Biomedical Imaging Group Rotterdam
The Biomedical Imaging Group Rotterdam (BIGR) is at the forefront of research in medical image analysis & artificial intelligence (AI). We aim to improve efficiency and quality of healthcare by developing innovative AI methods in medical imaging.
We focus on both fundamental and applied research, covering the topics of image analysis, machine learning, image reconstruction, quantitative imaging biomarkers, image-guided interventions, making use of both research data and routine clinical data.
We have a strong outward look: towards other imaging sources, other diagnostic modalities, integrated diagnostics, collaboration with clinical departments. We have strong collaborations with many researchers, clinicians and industry partners.
September 16, 2026
Karen van der Werff published her first paper as first-author
September 8, 2026
Myrthe van Haaften published her latest research
Tumor localization and visualization using magnetic seed tracking and augmented reality
2024 - 2028
WThis student project focuses on developing a multimodal deep learning model to differentiate between etiologies of dementia, specifically Alzheimer’s disease and frontotemporal dementia, using data like brain MRIs and neuropsychological tests. To overcome current limitations in clinical AI, the project will explore advanced data integration methods, such as cross-attention, alongside novel techniques to handle data that is missing not at random due to diagnostic biases.
Medical imaging research repositories commonly rely on XNAT to store and organize imaging datasets and associated metadata. The amounts of data sometimes make it daunting to interpret the data. An AI agent based on Large Language Models (LLMs) can help answer meaningful questions about the data on an XNAT server and perform curation basic tasks. However, before AI agents can interact with XNAT, XNAT’s functionality must first be exposed through a standardized tool interface. XNAT offers a REST-API for programmatic access to the database. To make it easier for python users we created the XNATpy package. But there is currently no mechanism that exposes XNAT/XNATpy in a manner directly consumable by AI agents. One emerging approach is the Model Context Protocol MCP. In this project, we propose to create a MCP layer for XNAT/XNATpy to communicate with an AI agent. To validate functionality, a test agent should be used to answer questions about the data on XNAT the user has access to and help with simple data management tasks.
The aim of this project is to translate an existing deep learning framework for qMRI from synthetic data to real clinical MRI data. The student will retrain and validate the model using data from healthy volunteers, with the goal of moving qMRI closer to clinical acceptance.
In our Group we continously have MSc and BSc thesis/internship projects in various topics, including applied medical image analysis, image guidance in intervention and therapy, neuroimage analysis, quantitative MR reconstruction, eye imaging, prostate and breast cancer analysis, computational population biology, and musculoskeletal image analysis. Check the full list of available projects here, or contact Prof. Stefan Klein for more information.
Biomedical Imaging Group Rotterdam is a part of Erasmus MC
