Curriculum vitae - Projects & Research Interests - Publications - Software - Conference Calendar - Students - Misc
My personal research interests are in image informatics (in particular "bioimage informatics" and digital pathology), machine learning, computer vision, big data, open science.
In 2010, I initiated the CYTOMINE research project which lead to the development of the CYTOMINE open-source software platform (Marée et al., Bioinformatics 2016), a "Google Maps"-like rich internet application for remote visualization, annotation and automated analysis of high-resolution, multi-gigapixels images. It is now used in various domains (including digital pathology) by various entities around the world. In addition to ongoing research at University of Liège, we created Cytomine SCRL FS, a not-for-profit cooperative company to provide services on top of the open-source software.
More recently we are focusing on designing methods for multispectral/multimodal data sources, benchmarking, and user behavior analytics (see CYTOMINE research project page).
This research is about the design of generic methods for automatic image classification, retrieval, interest point detection, and semantic segmentation.
Indeed, as potential applications of image recognition technologies are multidinous, we seek to develop general-purpose methods for the recognition of various types
of images that share some visual regularities, without relying on too strong assumptions about patterns to recognize and acquisition
conditions, and without having to rely on domain experts to design specific features.
This book chapter (2013) summarizes our work where we combine ensemble of randomized decision trees with random extraction of subwindows (square patches) described by their raw pixel values. We are conducting large-scale empirical studies on several recognition datasets to better identify influential design choices and draw general guidelines for future use, and to further increase robustness of our approaches. See e.g. our image classification paper in Pattern Recognition Letters (2016) or our interest point detection paper in Nature Scientific Reports (2018). More recently, we are trying to combine ideas from tree-based methods with deep learning methods, see e.g. our CVPR-CVMI paper (2018).
Between January 2005 and October 2014, I was the GIGA Bioinformatics platform manager (scientific head: Prof. L. Wehenkel). In close collaboration with the Bioinformatics and Modeling research unit, this platform offers software development and data analysis services to academic (within the GIGA research center and beyond) as well as to industrial researchers. Its services include classification of biological/biomedical data (SELDI mass spectra, microarrays, clinical databases, ...) obtained from various medical instrumentation based on machine learning methods. This activity lead to co-authorship of several journal papers (in Journal of Immunology, Proteomics, Annals of the rheumatic diseases, ...) in various application domains (inflammatory diseases, cancer, ...).
I'm very much in favor of basic principles of open science (open access, open data, open source, open hardware) although I still have much to learn about it.