Scientific publications (Google Scholar)
Finding the best channel for tissue segmentation in whole-slide images
Proc. 19th International Symposium on Medical Information Processing and Analysis, 2023
Assessing Local Descriptors for Feature-Based Registration of Whole-Slide Images
Proc. 19th International Symposium on Medical Information Processing and Analysis, 2023
Panoptic Quality should be avoided as a metric for assessing cell nuclei segmentation and classification in digital pathology
Scientific Reports 13 (8614)
Impact of real-world annotations on the training and evaluation of deep learning algorithms in digital pathology
PhD dissertation. Publicly defended on October 25th, 2022.
Shortcomings and areas for improvement in digital pathology image segmentation challenges
Computerized Medical Imaging and Graphics 103, 2023
Evaluating participating methods in image analysis challenges: lessons from MoNuSAC 2020
Preprint, 2022 (currently under review)
Comments on "Monusac2020: A Multi-Organ Nuclei Segmentation and Classification Challenge"
IEEE Trans. Medical Imaging, 2022
Processing multi-expert annotations in digital pathology: a study of the Gleason 2019 challenge
Proceedings Volume 12088, 17th International Symposium on Medical Information Processing and Analysis (SIPAIM)
Strategies to Reduce the Expert Supervision Required for Deep Learning-Based Segmentation of Histopathological Images.
Frontiers in Medicine (6). 2019.
SNOW: Semi-Supervised, NOisy and/or Weak Data for Deep Learning in Digital Pathology.
IEEE 16th Int'l Symposium on Biomedical Imaging (ISBI 2019) (pp. 1869-1872).
Artifact Identification in Digital Pathology from Weak and Noisy Supervision with Deep Residual Networks.
4th Int'l Conference on Cloud Computing Technologies and Application (CloudTech'18).
Unsupervised vehicle detection in traffic scene using distributed one class classifiers.
Int'l Symposium on signal, Image, Video and Communications. 2012.
Other publications
Comprendre et évaluer les intelligences artificielles
Séminaire donné au Skeptics in the Pub Liège (décembre 2023)
Intelligence artificielle: une nouvelle ère?
Séminaire donné en faculté de Droit (mars 2023)
Aller plus loin.... sans se perdre: la zone de défis.
Le Mag Anim' #13 - Mars 2019
2xRien - Un Blog (opinions)
Research Blog - Deep Learning in Digital Pathology
Work Experience
November 2022 - Present
Postdoctoral researcher, LISA, University of Brussels
Multimodal in-vivo to ex-vivo image registration for preclinical studies in protontherapy. Part of the Protherwal project of the Walloon region.
November 2015 - October 2022
Teaching Assistant and PhD Student, LISA, University of Brussels
Thesis title: Impact of real-world annotations on the training and evaluation of deep learning algorithms in digital pathology.
September 2013 - October 2015
Developper, Kisano Belgium S.A.
Web-based solutions Teleradiology Health information technologies
September 2011 - August 2013
Research Engineer, LISA Image, University of Brussels.
Image processing Machine learning Video analysis
August 2010 - November 2010
Intranet Patient flow & appointments Database
Education
- 2022: PhD in biomedical engineering, University of Brussels (ULB). [ Dissertation]
- 2012: International Computer Vision Summer School (ICVSS 2012) in Sicily, Italy (15-21 July 2012).
- 2009-2011: Master in Biomedical Engineering (Medical Imaging and Informatics), University of Brussels (ULB)
- 2006-2009: Bachelor in Engineering, University of Brussels (ULB)
- 2006: Certificat d'Études Secondaires Supérieures, section Latin-Mathématiques, Athénée Émile Bockstael, Brussels.
Other activities
- 2010 - Present: Trainer, Scouts et Guides Pluralistes.
- 2014 - 2016: Group Leader, 164th Unit, Scouts et Guides Pluralistes.
- 2006 - 2011: Youth Leader (Cub Scouts), Les Scouts Pluralistes.
- 2006 - 2011: Board of European Students of Technology member. Local IT Responsible, ULB (2006-2008) ; local vice-president, ULB (2007-2009).
- 2009: Youth leader certification, Fédération Wallonie-Bruxelles.
Languages
- French: mother tongue
- English: fluent