Publications

Personalized Prediction of Future Lesion Activity and Treatment Effect in Multiple Sclerosis from Baseline MRI
Joshua D. Durso-Finley
Jean-Pierre R. Falet
Brennan Nichyporuk
Douglas Arnold
Tal Arbel
Precision medicine for chronic diseases such as multiple sclerosis (MS) involves choosing a treatment which best balances efficacy and side … (voir plus)effects/preferences for individual patients. Making this choice as early as possible is important, as delays in finding an effective therapy can lead to irreversible disability accrual. To this end, we present the first deep neural network model for individualized treatment decisions from baseline magnetic resonance imaging (MRI) (with clinical information if available) for MS patients which (a) predicts future new and enlarging T2 weighted (NE-T2) lesion counts on follow-up MRI on multiple treatments and (b) estimates the conditional average treatment effect (CATE), as defined by the predicted future suppression of NE-T2 lesions, between different treatment options relative to placebo. Our model is validated on a proprietary federated dataset of 1817 multi-sequence MRIs acquired from MS patients during four multi-centre randomized clinical trials. Our framework achieves high average precision in the binarized regression of future NE-T2 lesions on five different treatments, identifies heterogeneous treatment effects, and provides a personalized treatment recommendation that accounts for treatment-associated risk (side effects, patient preference, administration difficulties,...).
2022-12-03
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning (publié)
doi.org
proceedings.mlr.press
Segmentation-Consistent Probabilistic Lesion Counting
Julien Schroeter
Chelsea Myers-colet
Douglas Arnold
Tal Arbel
Lesion counts are important indicators of disease severity, patient prognosis, and treatment efficacy, yet counting as a task in medical ima… (voir plus)ging is often overlooked in favor of segmentation. This work introduces a novel continuously differentiable function that maps lesion segmentation predictions to lesion count probability distributions in a consistent manner. The proposed end-to-end approach—which consists of voxel clustering, lesion-level voxel probability aggregation, and Poisson-binomial counting—is non-parametric and thus offers a robust and consistent way to augment lesion segmentation models with post hoc counting capabilities. Experiments on Gadolinium-enhancing lesion counting demonstrate that our method outputs accurate and well-calibrated count distributions that capture meaningful uncertainty information. They also reveal that our model is suitable for multi-task learning of lesion segmentation, is efficient in low data regimes, and is robust to adversarial attacks.
2022-12-03
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning (publié)
doi.org
proceedings.mlr.press
Tackling hypo and hyper sensory processing heterogeneity in autism: From clinical stratification to genetic pathways
Aline Lefebvre
Julian Tillmann
Freddy Cliquet
Frederique Amsellem
Anna Maruani
Claire Leblond
Anita Beggiato
David Germanaud
Anouck Amestoy
Myriam Ly‐Le Moal
Daniel Umbricht
Christopher H. Chatham
Lorraine Murtagh
Manuel Bouvard
Marion Leboyer
Tony Charman
Thomas Bourgeron
Richard Delorme
Guillaume Dumas
2022-12-03
Autism Research (publié)
doi.org
Performative Prediction in Time Series: A Case Study
Rupali Bhati
Jennifer Jones
David Langelier
Anthony Reiman
Jonathan Greenland
Kristin Campbell
Audrey Durand
2022-12-01
NeurIPS.cc/2022/Workshop/TS4H (poster)
openreview.net
openreview.net
Advancing ethics review practices in AI research
Madhulika Srikumar
Rebecca Finlay
Grace M. Abuhamad
Carolyn Ashurst
Rosie Campbell
Emily Campbell-Ratcliffe
Hudson Hongo
Sara Rene Jordan
Joseph Lindley
Aviv Ovadya
Joelle Pineau
2022-11-30
Nature Machine Intelligence (publié)
doi.org
APOE alleles are associated with sex-specific structural differences in brain regions affected in Alzheimer's disease and related dementia
Chloé Savignac
Sylvia Villeneuve
AmanPreet Badhwar
Karin Saltoun
Kimia Shafighi
Chris Zajner
Vaibhav Sharma
Sarah A. Gagliano Taliun
Sali Farhan
Judes Poirier
Danilo Bzdok
Alzheimer’s disease is marked by intracellular tau aggregates in the medial temporal lobe (MTL) and extracellular amyloid aggregates in th… (voir plus)e default network (DN). Here, we examined codependent structural variations between the MTL’s most vulnerable structure, the hippocampus (HC), and the DN at subregion resolution in individuals with Alzheimer’s disease and related dementia (ADRD). By leveraging the power of the approximately 40,000 participants of the UK Biobank cohort, we assessed impacts from the protective APOE ɛ2 and the deleterious APOE ɛ4 Alzheimer’s disease alleles on these structural relationships. We demonstrate ɛ2 and ɛ4 genotype effects on the inter-individual expression of HC-DN co-variation structural patterns at the population level. Across these HC-DN signatures, recurrent deviations in the CA1, CA2/3, molecular layer, fornix’s fimbria, and their cortical partners related to ADRD risk. Analyses of the rich phenotypic profiles in the UK Biobank cohort further revealed male-specific HC-DN associations with air pollution and female-specific associations with cardiovascular traits. We also showed that APOE ɛ2/2 interacts preferentially with HC-DN co-variation patterns in estimating social lifestyle in males and physical activity in females. Our structural, genetic, and phenotypic analyses in this large epidemiological cohort reinvigorate the often-neglected interplay between APOE ɛ2 dosage and sex and link APOE alleles to inter-individual brain structural differences indicative of ADRD familial risk.
2022-11-30
PLoS Biology (publié)
doi.org
Autism incidence and spatial analysis in more than 7 million pupils in English schools: a retrospective, longitudinal, school registry study.
Andres Roman-Urrestarazu
Justin Christopher Yang
R. van Kessel
Varun Warrier
Guillaume Dumas
H. Jongsma
Gabriel Gatica-bahamonde
Carrie Allison
F. Matthews
Simon Baron-Cohen
Carol Brayne
2022-11-30
The Lancet Child & Adolescent Health (publié)
doi.org
Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining
Andreas Madsen
Nicholas Meade
Vaibhav Adlakha
Siva Reddy
To explain NLP models a popular approach is to use importance measures, such as attention, which inform input tokens are important for makin… (voir plus)g a prediction. However, an open question is how well these explanations accurately reflect a model's logic, a property called faithfulness. To answer this question, we propose Recursive ROAR, a new faithfulness metric. This works by recursively masking allegedly important tokens and then retraining the model. The principle is that this should result in worse model performance compared to masking random tokens. The result is a performance curve given a masking-ratio. Furthermore, we propose a summarizing metric using relative area-between-curves (RACU), which allows for easy comparison across papers, models, and tasks. We evaluate 4 different importance measures on 8 different datasets, using both LSTM-attention models and RoBERTa models. We find that the faithfulness of importance measures is both model-dependent and task-dependent. This conclusion contradicts previous evaluations in both computer vision and faithfulness of attention literature.
2022-11-30
Findings of the Association for Computational Linguistics: EMNLP 2022 (publié)
doi.org
arxiv.org
Implementing automation in deep brain stimulation: has the time come?
Marco Bonizzato
Alfonso Fasano
2022-11-30
The Lancet Digital Health (publié)
doi.org
Improving Passage Retrieval with Zero-Shot Question Generation
Devendra Singh Sachan
Mike Lewis
Mandar Joshi
Armen Aghajanyan
Wen-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… (voir plus)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.
2022-11-30
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (publié)
doi.org
arxiv.org
In-Processing Fairness Improvement Methods for Regression Data-Driven Building Models: Achieving Uniform Energy Prediction
Ying Sun
Benjamin C. M. Fung
Fariborz Haghighat
2022-11-30
Energy and Buildings (publié)
doi.org
A Multifaceted Framework to Evaluate Evasion, Content Preservation, and Misattribution in Authorship Obfuscation Techniques
Malik H. Altakrori
Thomas Scialom
Benjamin C. M. Fung
Jackie CK Cheung
2022-11-30
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (publié)
doi.org