Publications

Interpretable domain adaptation using unsupervised feature selection on pre-trained source models
Luxin Zhang
Pascal Germain
Yacine Kessaci
C. Biernacki
2022-08-31
Neurocomputing (published)
doi.org
A novel domain adaptation theory with Jensen-Shannon divergence
Changjian Shui
Qi CHEN
Jun Wen
Fan Zhou
Christian Gagné
Boyu Wang
2022-08-31
Knowledge-Based Systems (published)
doi.org
The load planning and sequencing problem for double-stack trains
Moritz Ruf
Jean-François Cordeau
Emma Frejinger
2022-08-31
Journal of Rail Transport Planning & Management (published)
doi.org
Two types of human TCR differentially regulate reactivity to self and non-self antigens
Assya Trofimov
Philippe Brouillard
Jean-David Larouche
Jonathan Séguin
Jean-Philippe Laverdure
Ann Brasey
Gregory Ehx
Denis-Claude Roy
Lambert Busque
Silvy Lachance
Sébastien Lemieux
Claude Perreault
Based on analyses of TCR sequences from over 1,000 individuals, we report that the TCR repertoire is composed of two ontogenically and funct… (see more)ionally distinct types of TCRs. Their production is regulated by variations in thymic output and terminal deoxynucleotidyl transferase (TDT) activity. Neonatal TCRs derived from TDT-negative progenitors persist throughout life, are highly shared among subjects, and are reported as disease-associated. Thus, 10%–30% of most frequent cord blood TCRs are associated with common pathogens and autoantigens. TDT-dependent TCRs present distinct structural features and are less shared among subjects. TDT-dependent TCRs are produced in maximal numbers during infancy when thymic output and TDT activity reach a summit, are more abundant in subjects with AIRE mutations, and seem to play a dominant role in graft-versus-host disease. Factors decreasing thymic output (age, male sex) negatively impact TCR diversity. Males compensate for their lower repertoire diversity via hyperexpansion of selected TCR clonotypes.
2022-08-31
iScience (published)
doi.org
Association between Anxiety and Disease Pathophysiology in Participants of Longitudinal Observational Studies in Aging during the COVID-19 Lockdown
Stijn Servaes
Firoza Lussier
Cécile Tissot
Joseph Therriault
Gleb Bezgin
Yi-Ting Wang
Jenna Stevenson
Nesrine Rahmouni
Vanessa Pallen
Guillaume Elgbeili
Jaime Fernandez Arias
Min Su Kang
Andrea Benedet
Mira Chamoun
Tharick Pascoal
Kok Pin Ng
Danilo Bzdok
Suzanne King
Serge Gauthier
Pedro Rosa-Neto
Abstract

The burden imposed by the COVID-19 pandemic deferentially interferes with the outcomes of clinical trials of aging… (see more) and dementia. We examined the impact of the lockdown on cognitive impairment due to Alzheimer’s Disease (AD), anxiety, and COVID-19-related stress in participants from the Translational Biomarkers In Aging and Dementia (TRIAD) cohort using neuropsychiatric assessments, tau and amyloid PET. We found that, before the lockdown, anxiety was higher in cognitively impaired individuals (CI) and positively associated with brain tau load. However, during the lockdown, anxiety increased only in the cognitively unimpaired (CU) and was positively associated with COVID-19 related stress. Interestingly, we found that in patients, tau load was anti-correlated with higher anxiety during lockdown. Our findings contribute to a framework for interpreting the effects of the pandemic on neuropsychiatric symptoms among clinical trial participants. Collectively, our results suggest that caregivers are more vulnerable to external stressors than patients.

2022-08-29
Research Square (preprint)
doi.org
Synthesizing theories of human language with Bayesian program induction
Kevin Ellis
Adam Albright
Armando Solar-Lezama
Joshua B. Tenenbaum
Timothy J. O'Donnell
Automated, data-driven construction and evaluation of scientific models and theories is a long-standing challenge in artificial intelligence… (see more). We present a framework for algorithmically synthesizing models of a basic part of human language: morpho-phonology, the system that builds word forms from sounds. We integrate Bayesian inference with program synthesis and representations inspired by linguistic theory and cognitive models of learning and discovery. Across 70 datasets from 58 diverse languages, our system synthesizes human-interpretable models for core aspects of each language’s morpho-phonology, sometimes approaching models posited by human linguists. Joint inference across all 70 data sets automatically synthesizes a meta-model encoding interpretable cross-language typological tendencies. Finally, the same algorithm captures few-shot learning dynamics, acquiring new morphophonological rules from just one or a few examples. These results suggest routes to more powerful machine-enabled discovery of interpretable models in linguistics and other scientific domains.
2022-08-29
Nature Communications (published)
doi.org
Deep Reinforcement Learning in Human Activity Recognition: A Survey
Bahareh Nikpour
Dimitrios Sinodinos
Narges Armanfard
<p>  Human activity recognition is a popular research field in computer vision that has already been widely studied. However, it is … (see more)still an active research field since it plays an important role in many current and emerging real-world intelligent systems, like visual surveillance and human-computer interaction. Deep Reinforcement Learning (DRL) has recently been employed to address the activity recognition problem with various purposes, such as finding attention in video data or obtaining the best network structure. DRL-based human activity recognition has only been around for a short time, and it is a challenging, novel field of study. Therefore, to facilitate further research in this field, we have constructed a comprehensive survey on activity recognition methods that incorporate deep reinforcement learning. Towards the end of this survey, we summarize key challenges and open problems in this area that can be addressed by researchers in the future.  </p>
2022-08-28
Figshare (preprint)
doi.org
Deep Reinforcement Learning in Human Activity Recognition: A Survey
Bahareh Nikpour
Dimitrios Sinodinos
Narges Armanfard
<p>  Human activity recognition is a popular research field in computer vision that has already been widely studied. However, it is … (see more)still an active research field since it plays an important role in many current and emerging real-world intelligent systems, like visual surveillance and human-computer interaction. Deep Reinforcement Learning (DRL) has recently been employed to address the activity recognition problem with various purposes, such as finding attention in video data or obtaining the best network structure. DRL-based human activity recognition has only been around for a short time, and it is a challenging, novel field of study. Therefore, to facilitate further research in this field, we have constructed a comprehensive survey on activity recognition methods that incorporate deep reinforcement learning. Towards the end of this survey, we summarize key challenges and open problems in this area that can be addressed by researchers in the future.  </p>
2022-08-28
Figshare (preprint)
doi.org
QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results
Raghav Mehta
Angelos Filos
Ujjwal Baid
Chiharu Sako
Richard McKinley
Michael Rebsamen
Katrin Datwyler
Raphael Meier
Piotr Radojewski
Gowtham Krishnan Murugesan
Sahil Nalawade
Chandan Ganesh
Ben Wagner
Fang F. Yu
Baowei Fei
Ananth J. Madhuranthakam
Joseph A. Maldjian
Laura Daza
Catalina Gomez
Pablo Arbelaez … (see 72 more)
Chengliang Dai
Shuo Wang
Hadrien Reynaud
Yuan-han Mo
Elsa Angelini
Yike Guo
Wenjia Bai
Subhashis Banerjee
Lin-min Pei
Murat AK
Sarahi Rosas-Gonzalez
Ilyess Zemmoura
Clovis Tauber
Minh H. Vu
Tufve Nyholm
Tommy Lofstedt
Laura Mora Ballestar
Veronica Vilaplana
Hugh McHugh
Gonzalo Maso Talou
Alan Wang
Jay Patel
Ken Chang
Katharina Hoebel
Mishka Gidwani
Nishanth Arun
Sharut Gupta
Mehak Aggarwal
Praveer Singh
Elizabeth R. Gerstner
Jayashree Kalpathy-Cramer
Nicolas Boutry
Alexis Huard
Lasitha Vidyaratne
Md Monibor Rahman
Khan M. Iftekharuddin
Joseph Chazalon
Elodie Puybareau
Guillaume Tochon
Jun Ma
Mariano Cabezas
Xavier Llado
Arnau Oliver
Liliana Valencia
Sergi Valverde
Mehdi Amian
Mohammadreza Soltaninejad
Andriy Myronenko
Ali Hatamizadeh
Xue Feng
Quan Dou
Nicholas Tustison
Craig Meyer
Nisarg A. Shah
Sanjay Talbar
Marc-André Weber
Abhishek Mahajan
Andras Jakab
Roland Wiest
Hassan M. Fathallah-Shaykh
Arash Nazeri
Mikhail Milchenko1
Daniel Marcus
Aikaterini Kotrotsou
Rivka Colen
John Freymann
Justin Kirby
Christos Davatzikos
Bjoern Menze
Spyridon Bakas
Yarin Gal
Tal Arbel
Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain… (see more) Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder translating DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties could enable clinical review of the most uncertain regions, thereby building trust and paving the way toward clinical translation. Several uncertainty estimation methods have recently been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019 and BraTS 2020 task on uncertainty quantification (QU-BraTS) and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentage of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, highlighting the need for uncertainty quantification in medical image analyses. Finally, in favor of transparency and reproducibility, our evaluation code is made publicly available at https://github.com/RagMeh11/QU-BraTS.
2022-08-25
Machine Learning for Biomedical Imaging (published)
doi.org
arxiv.org
Fractal impedance for passive controllers: a framework for interaction robotics
Keyhan Kouhkiloui Babarahmati
Carlo Tiseo
Joshua Smith
Hsiu-Chin Lin
M. S. Erden
Michael Nalin Mistry
2022-08-24
Nonlinear Dynamics (published)
doi.org
arxiv.org
Learning Shared Neural Manifolds from Multi-Subject fMRI Data
Jessie Huang
Erica Busch
Tom Wallenstein
Michal Gerasimiuk
Andrew Benz
Guillaume Lajoie
Guy Wolf
Nicholas Turk-Browne
Smita Krishnaswamy
Functional magnetic resonance imaging (fMRI) is a notoriously noisy measurement of brain activity because of the large variations between in… (see more)dividuals, signals marred by environmental differences during collection, and spatiotemporal averaging required by the measurement resolution. In addition, the data is extremely high dimensional, with the space of the activity typically having much lower intrinsic dimension. In order to understand the connection between stimuli of interest and brain activity, and analyze differences and commonalities between subjects, it becomes important to learn a meaningful embedding of the data that denoises, and reveals its intrinsic structure. Specifically, we assume that while noise varies significantly between individuals, true responses to stimuli will share common, low-dimensional features between subjects which are jointly discoverable. Similar approaches have been exploited previously but they have mainly used linear methods such as PCA and shared response modeling (SRM). In contrast, we propose a neural network called MRMD-AE (manifold-regularized multiple decoder, autoencoder), that learns a common embedding from multiple subjects in an experiment while retaining the ability to decode to individual raw fMRI signals. We show that our learned common space represents an extensible manifold (where new points not seen during training can be mapped), improves the classification accuracy of stimulus features of unseen timepoints, as well as improves cross-subject translation of fMRI signals. We believe this framework can be used for many downstream applications such as guided brain-computer interface (BCI) training in the future.
2022-08-21
2022 IEEE 32nd International Workshop on Machine Learning for Signal Processing (MLSP) (published)
doi.org
openreview.net
Proteogenomics and Differential Ion Mobility Enable the Exploration of the Mutational Landscape in Colon Cancer Cells
Zhaoguan Wu
Éric Bonneil
Michael Belford
Cornelia Boeser
Maria Virginia Ruiz Cuevas
Sébastien Lemieux
Jean-Jacques Dunyach
Pierre Thibault
The sensitivity and depth of proteomic analyses are limited by isobaric ions and interferences that preclude the identification of low abund… (see more)ance peptides. Extensive sample fractionation is often required to extend proteome coverage when sample amount is not a limitation. Ion mobility devices provide a viable alternate approach to resolve confounding ions and improve peak capacity and mass spectrometry (MS) sensitivity. Here, we report the integration of differential ion mobility with segmented ion fractionation (SIFT) to enhance the comprehensiveness of proteomic analyses. The combination of differential ion mobility and SIFT, where narrow windows of ∼m/z 100 are acquired in turn, is found particularly advantageous in the analysis of protein digests and typically provided more than 60% gain in identification compared to conventional single-shot LC–MS/MS. The application of this approach is further demonstrated for the analysis of tryptic digests from different colorectal cancer cell lines where the enhanced sensitivity enabled the identification of single amino acid variants that were correlated with the corresponding transcriptomic data sets.
2022-08-21
Analytical Chemistry (published)
doi.org