Zhang Group: Artificial Intelligence in Cardiovascular Imaging
We work with clinicians and MR scientists on a day-to-day basis to develop novel AI machine-learning approaches for cardiovascular imaging.
The Group’s primary aim is to advance cardiac diagnostic imaging and enrich cardiovascular clinical studies through the deep integration of AI machine learning with MRI and cardiology. In particular:
- Make cardiovascular MRI scanning safer, faster and more informative by enhancing the image contrast with novel generative AI approaches. A representative work is the Virtual Native Enhancement technology.
- Automate the cardiovascular MRI post-processing and reporting using pipelines empowered by feature detection, registration and segmentation machine-learning methods.
- Enrich large biomedical studies with novel AI imaging biomarkers and machine-learning tools, through collaborations with the BHF CRE network, Big Data Institute and the Institute of Biomedical Engineering.
Two deep learning DPhil projects are available for 2025 entry:
(1) Generative Artificial Intelligence for Cardiovascular Imaging, Radcliffe Department of Medicine.
(2) AI-enhanced cardiovascular imaging using machine learning at population scale, apply via NDPH and based at the Big Data Institute.
Contact: qiang.zhang@cardiov.ox.ac.uk
COLLABORATORS
- Prof Konstantinos Kamnitsas, Institute of Biomedical Imaging, University of Oxford
- Prof Sven Plein, Leeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds
- Prof Rohan Dharmakumar, Krannert Cardiovascular Research Center, Indiana University, USA
- Prof Steffen Petersen, Queen Mary University of London, NIHR Barts Biomedical Research Centre (BRC)
- Prof Minjie Lu, National Centre for Cardiovascular Diseases (NCCD), Chinese Academy of Medical Science, China
FUNDING
- British Heart Foundation
- Oxford BHF Centre of Research Excellence
- John Fell Fund, University of Oxford