Portrait of Julien Cohen-Adad

Julien Cohen-Adad

Associate Academic Member
Associate Professor, Polytechnique Montréal, Electrical Engineering Department
Adjunct Professor, Université de Montréal, Department of Neuroscience
Research Topics
Medical Machine Learning
Website
Google Scholar
X

Biography

Julien Cohen-Adad is a professor at Polytechnique Montréal and the associate director of the Neuroimaging Functional Unit at Université de Montréal. He is also the Canada Research Chair in Quantitative Magnetic Resonance Imaging.

His research focuses on advancing neuroimaging methods with the help of AI. Some examples of projects are:

- Multi-modal training for medical imaging tasks (segmentation of pathologies, diagnosis, etc.)

- Adding prior from MRI physics to improve model generalization

- Incorporating uncertainty measures to deal with inter-rater variability

- Continuous learning strategies when data sharing is restricted

- Bringing AI methods into clinical radiology routine via user-friendly software solutions

Cohen-Adad also leads multiple open-source software projects that are benefiting the research and clinical community (see neuro.polymtl.ca/software.html). In short, he loves MRI with strong magnets, neuroimaging, programming and open science!

Current Students

Rohan Banerjee
Master's Research - Polytechnique Montréal
Co-supervisor :
Gauthier Gidel
Website
Github
Google Scholar
Pierre Louis Benveniste
PhD - Polytechnique Montréal
Co-supervisor :
Hervé Lombaert
Website
Github
Google Scholar
Armand Collin
PhD - Polytechnique Montréal
Github
Thomas Dagonneau
Master's Research - Polytechnique Montréal
Github
Naga Karthik Enamundram
PhD - Polytechnique Montréal
Co-supervisor :
Sarath Chandar
emvnagakarthik@gmail.com
Website
Github
Google Scholar
Nilser Laines Medina
PhD - Polytechnique Montréal
Nathan Molinier
PhD - Polytechnique Montréal
Github
Kalum Ost
Collaborating researcher
Simon Queric
Research Intern - Polytechnique Montréal
Github
Abel Salmona Salmona
Research Intern - Polytechnique Montréal
abel.salmona@gmail.com
Github
Julien Thouveny
Master's Research - Université de Montréal
Arthur Toulouse
Master's Research - Polytechnique Montréal
Github
Jan Valosek
Postdoctorate - Polytechnique Montréal
Website
Github
Google Scholar

Publications

Rapid simultaneous acquisition of macromolecular tissue volume, susceptibility, and relaxometry maps
Fang Frank Yu
Susie Y. Huang
T. Witzel
Ashwin S. Kumar
Congyu Liao
Tanguy Duval
Julien Cohen-Adad
Berkin Bilgic
Purpose A major obstacle to the clinical implementation of quantitative MR is the lengthy acquisition time required to derive multi-contrast… (see more) parametric maps. We sought to reduce the acquisition time for quantitative susceptibility mapping (QSM) and macromolecular tissue volume (MTV) by acquiring both contrasts simultaneously by leveraging their redundancies. The Joint Virtual Coil concept with generalized autocalibrating partially parallel acquisitions (JVC-GRAPPA) was applied to reduce acquisition time further. Methods Three adult volunteers were imaged on a 3T scanner using a multi-echo 3D GRE sequence acquired at three head orientations. MTV, QSM, R2*, T1, and proton density maps were reconstructed. The same sequence (GRAPPA R=4) was performed in subject #1 with a single head orientation for comparison. Fully sampled data was acquired in subject #2, from which retrospective undersampling was performed (R=6 GRAPPA and R=9 JVC-GRAPPA). Prospective undersampling was performed in subject #3 (R=6 GRAPPA and R=9 JVC-GRAPPA) using gradient blips to shift k-space sampling in later echoes. Results Subject #1’s multi-orientation and single-orientation MTV maps were not significantly different based on RMSE. For subject #2, the retrospectively undersampled JVC-GRAPPA and GRAPPA generated similar results as fully sampled data. This approach was validated with the prospectively undersampled images in subject #3. Using QSM, R2*, and MTV, the contributions of myelin and iron content to susceptibility was estimated. Conclusion We have developed a novel strategy to simultaneously acquire data for the reconstruction of five intrinsically co-registered 1-mm isotropic resolution multi-parametric maps, with a scan time of 6 minutes using JVC-GRAPPA.
2021-06-09
bioRxiv (preprint)
doi.org