Specialization
Focus of research
**CALL FOR INTERNSHIP OPPORTUNITY**
Description
Introduction Radiotherapy (RT) is among the primary local treatment options for intracranial tumors, but its effects on healthy(-appearing) brain tissue, which ultimately affects the patients’ quality-of-life (QoL) and survival, are not well known. Previous studies have quantified changes in brain tissue due to RT using different approaches such as tissue segmentation or similar quantification methods [1–3]. However, these methods rely on existing MRIs, limiting their ability to forecast the effects of RT dose on the patient's future tissue changes and therefore on QoL. In one of our studies, we focused on quantifying the effects of radiotherapy on patients’ QoL using a BrainAGE score derived from MRI [4]. By predicting the post-treatment images, one could provide feedback for treatment planning as well as quantify the potential follow-up QoL of the patients. These predictions only require the dose distribution and the pretreatment status of the patient, which include clinical description (age, sex, type of tumor, etc.) and the planning MRIs. In patients with Alzheimer's disease, diffusion models have already been developed to predict morphological changes over time in image format have already been developed [5]. Yet, such advancements have not been made in the context of RT. However, since RT-induced brain changes occur more rapidly than those in Alzheimer's disease, it should be even more feasible to capture these changes in the RT-affected brain.
Potential research projects
1 – Develop generative AI models for post-radiotherapy MRI generation for any follow-up timepoint
2 – Further development of the BrainAge model
3 – Continuation of previous efforts in quantifying the effect of RT on the human brain
4 – Synthetic generation of missing contrast MRIs
5 – Tumor and tissue segmentation from arbitrary contrast MRI
6 – Open discussion on any similar project related to image analysis and brain radiotherapy.
Do you have an amazing idea? Let's work on it together!
What we offer
Clinically motivated projects with technical supervision • Weekly 1-on-1 sessions and group meetings with fellow students • You will learn, write, code and present – never a dull moment!
What we expect
Participate in a wide-ranging research initiative focused on brain cancer treatment outcomes • Collaboration in a multidisciplinary team with experts from both technical and clinical fields • Knowledge of ML, data science, computer vision, modelling – you will handle data/images and analyze it accordingly • A keen interest in medical imaging. Knowledge of medical imaging is an advantage but not required. Don't have any previous experience? No problem! • Attend research meetings, seminars, group meetings, etc. within the topic of radiotherapy • Contribute to the preparation of research articles, depending on the internship's duration and success.
Want to do a PhD later on? Increase your chances and gain experience by writing a research article now!
In practice • Duration: 5–9 months (full-time) • Location: Amsterdam UMC, VUmc location, Department of Radiation Oncology (De Boelelaan) + remote access • Start date: Flexible • Application: Send CV to [s.david@amsterdamumc.nl] + whatever you think is important to show or mention
Check out the thesis of previous UvA AI and Data science master students
2024
Prediction of morphological changes in MRI for brain radiotherapy patients utilizing generative AI techniques - https://scripties.uba.uva.nl/search?id=record_55773 (Grade 9) This work won the UVA ‘Thesis of the Year’ award from the Faculty of Medicine (2025)
2025
Pixels to Perception: Loss Function Exploration in Diffusion Models for Post-Radiotherapy Brain MRI Generation - https://scripties.uba.uva.nl/search?id=record_56142 (Grade 9)
Generating 3D Post Radiotherapy MRIs for Patients with Brain Metastases - https://scripties.uba.uva.nl/search?id=record_56143 (Grade 9)
Machine Learning-based Prediction of Quality of Life in Patients with Brain Metastases using Brain Disconnectome Data - https://scripties.uba.uva.nl/search?id=record_56677
Incorporating the Brain Disconnectome and Dose into Survival Prediction Models for Radiotherapy Patients - https://scripties.uba.uva.nl/search?id=record_56693
Modeling Volumetric Changes in Brain Tissue after Radiotherapy - https://scripties.uba.uva.nl/search?id=record_56496
References
Nagtegaal SHJ, David S, Snijders TJ, Philippens MEP, Leemans A, Verhoeff JJC. Effect of radiation therapy on cerebral cortical thickness in glioma patients: treatment-induced thinning of the healthy cortex. Neuro-Oncol Adv. 2020;2.
Nagtegaal SHJ, David S, Philippens MEP, Snijders TJ, Leemans A, Verhoeff JJC. Dose-dependent volume loss in subcortical deep grey matter structures after cranial radiotherapy. Clin Transl Radiat Oncol. 2021;26:35–41.
Nagtegaal SHJ, David S, van Grinsven EE, van Zandvoort MJE, Seravalli E, Snijders TJ, et al. Morphological changes after cranial fractionated photon radiotherapy: Localized loss of white matter and grey matter volume with increasing dose. Clin Transl Radiat Oncol. 2021;31:14–20.
Huisman SI, van der Boog ATJ, Cialdella F, Verhoeff JJC, David S. Quantifying the post-radiation accelerated brain aging rate in glioma patients with deep learning. Radiother Oncol. 2022;175:18–25.
Dhinagar NJ, Thomopoulos SI, Laltoo E, Thompson PM. Counterfactual MRI Generation with Denoising Diffusion Models for Interpretable Alzheimer’s Disease Effect Detection. 2024 46th Annu Int Conf IEEE Eng Med Biol Soc EMBC [Internet]. 2024 [cited 2025 Aug 28]. p. 1–6. Available from: https://ieeexplore.ieee.org/document/10782737