I am leading the independent research group for Machine Learning in Medical Image Analysis at the University of Tübingen as part of the Cluster of Excellence - Machine Learning for Science.
My research focuses on developing machine learning methodologies that bridge the gap between ML theory and clinical applications. Specifically, I am interested in technologies facilitating human-AI collaboration, as well as using probabilistic modelling to discover disease effects and connections between clinical variables. I am pursuing those goals along the following directions:
- Safety and uncertainty: In medical image analysis, confidently predicting something false can have devastating consequences. Hence, it is crucial to develop machine learning algorithms that reflect the various uncertainties in the medical image analysis pipeline and can help clinical practitioners to safely use this technology in practice.
Interpretable machine learning: It is clear that artificial intelligence is in no position to replace clinicians and will not be for a long time, if ever. Therefore, we must develop techniques to allow clinicians and patients to optimally interface with machine learning algorithms. One important aspect of this question is making algorithmic decision processes transparent.
Human-in-the-loop systems: Humans are an essential component in every ML system in multiple ways: they provide training data, they select and train the model, they operate the system. Thus it makes sense to put emphasis on the human role in this process for instance by developing techniques for reducing annotation effort, active learning, and interactive predictions.
- Discovering effects in big medical data: Recent advances in probabilistic machine learning techniques offer a unique opportunity to explore datasets with ten thousands of images (such as the German National Cohort Study) to better understand disease processes.
See more details in the Research Interests section.
Before joining the University of Tübingen, I was working in a senior research engineering role at PTC Vuforia, where I focused on research and development of machine learning technology for augmented reality applications. Prior to this, I was a Post-doc at the Biomedical Image Computing Group at ETH Zürich working with Prof. Ender Konukoglu, and before in the Biomedical Image Analysis Lab with Prof. Daniel Rueckert. I completed my PhD in 2016 under the joint supervision of Prof. Andy King and Prof. Daniel Rueckert at King’s College London in the School of Biomedical Engineering & Imaging Sciences (link to PhD thesis). I obtained my Master’s degree in Biomedical Engineering and my Bachelor’s degree in Information Technology and Electrical Engineering from ETH Zürich.
April 2021: We have two new openings for PhD students and a post-doc! See the jobs page for more details. Oct 2020: You can apply for PhD positions in our group through the International Max Planck Research School for Intelligent Systems (IMPRS-IS). The deadline is Nov 2, 2020. Get in touch for details how to apply to work with us! More details here.
- Oct 2020: Accepted position as Independent Research Group Leader at the University of Tübingen