PhD in Physics-Informed Generative AI for Dynamic Cardiac MRI
Develop trustworthy generative AI methods to enable safe, low-dose cardiac magnetic resonance imaging.
Best for:Best for graduate students with a strong background in deep learning, Python, PyTorch, and an interest in medical imaging or physics-informed machine learning.
Overview
Eindhoven University of Technology is offering a four-year PhD position focused on creating physics-informed generative AI models for cardiac MRI. Part of the PRIMA-CMR collaborative project within the EuroTech Universities Alliance, the research aims to recover diagnostic information from low-dose scans while quantifying uncertainty for clinical validation. The successful candidate will spend six months visiting the Technical University of Munich and will split their time between algorithmic development, clinical validation, and teaching duties. Applicants are expected to hold a relevant master's degree and bring strong programming skills in Python and PyTorch.
What you'll do
- Develop novel generative AI architectures designed to reconstruct trustworthy diagnostic data from low-dose cardiac MRI scans.
- Integrate MRI physics, inverse problems, and clinical patient data into machine learning models.
- Implement robust uncertainty quantification methods to ensure model reliability for clinical interpretation.
- Collaborate with international academic partners and clinical teams to validate models on real-world clinical data.
- Participate in a six-month research stay at the Technical University of Munich.
- Contribute 10% to 15% of working time to teaching tasks and mentoring students.
- Publish research findings in peer-reviewed journals and present work at international conferences.
Requirements
Degree required: Master of Science or equivalent university degree in Biomedical Engineering, Computer Science, Electrical Engineering, Applied Physics, Applied Mathematics, or a related field
Degree offered: PhD
Language: English; fluent spoken and written proficiency at C1 level
Instruction: English
- Solid foundation in deep learning with specific interest in generative models
- Proficiency in Python and deep learning frameworks such as PyTorch
- Strong analytical thinking, problem-solving abilities, and a research-oriented attitude
- Capability to work effectively within an international, interdisciplinary team
- Willingness to complete a six-month research placement in Munich
Funding & terms
How to apply
Deadline: 2026-11-21 · open until filled
Candidates must submit their application online using the official application portal. The submission must include a detailed motivation letter, a curriculum vitae with reference contacts, a summary of the master's thesis, and complete academic transcripts.
- Cover letter
- CV
- List of publications
- Brief description of MSc thesis and related research projects
- List of Bachelor's and Master's courses and grades
Contact
Cian Scannell· Assistant Professor of Medical Image Analysis
Create a free profile to unlock your personal match score, the full requirements, funding details and how to apply — in English or Persian.