PhD candidate ‘Deepfakes’ in radiology? Synthetic imaging data for medical AI regulation

You will be based in the Department of Medical Imaging at Radboud University Medical Center (Radboudumc), embedded in the Diagnostic Image Analysis Group (DIAG). DIAG is one of Europe’s leading research groups in medical image analysis, with researchers across Radiology and Nuclear Medicine, Pathology, and Cardiology. The group has a strong track record of publishing in high-impact journals. The working atmosphere is collaborative, international, and focused on clinical impact.

This project connects technical research on synthetic medical imaging data with clinical evidence and regulatory science. Within COMPASS4MD, a Horizon Europe consortium developing new methodologies for evaluating clinical evidence for medical devices, you will investigate when synthetic imaging data can support the development and regulatory evaluation of medical AI. You will combine technical evaluation with research on the evidence requirements for responsible regulatory use.

You will be jointly supervised by Dr M. Huisman (PI), at Radboudumc and Dr Michail Klontzas at the University of Crete. Dr Huisman is an attending cardiovascular and musculoskeletal radiologist and Vice President Elect of EuSoMII, with expertise in clinical AI validation, post-market surveillance, and standardisation of AI as a regulated clinical technology. Dr Klontzas and his team lead the technical characterisation of synthetic imaging within COMPASS4MD. Your promotor is Prof. Henkjan Huisman (DIAG, Radiology).

You will work relatively independently within a group with strong technical expertise in imaging AI, while maintaining close collaboration with the University of Crete and other international partners across the COMPASS4MD consortium. The project offers opportunities to engage with clinical researchers, AI developers, regulators, and notified bodies. Hybrid working is possible, depending on individual circumstances and project requirements.

At the Department of Medical Imaging, you work on diagnostics, interventions, education, and scientific research. Our focus spans three key areas: Radiology, Nuclear Medicine, and Anatomy. Together with your colleagues, you contribute to the early detection of diseases and the improvement of treatments, helping us make healthcare more precise and patient friendly.

The ideal candidate is an intellectually independent, intrinsically motivated researcher with a strong interest in connecting medical imaging AI, research methodology, and regulatory science. You can critically evaluate technical methods and translate findings into meaningful evidence requirements. You are resourceful and proactive, take ownership of your work, and can organise complex research activities independently within a multidisciplinary and international environment. Familiarity with the European medical-device regulatory framework, particularly the MDR and AI Act, is an advantage.

Education

You have an MSc degree in Artificial Intelligence, Data Science, Computer Science, Biomedical Engineering, Technical Medicine, Medical Image Analysis, Medical Informatics, or a closely related discipline. Candidates with a background in health law or technology regulation are also welcome, provided they demonstrate experience with empirical research and a strong aptitude for quantitative and technical methods.

Experience & competencies

• Experience with Python and machine learning, preferably applied to medical imaging or computer vision.
• A critical understanding of AI model development and evaluation, including the capabilities and limitations of generative AI and synthetic data.
• Experience with image analysis, synthetic image generation, downstream model evaluation, bias assessment, or privacy-preserving machine learning is an advantage.
• An understanding of research methodology and statistics, with an interest in evaluating data quality, representativeness, and clinical validity.
• An interest in medical-device regulation and how technical findings inform clinical evidence and regulatory decision-making. Prior regulatory expertise is not required.
• The ability to combine technical research with structured literature reviews and stakeholder research, including interviews and consensus methods.
• Strong organisational skills and the ability to communicate with technical, clinical, and regulatory stakeholders.
• Scientific writing and presentation skills.
• Working proficiency in English (C1–C2).

• Preferred start date: 1 February 2027
• This is a 4-year PhD position within the COMPASS4MD Horizon Europe consortium.
• You will be based at Radboudumc and jointly supervised by Dr Merel Huisman and Dr Michail Klontzas at the University of Crete.
• This position requires a Certificate of Conduct (VOG).

We are recruiting for this position ourselves. Unsolicited marketing is not appreciated, but do feel free to share the vacancy in your network!