Publications

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)

On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?

Nouha Dziri

Sivan Milton

Mo Yu

Osmar R Zaiane

Siva Reddy

Knowledge-grounded conversational models are known to suffer from producing factually invalid statements, a phenomenon commonly called hallu… (see more)cination. In this work, we investigate the underlying causes of this phenomenon: is hallucination due to the training data, or to the models? We conduct a comprehensive human study on both existing knowledge-grounded conversational benchmarks and several state-of-the-art models. Our study reveals that the standard benchmarks consist of > 60% hallucinated responses, leading to models that not only hallucinate but even amplify hallucinations. Our findings raise important questions on the quality of existing datasets and models trained using them. We make our annotations publicly available for future research.

2022-04-17

ArXiv (preprint)

Improving Passage Retrieval with Zero-Shot Question Generation

Devendra Singh Sachan

Mike Lewis

Mandar S. Joshi

Armen Aghajanyan

Wen-292 Tau Yih

Joelle Pineau

Luke Zettlemoyer

We propose a simple and effective re-ranking method for improving passage retrieval in open question answering. The re-ranker re-scores retr… (see more)ieved passages with a zero-shot question generation model, which uses a pre-trained language model to compute the probability of the input question conditioned on a retrieved passage. This approach can be applied on top of any retrieval method (e.g. neural or keyword-based), does not require any domain- or task-specific training (and therefore is expected to generalize better to data distribution shifts), and provides rich cross-attention between query and passage (i.e. it must explain every token in the question). When evaluated on a number of open-domain retrieval datasets, our re-ranker improves strong unsupervised retrieval models by 6%-18% absolute and strong supervised models by up to 12% in terms of top-20 passage retrieval accuracy. We also obtain new state-of-the-art results on full open-domain question answering by simply adding the new re-ranker to existing models with no further changes.

2022-04-15

ArXiv (preprint)

Evolution of cell size control is canalized towards adders or sizers by cell cycle structure and selective pressures

Felix Proulx-Giraldeau

J. Skotheim

Paul François

Cell size is controlled to be within a specific range to support physiological function. To control their size, cells use diverse mechanisms… (see more) ranging from ‘sizers’, in which differences in cell size are compensated for in a single cell division cycle, to ‘adders’, in which a constant amount of cell growth occurs in each cell cycle. This diversity raises the question why a particular cell would implement one rather than another mechanism? To address this question, we performed a series of simulations evolving cell size control networks. The size control mechanism that evolved was influenced by both cell cycle structure and specific selection pressures. Moreover, evolved networks recapitulated known size control properties of naturally occurring networks. If the mechanism is based on a G1 size control and an S/G2/M timer, as found for budding yeast and some human cells, adders likely evolve. But, if the G1 phase is significantly longer than the S/G2/M phase, as is often the case in mammalian cells in vivo, sizers become more likely. Sizers also evolve when the cell cycle structure is inverted so that G1 is a timer, while S/G2/M performs size control, as is the case for the fission yeast S. pombe. For some size control networks, cell size consistently decreases in each cycle until a burst of cell cycle inhibitor drives an extended G1 phase much like the cell division cycle of the green algae Chlamydomonas. That these size control networks evolved such self-organized criticality shows how the evolution of complex systems can drive the emergence of critical processes.

2022-04-14

bioRxiv (preprint)

Masked Siamese Networks for Label-Efficient Learning

Mahmoud Assran

Mathilde Caron

Ishan Misra

Piotr Bojanowski

Florian Bordes

Pascal Vincent

Armand Joulin

Michael Rabbat

Nicolas Ballas

We propose Masked Siamese Networks (MSN), a self-supervised learning framework for learning image representations. Our approach matches the … (see more)representation of an image view containing randomly masked patches to the representation of the original unmasked image. This self-supervised pre-training strategy is particularly scalable when applied to Vision Transformers since only the unmasked patches are processed by the network. As a result, MSNs improve the scalability of joint-embedding architectures, while producing representations of a high semantic level that perform competitively on low-shot image classification. For instance, on ImageNet-1K, with only 5,000 annotated images, our base MSN model achieves 72.4% top-1 accuracy, and with 1% of ImageNet-1K labels, we achieve 75.7% top-1 accuracy, setting a new state-of-the-art for self-supervised learning on this benchmark. Our code is publicly available.

2022-04-14

ArXiv (preprint)

Microscopy analysis neural network to solve detection, enumeration and segmentation from image-level annotations

Anthony Bilodeau

Constantin V. L. Delmas

M. Parent

Paul De Koninck

Audrey Durand

Flavie Lavoie-Cardinal

2022-04-14

Nature Machine Intelligence (published)

Samira Abbasgholizadeh-Rahimi

User Experience of a Computer-Based Decision Aid for Prenatal Trisomy Screening: Mixed Methods Explanatory Study

Titilayo Tatiana Agbadje

Chantale Pilon

Pierre Bérubé

Jean‐claude Forest

François Rousseau

Yves Giguère

France Légaré

Background Mobile health tools can support shared decision-making. We developed a computer-based decision aid (DA) to help pregnant women an… (see more)d their partners make informed, value-congruent decisions regarding prenatal screening for trisomy. Objective This study aims to assess the usability and usefulness of computer-based DA among pregnant women, clinicians, and policy makers. Methods For this mixed methods sequential explanatory study, we planned to recruit a convenience sample of 45 pregnant women, 45 clinicians from 3 clinical sites, and 15 policy makers. Eligible women were aged >18 years and >16 weeks pregnant or had recently given birth. Eligible clinicians and policy makers were involved in prenatal care. We asked the participants to navigate a computer-based DA. We asked the women about the usefulness of the DA and their self-confidence in decision-making. We asked all participants about usability, quality, acceptability, satisfaction with the content of the DA, and collected sociodemographic data. We explored participants’ reactions to the computer-based DA and solicited suggestions. Our interview guide was based on the Mobile App Rating Scale. We performed descriptive analyses of the quantitative data and thematic deductive and inductive analyses of the qualitative data for each participant category. Results A total of 45 pregnant women, 14 clinicians, and 8 policy makers participated. Most pregnant women were aged between 25 and 34 years (34/45, 75%) and White (42/45, 94%). Most clinicians were aged between 35 and 44 years (5/14, 36%) and women (11/14, 79%), and all were White (14/14, 100%); the largest proportion of policy makers was aged between 45 and 54 years (4/8, 50%), women (5/8, 62%), and White (8/8, 100%). The mean usefulness score for preparing for decision-making for women was 80/100 (SD 13), and the mean self-efficacy score was 88/100 (SD 11). The mean usability score was 84/100 (SD 14) for pregnant women, 77/100 (SD 14) for clinicians, and 79/100 (SD 23) for policy makers. The mean global score for quality was 80/100 (SD 9) for pregnant women, 72/100 (SD 12) for clinicians, and 80/100 (SD 9) for policy makers. Regarding acceptability, participants found the amount of information just right (52/66, 79%), balanced (58/66, 88%), useful (38/66, 58%), and sufficient (50/66, 76%). The mean satisfaction score with the content was 84/100 (SD 13) for pregnant women, 73/100 (SD 16) for clinicians, and 73/100 (SD 20) for policy makers. Participants thought the DA could be more engaging (eg, more customizable) and suggested strategies for implementation, such as incorporating it into clinical guidelines. Conclusions Pregnant women, clinicians, and policy makers found the DA usable and useful. The next steps are to incorporate user suggestions for improving engagement and implementing the computer-based DA in clinical practice.

2022-04-14

JMIR Pediatrics and Parenting (published)

Aspirations and Practice of ML Model Documentation: Moving the Needle with Nudging and Traceability

Avinash Bhat

Austin Coursey

Grace Hu

Sixian Li

Nadia Nahar

Shurui Zhou

Christian Kästner

Jin Guo

The documentation practice for machine-learned (ML) models often falls short of established practices for traditional software, which impede… (see more)s model accountability and inadvertently abets inappropriate or misuse of models. Recently, model cards, a proposal for model documentation, have attracted notable attention, but their impact on the actual practice is unclear. In this work, we systematically study the model documentation in the field and investigate how to encourage more responsible and accountable documentation practice. Our analysis of publicly available model cards reveals a substantial gap between the proposal and the practice. We then design a tool named DocML aiming to (1) nudge the data scientists to comply with the model cards proposal during the model development, especially the sections related to ethics, and (2) assess and manage the documentation quality. A lab study reveals the benefit of our tool towards long-term documentation quality and accountability.

2022-04-13

ArXiv (preprint)

NeoRS: A Neonatal Resting State fMRI Data Preprocessing Pipeline

Vicente Enguix

Jeanette K. Kenley

David Luck

G. 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.

2022-04-08

ArXiv (preprint)

Rapid, automated nerve histomorphometry through open-source artificial intelligence

S. Daeschler

Marie-Hélène Bourget

Dorsa Derakhshan

Vasudev Sharma

Stoyan Ivaylov Asenov

Tessa Gordon

G. Borschel

2022-04-08

Scientific Reports (published)

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

2022-04-06

ArXiv (preprint)

Structure-aware protein self-supervised learning

Can Chen

Jingbo Zhou

Fan Wang

Xue (Steve) Liu

Dejing Dou

Abstract Motivation Protein representation learning methods have shown great potential to many downstream tasks in biological applications. … (see more)A few recent studies have demonstrated that the self-supervised learning is a promising solution to addressing insufficient labels of proteins, which is a major obstacle to effective protein representation learning. However, existing protein representation learning is usually pretrained on protein sequences without considering the important protein structural information. Results In this work, we propose a novel structure-aware protein self-supervised learning method to effectively capture structural information of proteins. In particular, a graph neural network model is pretrained to preserve the protein structural information with self-supervised tasks from a pairwise residue distance perspective and a dihedral angle perspective, respectively. Furthermore, we propose to leverage the available protein language model pretrained on protein sequences to enhance the self-supervised learning. Specifically, we identify the relation between the sequential information in the protein language model and the structural information in the specially designed graph neural network model via a novel pseudo bi-level optimization scheme. We conduct experiments on three downstream tasks: the binary classification into membrane/non-membrane proteins, the location classification into 10 cellular compartments, and the enzyme-catalyzed reaction classification into 384 EC numbers, and these experiments verify the effectiveness of our proposed method. Availability and implementation The Alphafold2 database is available in https://alphafold.ebi.ac.uk/. The PDB files are available in https://www.rcsb.org/. The downstream tasks are available in https://github.com/phermosilla/IEConv\_proteins/tree/master/Datasets. The code of the proposed method is available in https://github.com/GGchen1997/STEPS_Bioinformatics.

2022-04-06

ArXiv (preprint)