Author

Philippe Poulin

Université de SherbrookeORCID 0000-0002-0116-4352Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Signature Assays, Organisms & Methods

Click to filter · or open tag

Research Focus:benchmarking· 2 Approach:deep learning· 1 Research Focus:dimensionality reduction· 1 Organism:human· 1 Assay:imaging· 1 Approach:machine learning (classical)· 1 Assay:multiome· 1 Approach:statistical model· 1

Frequent Co-Authors

Maxime DescoteauxiD· 3 shared François RheaultiD· 2 shared Guillaume TheaudiD· 2 shared Laurent PetitiD· 2 shared Alessandro DaducciiD· 1 shared Alessandro DE BENEDICTISiD· 1 shared Arnaud BoréiD· 1 shared Chantal M. W. TaxiD· 1 shared

Activity by Year

2017-2022 · peak 1/yr

Co-Author Collaboration Network

10 top collaborators · 39 mutual co-author links

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

3 shared papersNeuroscience

Maxime DescoteauxORCID

Mutual co-authors in cluster

Author profile →

3 papers

Recent·Most cited

TractoInferno: A large-scale, open-source, multi-site database for machine learning dMRI tractography

Philippe Poulin, Guillaume Theaud, François Rheault, Etienne St‐Onge, Arnaud Boré, Emmanuelle Renauld, Louis De Beaumont, Samuel Guay, Pierre‐Marc Jodoin, Maxime Descoteaux

TractoInferno provides a large-scale, multi-site database for benchmarking machine learning tractography methods using standardized data and evaluation protocols.

Scientific Data · Nov 25, 2022Peer-reviewedNeuroscience

Tractostorm: Rater reproducibility assessment in tractography dissection of the pyramidal tract

François Rheault, Alessandro DE BENEDICTIS, Alessandro Daducci, Chiara Maffei, Chantal M. W. Tax, David Romascano, Eduardo Caverzasi, Félix C. Morency, Francesco Corrivetti, Franco Pestilli, Gabriel Girard, Guillaume Theaud, Ilyess Zemmoura, Janice Hau, Kelly Glavin, , Maxime Descoteaux

This study assesses the reproducibility of manual segmentation of the pyramidal tract in diffusion MRI tractography across experts and non-experts, finding voxel-wise measures more reproducible than streamline-wise ones.

bioRxiv · Apr 30, 2019 · PreprintNeuroscience

Learn to Track: Deep Learning for Tractography

Philippe Poulin, Marc-Alexandre Côté, Jean‐Christophe Houde, Laurent Petit, Peter Neher, Klaus Hermann Maier-Hein, Hugo Larochelle, Maxime Descoteaux

This paper applies deep learning to fiber tractography, showing models can generate streamlines from DWI data and outperform traditional methods in accuracy and false connection control.

Lecture notes in computer science · Jan 1, 2017Peer-reviewedNeuroscience