Julien Cohen-Adad

Thomas Dagonneau

Master's Research - Polytechnique Montréal

Naga Karthik Enamundram

PhD - Polytechnique Montréal

Co-supervisor :

Sarath Chandar

emvnagakarthik@gmail.com

PhD - Polytechnique Montréal

Nathan Molinier

PhD - Polytechnique Montréal

Kalum Ost

Collaborating researcher

Abel Salmona Salmona

Research Intern - Polytechnique Montréal

abel.salmona@gmail.com

Julien Thouveny

Master's Research - Université de Montréal

Arthur Toulouse

Master's Research - Polytechnique Montréal

Jan Valosek

Postdoctorate - Polytechnique Montréal

Website

Google Scholar

Publications

Segmentation of Multiple Sclerosis Lesions across Hospitals: Learn Continually or Train from Scratch?

Enamundram Naga Karthik

Anne Kerbrat

Pierre Labauge

Tobias Granberg

Jason F. Talbott

Daniel S Reich

Massimo Filippi

Rohit Bakshi

Virginie Callot

Sarath Chandar

Segmentation of Multiple Sclerosis (MS) lesions is a challenging problem. Several deep-learning-based methods have been proposed in recent y… (see more)ears. However, most methods tend to be static, that is, a single model trained on a large, specialized dataset, which does not generalize well. Instead, the model should learn across datasets arriving sequentially from different hospitals by building upon the characteristics of lesions in a continual manner. In this regard, we explore experience replay, a well-known continual learning method, in the context of MS lesion segmentation across multi-contrast data from 8 different hospitals. Our experiments show that replay is able to achieve positive backward transfer and reduce catastrophic forgetting compared to sequential fine-tuning. Furthermore, replay outperforms the multi-domain training, thereby emerging as a promising solution for the segmentation of MS lesions. The code is available at this link: https://github.com/naga-karthik/continual-learning-ms

2022-10-27

ArXiv (preprint)

Recommendations and guidelines from the ISMRM Diffusion Study Group for preclinical diffusion MRI: Part 2 -- Ex vivo imaging

Kurt G Schilling

Francesco Grussu

Andrada Ianus

Brian Hansen

Manisha Aggarwal

Stijn Michielse

Fatima Nasrallah

Warda Syeda

Nian Wang

Jelle Veraart

Alard Roebroeck

Andrew F. Bagdasarian

Cornelius Eichner

Farshid Sepehrband

Jan Zimmermann

Ben Jeurissen

Lucio Frydman

Yohan van de Looij

David Hike

Jeff F. Dunn … (see 30 more)

Karla Miller

Bennett Landman

Noam Shemesh

Arthur Anderson

Emilie McKinnon

Shawna Farquharson

Flavio Dell’Acqua

Carlo Pierpaoli

Ivana Drobnjak

Alexander Leemans

Kevin D. Harkins

Maxime Descoteaux

Duan Xu

Mathieu D. Santin

Samuel C. Grant

Andre Obenaus

Gene S. Kim

Dan Wu

Denis Le Bihan

Stephen J. Blackband

Luisa Ciobanu

Els Fieremans

Ruiliang Bai

Trygve B. Leergaard

Jiangyang Zhang

Tim B. Dyrby

G. Allan Johnson

Matthew D. Budde

Ileana O. Jelescu

2022-09-27

ArXiv (preprint)

Recommendations and guidelines from the ISMRM Diffusion Study Group for preclinical diffusion MRI: Part 1 -- In vivo small-animal imaging

Ileana O. Jelescu

Francesco Grussu

Andrada Ianus

Brian Hansen

Manisha Aggarwal

Stijn Michielse

Fatima Nasrallah

Warda Syeda

Nian Wang

Jelle Veraart

Alard Roebroeck

Andrew F. Bagdasarian

Cornelius Eichner

Farshid Sepehrband

Jan Zimmermann

Ben Jeurissen

Lucio Frydman

Yohan van de Looij

David Hike

Jeff F. Dunn … (see 30 more)

Karla Miller

Bennett Landman

Noam Shemesh

Arthur Anderson

Emilie McKinnon

Shawna Farquharson

Flavio Dell’Acqua

Carlo Pierpaoli

Ivana Drobnjak

Alexander Leemans

Kevin D. Harkins

Maxime Descoteaux

Duan Xu

Mathieu D. Santin

Samuel C. Grant

Andre Obenaus

Gene S. Kim

Dan Wu

Denis Le Bihan

Stephen J. Blackband

Luisa Ciobanu

Els Fieremans

Ruiliang Bai

Trygve B. Leergaard

Jiangyang Zhang

Tim B. Dyrby

G. Allan Johnson

Matthew D. Budde

Kurt G Schilling

The value of in vivo preclinical diffusion MRI (dMRI) is substantial. Small-animal dMRI has been used for methodological development and val… (see more)idation, characterizing the biological basis of diffusion phenomena, and comparative anatomy. Many of the influential works in this field were first performed in small animals or ex vivo samples. The steps from animal setup and monitoring, to acquisition, analysis, and interpretation are complex, with many decisions that may ultimately affect what questions can be answered using the data. This work aims to serve as a reference, presenting selected recommendations and guidelines from the diffusion community, on best practices for preclinical dMRI of in vivo animals. In each section, we also highlight areas for which no guidelines exist (and why), and where future work should focus. We first describe the value that small animal imaging adds to the field of dMRI, followed by general considerations and foundational knowledge that must be considered when designing experiments. We briefly describe differences in animal species and disease models and discuss how they are appropriate for different studies. We then give guidelines for in vivo acquisition protocols, including decisions on hardware, animal preparation, imaging sequences and data processing, including pre-processing, model-fitting, and tractography. Finally, we provide an online resource which lists publicly available preclinical dMRI datasets and software packages, to promote responsible and reproducible research. An overarching goal herein is to enhance the rigor and reproducibility of small animal dMRI acquisitions and analyses, and thereby advance biomedical knowledge.

2022-09-26

ArXiv (preprint)

Intervertebral Disc Labeling With Learning Shape Information, A Look Once Approach

Reza Azad

Moein Heidari

Ehsan Adeli

Dorit Merhof

Accurate and automatic segmentation of intervertebral discs from medical images is a critical task for the assessment of spine-related disea… (see more)ses such as osteoporosis, vertebral fractures, and intervertebral disc herniation. To date, various approaches have been developed in the literature which routinely relies on detecting the discs as the primary step. A disadvantage of many cohort studies is that the localization algorithm also yields false-positive detections. In this study, we aim to alleviate this problem by proposing a novel U-Net-based structure to predict a set of candidates for intervertebral disc locations. In our design, we integrate the image shape information (image gradients) to encourage the model to learn rich and generic geometrical information. This additional signal guides the model to selectively emphasize the contextual representation and suppress the less discriminative features. On the post-processing side, to further decrease the false positive rate, we propose a permutation invariant 'look once' model, which accelerates the candidate recovery procedure. In comparison with previous studies, our proposed approach does not need to perform the selection in an iterative fashion. The proposed method was evaluated on the spine generic public multi-center dataset and demonstrated superior performance compared to previous work. We have provided the implementation code in https://github.com/rezazad68/intervertebral-lookonce

2022-09-16

Predictive Intelligence in Medicine (published)

Advanced MRI Scan Acquisition Metrics Improve Baseline Disease Severity Predictions Compared to Traditional Community MRI Scan Metrics

Abdul Al-Shawwa

Kalum Ost

David W. Cadotte

David Anderson

Nathan Evaniew

Nathan

B. Jacobs

Degenerative Cervical Myelopathy (DCM) is the functional derangement of the spinal cord and acts as one of the most common atraumatic spinal… (see more) cord injuries. Magnetic resonance imaging (MRI) are key in confirming the diagnosis of DCM in patients, though the utilization of higher fidelity magnetic resonance imaging scans and their integration into machine learning models remains largely unexplored. This study looks at the predictive ability of common community MRI scans in comparison to high fidelity scans in disease diagnosis. We hypothesize that the utilization of higher fidelity "advanced" MRI scans will increase the effectiveness of machine learning models predicting DCM severity. Through the utilization of Random Forest Classifiers, we have been able to predict disease severity with 41.8% accuracy in current community MRI scans and 63.9% in the advanced MRI scans. Furthermore, across the different predictive model variations tested, the advanced MRI scans consistently produced higher prediction accuracies compared to the community MRI counterparts. These results support our hypothesis and indicate that machine learning models have the potential to predict disease severity. However, neither performed well enough to be considered for use in clinical practice, indicating that the utilization of more sophisticated machine models may be required for these purposes.

2022-07-07

medRxiv (preprint)

Relationship Between Arterial Stiffness Index, Pulse Pressure, and Magnetic Resonance Imaging Markers of White Matter Integrity: A UK Biobank Study

Atef Badji

Hélène Girouard

2022-06-21

Frontiers in Aging Neuroscience (published)

NeoRS: A Neonatal Resting State fMRI Data Preprocessing Pipeline

Vicente Enguix

Jeanette Kenley

David Luck

Gregory Anton Lodygensky

Resting state functional MRI (rsfMRI) has been shown to be a promising tool to study intrinsic brain functional connectivity and assess its … (see more)integrity in cerebral development. In neonates, where functional MRI is limited to very few paradigms, rsfMRI was shown to be a relevant tool to explore regional interactions of brain networks. However, to identify the resting state networks, data needs to be carefully processed to reduce artifacts compromising the interpretation of results. Because of the non-collaborative nature of the neonates, the differences in brain size and the reversed contrast compared to adults due to myelination, neonates can’t be processed with the existing adult pipelines, as they are not adapted. Therefore, we developed NeoRS, a rsfMRI pipeline for neonates. The pipeline relies on popular neuroimaging tools (FSL, AFNI, and SPM) and is optimized for the neonatal brain. The main processing steps include image registration to an atlas, skull stripping, tissue segmentation, slice timing and head motion correction and regression of confounds which compromise functional data interpretation. To address the specificity of neonatal brain imaging, particular attention was given to registration including neonatal atlas type and parameters, such as brain size variations, and contrast differences compared to adults. Furthermore, head motion was scrutinized, and motion management optimized, as it is a major issue when processing neonatal rsfMRI data. The pipeline includes quality control using visual assessment checkpoints. To assess the effectiveness of NeoRS processing steps we used the neonatal data from the Baby Connectome Project dataset including a total of 10 neonates. NeoRS was designed to work on both multi-band and single-band acquisitions and is applicable on smaller datasets. NeoRS also includes popular functional connectivity analysis features such as seed-to-seed or seed-to-voxel correlations. Language, default mode, dorsal attention, visual, ventral attention, motor and fronto-parietal networks were evaluated. Topology found the different analyzed networks were in agreement with previously published studies in the neonate. NeoRS is coded in Matlab and allows parallel computing to reduce computational times; it is open-source and available on GitHub (https://github.com/venguix/NeoRS). NeoRS allows robust image processing of the neonatal rsfMRI data that can be readily customized to different datasets.

2022-06-17

Frontiers in Neuroinformatics (published)

Vendor-neutral sequences and fully transparent workflows improve inter-vendor reproducibility of quantitative MRI

Agah Karakuzu

Labonny Biswas

Nikola Stikov

Purpose We developed an end-to-end workflow that starts with a vendor-neutral acquisition and tested the hypothesis that vendor-neutral sequ… (see more)ences decrease inter-vendor variability of T1, MTR and MTsat measurements. Methods We developed and deployed a vendor-neutral 3D spoiled gradient-echo (SPGR) sequence on three clinical scanners by two MRI vendors. We then acquired T1 maps on the ISMRM-NIST system phantom, as well as T1, MTR and MTsat maps in three healthy participants. We performed hierarchical shift function analysis in vivo to characterize the differences between scanners when the vendor-neutral sequence is used instead of commercial vendor implementations. Inter-vendor deviations were compared for statistical significance to test the hypothesis. Results In the phantom, the vendor-neutral sequence reduced inter-vendor differences from 8 - 19.4% to 0.2 - 5% with an overall accuracy improvement, reducing ground truth T1 deviations from 7 - 11% to 0.2 - 4%. In vivo we found that the variability between vendors is significantly reduced (p = 0.015) for all maps (T1, MTR and MTsat) using the vendor-neutral sequence. Conclusion We conclude that vendor-neutral workflows are feasible and compatible with clinical MRI scanners. The significant reduction of inter-vendor variability using vendor-neutral sequences has important implications for qMRI research and for the reliability of multicenter clinical trials.

2022-06-03

Magnetic Resonance in Medicine (published)

Brain-spinal cord interaction in long-term motor sequence learning in human: An fMRI study

Ali Khatibi

Shahabeddin Vahdat

Ovidiu Lungu

Jürgen Finsterbusch

Christian Büchel

V. Marchand-Pauvert

Julien Doyon

2022-06-01

NeuroImage (published)

Diffusion Kurtosis Imaging of the neonatal Spinal Cord: design and application of the first processing pipeline implemented in Spinal Cord Toolbox

Rosella Trò

Monica Roascio

Domenico Tortora

Mariasavina Severino

Andrea Rossi

Marco Massimo Fato

Gabriele Arnulfo

Diffusion Kurtosis Imaging (DKI) has undisputed advantages over more classical diffusion Magnetic Resonance Imaging (dMRI), as witnessed by … (see more)a fast-increasing number of clinical applications and software packages widely adopted in brain imaging domain. Despite its power in probing tissue microstructure compared to conventional MRI, DKI is still largely underutilized in Spinal Cord (SC) imaging because of its inherently demanding technological requirements. If state-of-the-art hardware advancements have recently allowed to make great strides in applying this emerging method to adult and child SC, the same does not apply to neonatal setting. Indeed, amplified technical issues related to SC district in this age range have made this field still unexplored. However, results arising from recent application of DKI to adult and child SC are promising enough to suggest how informative this technique would be in investigating newborns, too. Due to its extreme sensitivity to non-gaussian diffusion, DKI proves particularly suitable for detecting complex, subtle, fast microstructural changes occurring in this area at this early and critical stage of development, and not identifiable with only DTI. Given the multiplicity of congenital anomalies of the spinal canal, their crucial effect on later developmental outcome, and the close interconnection between SC region and the above brain, managing to apply such a method to neonatal cohort becomes of utmost importance. In this work, we illustrate the first semi-automated pipeline for handling with DKI data of neonatal SC, from acquisition setting to estimation of diffusion (DTI & DKI) measures, through accurate adjustment of processing algorithms customized for adult SC. Each processing step of this pipeline, built on Spinal Cord Toolbox (SCT) software, has undergone Quality Control check by supervision of an expert pediatric neuroradiologist, and the overall procedure has preliminarily been tested in a pilot clinical case study. Results of this application agree with findings achieved in a corresponding adult survey, thus confirming validity of adopted pipeline and diagnostic value of DKI in pediatrics. This novel tool hence paves the wave for extending its application also to other promising advanced dMRI models, such as Neurite Orientation Dispersion and Density Imaging (NODDI), and to a wider range of potential clinical applications concerning neonatal period.

2022-05-23

Frontiers in Radiology (published)

Microscopy-BIDS: An Extension to the Brain Imaging Data Structure for Microscopy Data

Marie-Hélène Bourget

Lee Kamentsky

Satrajit S. Ghosh

Giacomo Mazzamuto

Alberto Lazari

Christopher J. Markiewicz

Robert Oostenveld

Guiomar Niso

Yaroslav O. Halchenko

Ilona Lipp

Sylvain Takerkart

Paule-Joanne Toussaint

Ali R. Khan

Gustav Nilsonne

Filippo Maria Castelli

Stefan Ross Eric Franklin Anthony Rémi Christopher J. Taylor Appelhoff

The Brain Imaging Data Structure (BIDS) is a specification for organizing, sharing, and archiving neuroimaging data and metadata in a reusab… (see more)le way. First developed for magnetic resonance imaging (MRI) datasets, the community-led specification evolved rapidly to include other modalities such as magnetoencephalography, positron emission tomography, and quantitative MRI (qMRI). In this work, we present an extension to BIDS for microscopy imaging data, along with example datasets. Microscopy-BIDS supports common imaging methods, including 2D/3D, ex/in vivo, micro-CT, and optical and electron microscopy. Microscopy-BIDS also includes comprehensible metadata definitions for hardware, image acquisition, and sample properties. This extension will facilitate future harmonization efforts in the context of multi-modal, multi-scale imaging such as the characterization of tissue microstructure with qMRI.

2022-04-19

Frontiers in Neuroscience (published)

Microscopy-BIDS: An Extension to the Brain Imaging Data Structure for Microscopy Data

Marie-Hélène Bourget

L. Kamentsky

Satrajit S. Ghosh

Giacomo Mazzamuto

Alberto Lazari

Christopher J. Markiewicz

Robert Oostenveld

Guiomar Niso

Yaroslav O. Halchenko

Ilona Lipp

Sylvain Takerkart

P. Toussaint

Ali Raza Khan

Gustav Nilsonne

Filippo Maria Castelli

2022-04-19

Frontiers in Neuroscience (published)