Statistical modelling of treatment response using AI-derived tumor volumes Researcher Postdoc

We are recruiting a highly motivated postdoctoral researcher with a strong background in statistics and/or mathematical modeling to join a translational research project focused on treatment response modeling in cancer, with an initial focus on pleural mesothelioma. This project leverages a unique large-scale longitudinal imaging dataset and cutting-edge AI-based tumor segmentation tools to quantitatively study tumor dynamics during systemic therapy.

This position offers excellent opportunities to develop and apply advanced statistical models to clinically relevant data, while working in close collaboration with radiologists, oncologists, and biostatisticians. The postdoc will play a central role in developing and validating models that describe tumor growth, treatment response, and resistance dynamics over time, and subsequently, linking these patterns to clinical outcomes and therapeutic strategies within a collaborative research environment at the Netherlands Cancer Institute.

Over the past years, we have developed and clinically validated state-of-the-art in-house AI models for automated tumor segmentation on CT. These models enable accurate, reproducible quantification of total tumor volume at scale and are already being used in clinical decision-making. This places us among the first groups worldwide that can study treatment response using longitudinal volumetric data across thousands of patients, rather than relying on manual diameter-based response criteria.

The postdoc will leverage this unique infrastructure and dataset to develop and validate statistical models that characterize tumor growth, treatment response, and resistance patterns over time, and directly link these insights to clinical outcomes and treatment strategies.

Pleural mesothelioma is a rare malignancy with limited treatment options and highly heterogeneous response to systemic therapy. Current response evaluation methods (e.g. mRECIST) are imprecise and poorly capture the complex growth dynamics of pleural disease. Using AI-derived tumor volumes from routine CT imaging, we can now model treatment response with far greater temporal resolution and biological interpretability.

We have assembled one of the largest longitudinal mesothelioma imaging datasets worldwide (>2,000 patients, >11,000 CT scans, including multiple international clinical trials). Analysis on this dataset with standard mathematical models already reveal distinct response patterns, resistance dynamics, and survival differences between treatments. Thus, the dataset is already curated and ready to be used upon your start date.

We aim to extend and formalize these models, quantify uncertainty and heterogeneity, and connect volumetric response patterns to patient characteristics and treatment mechanisms. The results will feed directly into extensions into other diseases and have the potential to improve clinical decision-making.

Your responsibilities will include:

• Develop and statistically validate models of longitudinal tumor volume dynamics under systemic treatment.

• Fit and compare phenomenological and mechanistic models (e.g. growth–decay mixtures, sensitive/resistant cell population models) to large-scale clinical and trial data.

• Characterize treatment response patterns beyond binary responder/non-responder classifications.

• Quantify parameter uncertainty, identifiability, and robustness in heterogeneous real-world datasets.

• Relate model-derived parameters to treatments, patient characteristics, and clinical endpoints such as overall survival.

• Investigate phenotypic signatures of treatment-dependent versus treatment-independent resistance.

• Contribute to peer-reviewed publications and to the preparation of follow-up (international) grant applications.

• Work closely with radiologists, oncologists, and biostatisticians in a translational setting, where methodological insights can be applied directly to clinical decision-making.

Why the Netherlands Cancer Institute?

At the Netherlands Cancer Institute, we have a shared goal: providing the best care for every patient and every type of cancer. Quite a lot, but not impossible. Here, science and health care join forces towards innovation. We keep finding new ways to help people facing cancer on a global scale. Here we save lives, gain time and quality.

• PhD in statistics, biostatistics, applied mathematics, systems biology, physics, or a closely related quantitative discipline.

• Experience with data analysis and statistical modeling.

• Proficiency in scientific programming: Python or R.

• Ability to work independently in an interdisciplinary clinical research environment.

• Excellent command of English, written and spoken.

Preferred:

• Experience in oncology or biomedical research.

• Experience with survival analysis, joint models, or nonlinear mixed-effects models.

• Familiarity with large observational or clinical trial datasets.

• Interest in translational research with direct clinical impact.

Your development opportunities and employment conditions

The basis for your employment conditions is in accordance with the CLA Hospitals. You will receive from us:

• A contract of 2 years for 36 hours per week;

• A gross monthly salary between €4539,- and € 5395,-, based on a 36-hour working week, in line with FWG 55 and depending on your experience;

• 144 holiday hours and 57 hours of Personal Life Budget, with full-time employment;

• Annual holiday pay of 8.33% and a fixed end-of-year bonus of 8.33%;

• A travel allowance of €0.23 per km;

• Free parking at the Netherlands Cancer Institute. And with our bicycle plan and discount on public transport we also make it attractive for you to leave the car at home;

• A great opportunity in a specialised hospital where you can also continue to learn and grow yourself if you wish: the AVL Academy offers innovative and inspiring education in the field of oncology professional knowledge, skills and personal development;

• Opportunity to exercise during working hours at our Fit Boutiqs;

• An active staff association.

Interested?

We are curious about your talent! Will you be the one to make a difference in the world of cancer care and research? Apply now by using the application (‘solliciteer’) button! Please attach your motivation letter (maximum one page), CV and contact details of two references to the application form. Make sure to include your reference information together with your application documents, as there is no option to submit them separately.

This vacancy is open for applications until the 1st of April.

For further information about the position, please contact Kevin Groot Lipman, Clinical AI Implementation Lead, via k.groot.lipman@nki.nl.

For questions about the application procedure, please contact Pascal van Kippersluis, Recruiter, via p.v.kippersluis@nki.nl.

Please respond to this vacancy only via the application button and not through email.