Zhang Group - AI deep generative models for contrast enhancement of MRI: Towards needle-free and more informative MRI examination of the heart

About the research

This DPhil project aims to develop novel generative AI to enhance cardiac MRI to assess myocardial pathologies beyond the current diagnostic capabilities of MRI. You will focus on one of the three research questions:

1. Beyond detecting focal scar (as discovered in our pilot work, Zhang et al, Circulation 2021; Circulation 2022), can AI-enhancement capture diffuse pathologies in common cardiac diseases without contrast injections?
2. How to develop stable, generalisable and explainable models for AI-enhancement of MRI for reliable clinical use?
3. Can AI-enhancement provide new imaging biomarkers beyond conventional MRI, for risk prediction of important clinical outcomes (such as sudden death) in large-scale clinical studies?

This student project is expected to contribute to our compressive programme working towards disruptive, AI-based cardiac MRI technologies, as robust diagnostic tools for in-depth myocardial tissue assessment. You will also work on novel machine-learning solutions for generative models, federated and transparent deep learning that are reliable for clinical use.

Training opportunities

You will benefit from an interdisciplinary core supervision team including a machine-learning scientist, cardiologist (Prof Vanessa Ferreira) and MR scientist (Prof Stefan Piechnik), and develop deep generative models at the forefront of cardiac clinical research, immersed in hospital settings.

You will have the chance to observe real-world clinical MR scans. Additional training in machine learning is supported by the Oxford Institute of Biomedical Engineering (Prof Konstantinos Kamnitsas).

Students are encouraged to attend the MRC Weatherall Institute of Molecular Medicine DPhil course, which takes place in the autumn of their first year. Running over several days, this course helps students to develop basic research and presentation skills as well as introducing them to a wide range of scientific techniques and principles, ensuring that students have the opportunity to build a broad-based understanding of differing research methodologies.

The Department has a successful mentoring scheme, open to graduate students, which provides an additional possible channel for personal and professional development outside the regular supervisory framework. We hold an Athena SWAN Silver Award in recognition of our efforts to build a happy and rewarding environment where all staff and students are supported to achieve their full potential.

Publications