PhD Scholarship in Unsupervised Machine Learning for Cardiovascular Image Analysis

We invite applications for a fully funded PhD research scholarship in “Unsupervised Machine Learning for Cardiovascular Image Analysis”. This opportunity is available to UK (Home) candidates only.

Fully-supervised AI techniques have shown remarkable success in cardiovascular image analysis, but they are limited by their dependence on large, expert-annotated datasets, covering all cardiac conditions. This makes them unsuitable for identifying rare or complex cases, where annotations are scarce or unreliable. Recently developed unsupervised learning methods allow to circumvent this limitation by learning patterns in unlabelled medical images and then leveraging them for downstream tasks.

In this project, you will develop novel unsupervised machine learning methods to analyse cardiovascular images, primarily focusing on MRI. In your research you will train models to learn a distribution of normal cardiac anatomy and function (including motion) from healthy subjects. By establishing an understanding of "what normal looks like", these models will detect deviations from the norm and effectively identify potential anomalies during testing. You will explore both self-supervised learning and generative modelling approaches, contributing to the cutting edge of medical AI.

You will carry out your PhD journey in the heart of London at the newly established City St George's, University of London, a dynamic institution formed from the merger of City, University of London and St George's, University of London in August 2024. As a PhD candidate, you'll become an integral part of the School of Science and Technology (proud member of the Alan Turing University Network) and be supervised by leading experts in machine learning for healthcare. You will also be affiliated to the School of Health & Medical Sciences and have access to invaluable clinical datasets provided by St George's Hospital. With the support of leading biomedical researchers with strong ties to radiology, your work holds the promise of making significant impacts on patient care and advancing the field of cardiac health.

What is offered:

The Scholarship includes:

• A competitive annual bursary for 4 years (£21,237/year)
• Full tuition fees for UK/Home Students
• The opportunity to earn up to £4,300/year through a non-compulsory teaching assistantship
• Funding to participate in conferences and training to support your professional development

Eligibility:

The scholarship will be awarded based on outstanding academic achievement and the potential to produce cutting-edge research. Prospective applicants must:

• Hold a good honours degree in an appropriate subject (including Computer Science, Physics, Maths, Engineering)
• Knowledge of modern machine learning techniques and experience with coding in Python is beneficial (but not a strong requirement)
• Applicants whose mother tongue is not English must meet any one or a combination of the following:
  • A minimum IELTS average score of 6.5; with a minimum of 6.0 in each of the four components
  • A master’s degree awarded in an English-speaking Country and taught in English

For questions regarding the application process, please contact pgr.sst.enquire@city.ac.uk.

For questions regarding the project, please contact the academic supervisors:

Dr Giacomo Tarroni (giacomo.tarroni@citystgeorges.ac.uk) or

Dr Marta Varela (mvarela@citystgeorges.ac.uk).

How to apply:

To apply online, please click the 'Apply' button, above.

Please add only ‘Unsupervised Machine Learning for Cardiovascular Image Analysis’ in the research proposal box.

Application deadline: 30^th May 2025 (or until the position has been filled).

The successful candidate will start their doctorate in Jul/Oct 2025.

Advert information