Microscopic assessment of histological tissue sections by pathologists is one of the cornerstones of diagnostics and of treatment decision making for patients. Every day, pathologists are tasked with detecting and classifying tissue patterns indicating presence of specific diseases, visually estimating the proportion of certain types of patterns to derive biomarkers, and with producing a textual report of their findings and their final diagnosis. This workload is steadily increasing due to the rise of disease incidences and an aging population, while at the same time the number of pathologists decreases and visual inspection is hampered by substantial inter-observer variability.

Task-specific Machine learning (ML) based on image analysis has already shown that it can support pathologists by improving their diagnostic performance and efficiency. Based on task- and application-specific developments, most of these “narrow” ML applications allow to “go from A to B”, replicating what humans can do. However, they often lack characteristics of robustness to out of distribution and out of domain data, transparency, interpretability, and do not exploit the wealth of multi-modal data (e.g., images and text) in pathology.

You will join the Computational Pathology Group to work on a project funded by the AMMODO Science Award for Groundbreaking Research, to address the aforementioned gaps by developing large multi-modal foundation models for digital pathology. You will use techniques of self-supervised learning, vision transformers for image analysis and natural language processing, and large-scale multi-modal digital pathology data, to build AI models that can learn end-to-end from large sets of multi-modal raw data, and eventually act as co-pilots for pathologists. You will investigate efficient approaches to train and use these models leveraging the wealth of whole-slide images and textual data available in clinical settings, and validate the methodology in clinical scenarios and in the largest dataset of oncological whole slide images in the world.

Tasks and responsibilities

• Work with self-supervised learning techniques to build large multi-modal foundation models with visual question-answering capabilities.
• Integrate language and image models to produce interpretable AI-generated textual output in the form of description of morphological features and clinical reports.
• Join a team within the computational pathology group with specific focus on foundation models.
• Collaborate with pathologists and (inter)national researchers to validate your developed algorithms in large cohorts.
• Have fun interactions with colleagues, present at local and (inter)national conferences, and develop yourself as an independent researcher.

Our new PhD candidate is a creative and ambitious researcher with an MSc degree in Computer Science, Data Science, Engineering, Technical Medicine, Biomedical Sciences or similar, with a clear interest in artificial intelligence and medical image analysis. Good communication and organizational skills are essential. Experience with deep learning and programming, preferably in Python should be evident from the (online) courses you've followed, your publications, GitHub account, etc. Experience with (multi-modal) foundation models and AI agents is a plus.

Fixed-term contract: 4 years.

At Radboud university medical center, you build on your future. We are committed to providing the best care, education, and research. And we are true to our word, because we help you develop and seize opportunities and give you the room to grow. As an employer, we believe that employees should feel vital and happy at work in all stages of life. We are also committed to creating a healthy and safe working environment. Our employment conditions contribute to that. What we offer:

• The salary depends on education. Scale 10 will be offered to MSc medical graduates; a gross monthly salary between €3.493 and € 5.504 (full-time). Those holding degrees in other disciplines will be offered scale 10A: upon commencement of employment, you will start at scale 10A, step 0 (€ 3.017 full-time). Over a maximum period of 4 years, you will progress to scale 10A, step 3 (€3.824 full-time). You will also receive an 8% holiday allowance, an 8.3% end-of-year bonus, and a 47% to 72% bonus for working unsocial hours.
• 172 vacation hours per year based on a 36-hour working week. (As of 1 January 2025, you will receive 176 vacation hours).

Radboudumc

The Computational Pathology Group is a research group of the department of Pathology of the Radboud University Medical Center. We are part of the interdepartmental Diagnostic Image Analysis Group (DIAG). We develop, validate and deploy novel medical image analysis methods, usually based on machine learning technology and focusing on computer-aided diagnosis. Application areas include diagnostics and prognostics of breast, prostate and colon cancer. Our group is among the international front runners in the field, where we closely collaborate with clinicians and industry.

Radboudumc
Welcome to Radboud university medical center (Radboudumc), where scientific breakthroughs are born through the curiosity and passion of our collaborating researchers in a vibrant environment. We believe trust and excitement are crucial elements to achieving our goals, and we approach our research as teams and with the utmost rigor to make a significant impact on health and healthcare. Our researchers are driven by their fascination with the biological, psychological, and sociological mechanisms underlying health and healthcare. They collaborate with partners from all over the world to improve health outcomes for all. Radboudumc unites patient care, research, education, and corporate learning, which allows us to approach our mission to shape the health and healthcare of the future in an innovative and person-centered way.

Our ambition is to lead the way in the pursuit of prevention, sustainability, meaningful care. We believe that through our research, we can significantly improve the health and well-being of society. Join us on our mission to make a difference in healthcare. Become a part of our community of gifted researchers, professionals or patient partners who are dedicated to making a real impact on population health and healthcare.

Read what it is like to do a PhD at the Radboud University Medical Center.

Any questions? Or wondering what it is like to work at Radboudumc? Then send an email to Francesco Ciompi, Associate Professor of Computational Pathology. Use the Apply button to submit your application.