My lab aims to create explainable and robust AI models for multimodal multi-centre medical data. Our research is deeply rooted in three key areas:

• explainable AI, which seeks to make the reasoning of AI algorithms transparent and understandable;
• privacy-preserving machine learning, aimed at developing techniques that safeguard patient identity while improving the quality of prediction models;
• and out-of-distribution generalization, which ensures that our AI models remain accurate and reliable even faced with data originating from different populations and acquisition settings.

Current team members: 

• Valentina Corbetta (PhD Candidate) - Generalizable and Robust Artificial Intelligence for Multi-center Cancer Data.
• Daan Boeke (PhD Candidate) - AI for immune micro-environment characterization.
• Aniek Eijpe (PhD Candidate) - Explainable AI for Multimodal Life Science Data.
• Jan van Eck (PhD Candidate) - Explaining the language of biology: feature disentanglement and hypothesis discovery for deep learning models.
• Avi Pandey (PhD Candidate) - Unveiling T Cell Dynamics by Monitoring, Evaluating, and Decoding Mechanisms in Cancer Immunotherapy through Cellular Behavior and Shape Analysis.
• Federica Rignanese (Visiting PhD student) - Meta-learning for Multimodal Medical Data.

News: 

Sep 2025 – Aniek, Daan, and I attended MICCAI 2025 in Seoul, South Korea, where our group presented three papers. We had one main conference paper, “Disentangled and Interpretable Multimodal Attention Fusion for Cancer Survival Prediction,” (https://arxiv.org/pdf/2503.16069) and two workshop papers: “Integrating Pathology and CT Imaging for Personalized Recurrence Risk Prediction in Renal Cancer” (https://arxiv.org/pdf/2508.21581) and “Evaluating the Predictive Value of Preoperative MRI for Erectile Dysfunction Following Radical Prostatectomy.” (https://arxiv.org/pdf/2508.03461). I was also part of the organizing team for iMIMIC, the workshop on Explainable AI for Medical Imaging, for another successful edition. 

Oct 2024 - Aniek, Miriam, Valentina, and I attended MICCAI 2024 in Marrakech, Morocco, where we presented three papers on Multi-task Learning (https://arxiv.org/abs/2408.08784), Cross-Modal Segmentation (https://arxiv.org/abs/2408.11733), and Federated Learning (https://arxiv.org/abs/2408.11701). Aniek received the best paper award at the Deep Generative Models workshop for her work, “Enhancing Cross-Modal Medical Image Segmentation through Compositionality.”. We were also part of the organizing team for iMIMIC, the workshop on Explainable AI for Medical Imaging, which was a great success, with a full room and engaging, insightful discussions.

Alumni (Postdoc, PhD): 

• Soufyan Lakbir (Postdoc) - Ordinal Learning for scRNA-seq Data. Now Postdoc at UMC Utrecht. 

• Miriam Cobo (PhD Candidate) - Robust and explainable deep learning for computed tomography-based diagnostic systems (cum laude). 2025. Now Postdoc at University of Cantabria. 

   

Alumni (MSc): 

• Tingyang Jiao (MSc student, UU) - Morphological Cell Classification under Weak Supervision: A Learning from Label Proportions Approach. 2024.
• Nathan Jones (MSc student, VU Amsterdam) - Predicting Erectile Dysfunction after Prostatectomy Using Clinical Data and AI. 2024. 
• Aniek Eijpe (MSc student, UvA) - Disentangled Representation Learning and Cross-Modality Translation for Improving Medical Image Segmentation. 2024. Now a PhD student in the lab. 
• Philip Schutte (MSc student, UvA) - Advancing Collaborative Medical Image Analysis: Federated Learning and Disentangled Representation for
  Privacy-preserving Segmentation. 2024
• Ioanna Gogou (MSc student, UvA) - Self-supervised Learning for Radiology. 2024
• Filipe Campos (MSc student, U Porto) - Conditional Diffusion Models for Visual Anonymization of Medical Case-based Explanations. 2024
• Rita Mendes (MSc student, U Porto) - Exploring Causal Learning in Privacy-Preserving Medical Case-based Explanations. 2024 
• Margarida Vieira (MSc student, U Porto) - Classify and Protect - how to generate privacy-preserving explanations in illegal pornography detection. 2024
• Melanie Groeneveld (MSc student, VU Amsterdam) - Predicting Knee Osteoarthritis Progression using Multi-Task Learning by Embedding Knowledge about the
  Femorotibial Angle. 2024
• Laura Latorre (MSc student, VU Amsterdam) - Towards Case-based Interpretability for Federated Learning Models. 2023.
• Isabela Miranda (MSc student, U Porto) - Integrating Anatomical Prior Knowledge for Increased Generalizability in Breast Cancer Multi-center Data. 2023.
• Daniel Silva (MSc student, U Porto) - Disentanglement Representation Learning for Generalisability in Medical Multi-Centre Data. 2023.