iCase PhD studentship in AI for cardiac imaging 2026 entry
Friday 26th September 2025
Contact Email for the Job Posting qiang.zhang@cardiov.ox.ac.uk
Organization University of Oxford
Location Oxford, UK
Title iCase PhD studentship in AI for cardiac imaging 2026 entry
URL https://www.medsci.ox.ac.uk/study/graduateschool/mrcdtp/how-to-apply/icase-2026/developing-accountable-ai-for-automated-cardiovascular-mr-processing-towards-precision-diagnostic-reporting
Closing date Dec 02, 2025
Description Developing Accountable AI for Automated Cardiovascular MR Processing towards Precision Diagnostic Reporting
MRC-Industrial studentships (Collaborative Awards in Science and Engineering)
Lead supervisor: Associate Professor Qiang Zhang
Co-supervisor: Professor Stefan Piechnik, Professor Vanessa Ferreira
Institute: RDM Cardiovascular Medicine, University of Oxford
Commercial partner: AI4MedImaging
Rate: International students applicable
Cardiovascular magnetic resonance (CMR) offers a comprehensive, non-invasive assessment of cardiac anatomy, function and tissue characterisation. Despite its diagnostic capability, routine use is limited by the time-consuming post-processing and reporting, which often rely on experienced cardiologists and are subject to operator variability. Artificial intelligence is transforming medical imaging, and has shown strong potential for automated CMR analysis, to significantly improve the accuracy and consistency of reporting, and increase its efficiency and throughput.
This project will:
(1) Develop an AI pipeline for automated CMR processing and reporting. The student will build on our pre-developed neural networks for motion correction, segmentation and landmark detection. They will expand the AI approaches to include more CMR sequences, advanced deep learning architectures, and larger data banks.
(2) Develop accountable and conscionable AI approaches to ensure clinical applicability. The student will expand the quality-control driven neural networks – a method and concept that can notify the users of unreliable results when the neural networks have low confidence. This will deliver reliable modules for the CMR reporting pipeline.
(3) Integrate the pipeline onto commercial software platforms. Interdisciplinary expertise and industrial platform are crucial components of translating AI solutions to the clinics. This DPhil will utilise the cloud-based platform supported by AI4Med, and implement the AI pipeline onto AI4Med’s reporting system and user interfaces.
(4) Validate it for clinical adoption. Lastly, the AI solutions will be disseminated and validated in various CMR configurations and clinical scenarios, and translated to the clinics via the commercial platforms.
This proposed project aligns with the MRC’s remit in several areas. The development of artificial intelligence for cardiac MRI will advance accurate diagnostic imaging and support AI-driven precision medicine. The resulting AI tools will enable large-scale data analytics at the interface of cardiac health and biology. Integrating AI into cardiac MRI workflows will improve accessibility and affordability of cardiac diagnostics, particularly in low- and middle-income countries. The project is inherently interdisciplinary, drawing on expertise in AI, biomedical imaging, MR physics, and industry partnerships, and will foster researcher mobility across health and AI sciences.
AI4Med as the commercial partner will support the delivery of the project, especially for objectives (3) and (4). AI4Med provides strong software development expertise to implement the developed AI solutions into commercial platforms, including its cloud-based platform. It also offers a validated pathway of testing AI solutions in big data and diverse clinical workflows.
Supported by a supervisory team with complementary expertise of machine learning (Prof Qiang Zhang), MRI physics (Prof Stefan Piechnik), and clinical cardiology (Prof Vanessa Ferreira), and the industrial mentorship of AI4Med (Dr Daniel Leite and Dr Adriano Pinto), this project will train the student to become a future leader at the intersection of AI, healthcare big data, and diagnostic imaging, with industrial experience and skills.