Edouard Duchesnay

Edouard Duchesnay

Research Director, Prof. in Machine Learning, Head of GAIA Lab.

AI, Machine Learning, Neuroimaging and Psychiatry

Research Director, Prof. in Machine Learning, Head of GAIA Laboratory for brain imaging and data science at NeuroSpin, CEA, Université Paris-Saclay, France.

As a leader of the team “Signatures of brain disorders” at NeuroSpin, CEA, Université Paris-Saclay, France, I supervise the design of machine learning and statistical models to uncover neural signatures predictive of clinical trajectories in psychiatric disorders. To unlock the access to data required by learning algorithms, I oversee the data management, calculation, and regulation (GDPR) of large-scale national and European initiatives.

Keywords

Machine Learning – Deep Learning – Statistics – Computer Vision – Neuroimaging – Scientific Computing – Datamanagement

Experience

Education

Projects

  • 2024-2029: Data analysis, computing and data management for IHU-ICE: Institut Hospitalo-Universitaire-Institut du Cerveau de l’Enfant Robert Debré. Leaders: R Delorme, G Dehaene, T Bourgeron.

  • 2023-2028: Data analysis, large-scale computing and management for (PEPR Santé Mentale) PROPSY: PROgram-project in Precision pSYchiatry. Leader: M Leboyer. Team budget: 4.6M€.

  • 2022-2026: Data analysis for RHU FAME: Improving FAMily members’ Experience in the ICU. Leader: E Azoulay. Team budget: 547k€.

  • 2020-2024: Leader of Artificial Intelligence (AI) Chair. Big2small, Transfer Learning from Big Data to Small Data: Leveraging Psychiatric Neuroimaging Biomarkers Discovery. Budget: 543k€.

  • 2019-2026: Data analysis for RHU-PsyCARE. Preventing psychosis through personalized care. PI: MO Krebs. Team budget: 715k€.

  • 2018-2023: WP leader of data analysis, computing and management for H2020 horizon europe R-LiNK. Optimizing response to Li treatment through personalized evaluation of individuals with bipolar I disorder. Leader: F Bellivier. Team budget: 800k€.

  • 2014-2018: BIP-Li7 (ANR-14-CE15-0003). Therapeutic Lithium response Bipolar Disorders and brain Lithium-7 NMR Spectroscopy Imaging at 7 Tesla. PI: F Bellivier, WP leader:F Boumezbeur. Team budget: 280k€.

  • 2011-2015: WP leader of data analysis for EU FP6-ERA-NET-NEURON MESCOG: Mechanisms of Small Vessel-Related Brain Damage and Cognitive Impairment: Integrating Imaging Findings from Genetic and Sporadic Disease. PI: M Dichgans. Team budget: 195k€.

  • 2012-2016: WP leader of image analysis for BRAINOMICS (ANR-10-BINF-04). Methodological and software solutions for the integration of neuroimaging and genomic data. PI: V Frouin. Team budget: 800k€.

  • 2010-2013: Leader (with A Roche) of Karamétria (ANR-09-BLAN-0332): A unified framework for feature-based morphometry of the brain. Team budget: 200k€.

  • 2007-2010: WP leader of data analysis for AGIR (ANR-07-NEUR-0001): AGIR – Autism: Genetic and Imaging Research. PI: M. Zilbovicius. Team budget: 150k€.

  • 2007-Present: Contribution to the CATI platform, a national platform created by the French Alzheimer plan in 2011 to support multicenter neuroimaging studies (9M€ grant). Leader: JF Mangin.

Publications & Scientific Impact

Bibliometry

  • Publications: 131(a), 93(b)
  • Total Number of Citations: 95,150(a) 42,237(b)
  • H-Index: 36(a), 26(b)

(a) Web of Science, (b) Google scholar

Publications

Selection of Publications

  • R. Louiset, E. Duchesnay, B. Dufumier, A. Grigis, and P. Gori (2024) “SepCLR: Separating common from salient patterns with Contrastive Representation Learning”, in The Twelfth International Conference on Learning Representations (ICLR) 2024
  • B. Dufumier, C. A. Barbano, R. Louiset, E. Duchesnay, and P. Gori (2024) “Integrating Prior Knowledge in Contrastive Learning with Kernel”, in 40th International Conference on Machine Learning (ICML) 2023
  • A. Iftimovici, J. Bourgin, J. Houenou, O. Gay, A. Grigis, J. Victor, B. Chaumette, M.-O. Krebs, E. Duchesnay, and ICAAR-plus Study Group. (2023) “Asynchronous neural maturation predicts transition to psychosis”, Psychiatry Clin Neurosci
  • B. Dufumier, A. Grigis, J. Victor, C. Ambroise, V. Frouin, and E. Duchesnay (2022) “OpenBHB: a Large-Scale Multi-Site Brain MRI Data-set for Age Prediction and Debiasing”, NeuroImage
  • J. Stout, F. Hozer, A. Coste, F. Mauconduit, N. Djebrani-Oussedik, S. Sarrazin, J. Poupon, M. Meyrel, S. Romanzetti, B. Etain, C. Rabrait-Lerman, J. Houenou, F. Bellivier, E. Duchesnay, and F. Boumezbeur (2020) “Accumulation of Lithium in the Hippocampus of Patients With Bipolar Disorder: A Lithium-7 Magnetic Resonance Imaging Study at 7 Tesla”, Biol Psychiatry
  • F. Hadj-Selem, T. Löfstedt, E. Dohmatob, V. Frouin, M. Dubois, V. Guillemot, and E. Duchesnay (2018) “Continuation of Nesterov’s Smoothing for Regression With Structured Sparsity in High-Dimensional Neuroimaging”, IEEE Transactions on Medical Imaging
  • A. de Pierrefeu, T. Lofstedt, F. Hadj-Selem, M. Dubois, R. Jardri, T. Fovet, P. Ciuciu, V. Frouin, and E. Duchesnay (2017) “Structured Sparse Principal Components Analysis With the TV-Elastic Net Penalty”, IEEE Transactions on Medical Imaging
  • A. de Pierrefeu, T. Fovet, F. Hadj-Selem, T. Löfstedt, P. Ciuciu, S. Lefebvre, P. Thomas, R. Lopes, R. Jardri, and E. Duchesnay (2018) “Prediction of activation patterns preceding hallucinations in patients with schizophrenia using machine learning with structured sparsity”, Hum. Brain Mapp.
  • F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay (2012) “Scikit-learn: Machine Learning in Python”, JMLR

Teaching

I wrote a course on Statistics and Machine Learning in Python, github: Jupyter notebooks and python sources and pdf.

I deliver lectures on machine learning/statistics in:

  • 2019-now: Introduction to AI: main algorithms of machine learning in Master 2 radiophysique médicale Paris-Saclay University.
  • 2018-now: Machine learning in Master 2 Modelisations Statistiques Economique & Financières MoSeF, Panthéon Sorbonne Paris 1 University, head: Rania Hentati Kaffel.
  • 2015-now: Machine learning in Master 2 Innovation, marché et science des données IMSD, Paris-Saclay University, head: Ekaterina Kalugina.
  • 2017-2020: Biostatistics 3rd year of CentralSupelec, Paris-Saclay University, head: Arthur Tenenhaus.
  • 2019-2020: Machine learning in 2nd & 3rd years of EPITA, Kremlin-Bicètre, Image processing option, head: Elodie Puybareau and Guillaume Tochon.
  • 2016-2017: Data analysis in Master 1 Mathématiques et applications, option “Ingénierie mathématique pour les sciences du vivant“, Paris Descartes University, head: Etienne Birmele.

Supervision experience

Ph.D.s

  • 2022-now: Thibault Dupont, co-supervised with Elie Azoulay and Julie Bourgin.
  • 2022-now: Sara Petiton, co-supervised with Antoine Grigis.
  • 2022-now: Pierre Auriau, co-supervised with Pietro Gori, Antoine Grigis and Jean-François Mangin.
  • 2020-now: Robin Louiset, co-supervised with Pietro Gori and Antoine Grigis.
  • 2019-2022: Benoit Dufumier, co-supervised with Arthur Tenenhaus, Pietro Gori and Antoine Grigis.
  • 2019-2021: Anton Iftimovici, co-supervised with Marie-Odile Krebs.
  • 2016-2019: Amicie de Pierrefeu, co-supervised with Philippe Ciuciu.
  • 2008-2012: Edith Lefloch, co-supervised with Vincent Frouin.
  • 2009-2011: Cecilia Damon together with Jean-Baptiste Poline.

Post-docs

  • 2017-2019: Pauline Favre, Post-doc, co-supervised with JF Mangin and J. Houenou. Now researcher at INSERM U955, team Translational Neuro-Psychiatry.
  • 2016: Pietro Gori, Post-doc together with JF Mangin and J. Houenou. Now Assistant Professor at Télécom ParisTech, Paris, France.
  • 2013-2015 Fouad Hadj Selem, Post-doc. Now research scientist at the Energy Transition Institute: VeDeCoM, France.
  • 2013-2015: Tommy Lofstedt, Post-doc. Now associate professor at Umea University, Sweden.
  • 2013-2014: Mathieu Dubois, Post-doc.

Engineers

  • 2023-now: Raphael Vock, co-supervised with Antoine Grigis.
  • 2022-now: Bérangère Dollé, co-supervised with Antoine Grigis.
  • 2021-now: Loic Dorval, co-supervised with Antoine Grigis.
  • 2019-2022: Julie Victor, co-supervised with Antoine Grigis.
  • 2014: Clémence Pinaud, Engineer trainee.
  • 2013-2014: Jinpeng Li, Research Engineer.

Patent

PCT/FR2010/050431: Inventors: Duchesnay, Edouard; Paillere, Marie-Laure; Cachia, Arnaud; Martinot, Jean-Luc; Artiges, Eric. ”Method for Developing an Information Prediction Device, Use Thereof, and Corresponding Storage Medium and Apparatus“.

Bio (IEEE style)

Edouard Duchesnay is a research director in data science at NeuroSpin, CEA, Paris-Saclay University, France. Since 2003, he has been designing machine learning models to discover brain imaging signatures of mental disorders. He explored dimension reduction and regularization strategies to overcome the “curse of dimensionality” caused by many neuroimaging measurements. In 2019, he obtained a chair in Artificial Intelligence to develop transfer learning algorithms to bridge the gap between big (heterogeneous) and small (homogeneous) datasets. He received his Ph.D. in signal and image processing in 2001 and M.S. in 1998 from Rennes 1 University (France). In 1997, he obtained his M.S. degree in software engineering from École Pour l’Informatique et les Techniques Avancées (France).