Research statement
In the past decade, the interactions between parts of a biological system have emerged as a central concept in biomedical sciences. I am convinced that exploiting this in practice by coupling graph-based representations with machine learning and statistics is key to yielding great predictive power for biomedical data. Compared with other diagnostic modalities, such as protein levels in the blood, imaging offers the unique benefit of spatial localization. The main goal of my research is thus to develop advanced machine learning methods to jointly model imaging data, omics data, and clinical data to yield improved clinical decision support. The applications include diagnosis, differential diagnosis, prognosis and forecasting, subtyping, and treatment planning.
Bio sketch
I am currently a principal investigator (responsable de recherche) and senior lecturer (MER1) at the Department of Radiology of the Lausanne University hospital (CHUV) and University of Lausanne (Faculty of Biology and Medicine), where I head the Translational Machine Learning Laboratory. I also head the Imaging for Precision Medicine Section of the Data Science Module of the CIBM Center for Biomedical Imaging.
I was previously Clinical Research Lead at Siemens Healthcare Switzerland’s Advanced Clinical Imaging Technology, a joint position with the Department of Radiology, Lausanne University Hospital. Before that, I was a Marie Curie Fellow with my project project “Modelling and Inference on brain Networks for Diagnosis” (#299500), jointly affiliated to the FINDlab at Stanford University and LabNIC at the University of Geneva. Between 2009 and 2012, I was a post-doctoral research fellow in the Medical Image Processing Lab, a joint position between the Ecole Polytechnique Fédérale de Lausanne (EPFL), Institute of Bioengineering, and the University of Geneva‘s Faculty of Medicine, Radiology and Medical Informatics Department. Prior to joining the group, I co-founded the information engineering consultancy PatternLab.
I obtained my Ph.D. in 2007 at EPFL in the laboratory of the Dalle Molle Institute for Perceptual Artificial Intelligence (LIDIAP), part of the now-fragmented Signal Processing Institute.
I have published over 90 peer-reviewed publications, with a focus on modelling and inference for complex multimodal biological data, in particular magnetic resonance imaging data and its combination with omics data. My perennial interest in on graph-based machine learning approaches, where all data is first represented as a graph, and machine learning approaches are applied to form prediction with graphs. My current areas of focus are stroke, cardiac structure and (dys)function, and brain cancer, with ongoing efforts to develop the necessary tools and infrastructure to access and process messy, hospital-scale data.
Awards and honours
- Leenaards Prize for translational Biomedical Research 2023 (with Indrit Bègue and Camilla Bellone)
- International Stroke Conference Paul Dudley White International Scholar Award 2021
- Int. Soc. For Magnetic Resonance Imaging (ISMRM) Magna Cum Laude abstract award 2021
- Mass Challenge Swizerland Pitcher of the Year 2016
- Volker Henn Best Poster Award at the Swiss Society for Neuroscience Annual Meeting 2010
- IEEE Best student paper award at ICASSP 2005
Service
I am involved in organising several workshops, including the European Conference on Machine Learning workshop on ML in Pharma and Healthcare (co-chair) and the Network Neuroscience Satellite at Network Science 2023. I’m also a steering committee member of the Machine Learning for Clinical Neuroimaging workshop at MICCAI, and a program board member for the Medical Imaging with Deep Learning (MIDL) conference.
Previously, I have been an organising committee member for the Int. Workshop on Pattern Recognition in Neuroimaging (PRNI) series since the beginning, including Istanbul 2010 (chair), Seoul 2011 (programme chair), London 2012 (programme chair), Philadelphia 2013 (steering committee chair), Tübingen in 2014 (steering committee chair), Stanford in 2015 (finance & sponsorship chair), Trento in 2016 (steering committee member), and Toronto in 2017 (steering committee member).
I have served as a project reviewer for the UK’s Medical Research Council and Engineering and Physical Sciences Research Council, France’s Fondation pour la recherche médicale, Netherland’s Organisation for Scientific Research, and the ETH Domain Strategic Focus Area Personalized Health and Related Technologies in Switzerland.
I serve as a journal reviewer in Engineering (IEEE Trans. on Pattern Analysis and Machine Intelligence, Proceedings of the IEEE, IEEE Trans. on Medical Imaging, SIAM Journal on Imaging Sciences, IEEE Trans. on Biomedical Engineering, Pattern Recognition, IEEE Signal Processing Letters, and others), Brain imaging (Nature Neuroscience, Cerebral Cortex, Human Brain Mapping, NeuroImage, American Journal of Neuroradiology, Neuroradiology, Brain Structure and Function, Brain Topography, Journal of Neuroscience Methods, and others),and topics in modelling of biological systems (Nature Communications, PNAS, PLoS Computational Biology, PLoS One).
I have also been a conference programme committee member in neuroimaging (NIPS Workshop on Machine Learning and Interpretation in NeuroImaging, Mathematical Methods for Brain Connectivity, Organisation for Human Brain Mapping Annual Meeting), signal/image processing (IEEE Int. Symposium on Biomedical Imaging, IEEE Int. Conference on Image Processing, Wavelets & Sparsity, IEEE Int. Conference on Acoustics, Speech, and Signal Processing, European Signal Processing Conference, and others), and machine learning (Neural Information Processing Systems (NIPS/NeurIPS), International Conference on Machine Learning (ICML), IAPR International Conference on Pattern Recognition (ICPR)).