidelity computational fluid dynamics (CFD) simulations of blood flow through arteries and develop a cutting-edge super-resolution framework using convolutional neural networks (CNNs). The ultimate goal is to vastly improve the reliability of haemodynamic metrics derived from Flow MRI, enabling their direct use in clinic to support cardiovascular disease management. Expected Outcomes Develop a novel machine learning framework for MR image super resolution using high fidelity CFD data. Validate the software using MRI scans of arterial flow phantoms. Collaborate directly with clinicians to maximise the translational and clinical impact of the research. Training Opportunities The student will benefit from working alongside a multidisciplinary team of engineers, scientists and clinicians...
Eligibility
Applicants should have, or expect to achieve, at least a 2.1 honours degree or a master’s (or international equivalent) in a relevant science, mathematics or engineering related discipline. Experience in programming (e.g., Python, MATLAB, C++, etc). Strong written and verbal communication skills.
Requirements
Applicants should have, or expect to achieve, at least a 2.1 honours degree or a master’s (or international equivalent) in a relevant science, mathematics or engineering related discipline. Experience in programming (e.g., Python, MATLAB, C++, etc). Strong written and verbal communication skills.
Funding and benefits
Funding eligibility: UK Students, International Students. Funding amount: £21,805 tax-free stipend and tuition fees will be paid (at home rate).
Required documents
CV
How to apply
Application deadline: 25.09.26 This 3.5 year project is funded by the Department of Mechanical and Aerospace Engineering. We recommend that you apply early as the advert may be removed before the deadline. However, its clinical application is currently severely limited by high noise (low signal-to-noise ratio) and low spatial and temporal resolution. This project aims to overcome these critical limitations by applying advanced machine learning techniques to denoise and improve spatial resolutions.
Open the official application information
Verify the deadline and final conditions on the official provider page before submitting an application.
Benefits
Funding eligibility: UK Students, International Students. Funding amount: £21,805 tax-free stipend and tuition fees will be paid (at home rate).
Eligibility summary
Applicants should have, or expect to achieve, at least a 2.1 honours degree or a master’s (or international equivalent) in a relevant science, mathematics or engineering related discipline. Experience in programming (e.g., Python, MATLAB, C++, etc). Strong written and verbal communication skills.
Requirements
Applicants should have, or expect to achieve, at least a 2.1 honours degree or a master’s (or international equivalent) in a relevant science, mathematics or engineering related discipline. Experience in programming (e.g., Python, MATLAB, C++, etc). Strong written and verbal communication skills.
Documents required
CV
Language/test requirements
Listing-board disclaimer
Prime Scholarship Alerts is a listing board only and does not provide application procedures or guarantee scholarship awards. Verify all requirements, deadlines, fees, and application instructions through the provider before applying.