Publications

The Image Biomarker Standardization Initiative: Standardized Convolutional Filters for Reproducible Radiomics and Enhanced Clinical Insights
Philip Whybra
Alex Zwanenburg
Vincent Andrearczyk
Roger Schaer
Aditya P. Apte
Alexandre Ayotte
Bhakti Baheti
Spyridon Bakas
Andrea Bettinelli
Ronald Boellaard
Luca Boldrini
Irene Buvat
Gary J. R. Cook
Florian Dietsche
Nicola Dinapoli
Hubert S. Gabryś
Vicky Goh
Matthias Guckenberger
Mathieu Hatt
Mahdi Hosseinzadeh … (voir 26 de plus)
Aditi Iyer
Jacopo Lenkowicz
Mahdi A. L. Loutfi
Steffen Löck
Francesca Marturano
Olivier Morin
Christophe Nioche
Fanny Orlhac
Sarthak Pati
Arman Rahmim
Seyed Masoud Rezaeijo
Christopher G. Rookyard
Mohammad R. Salmanpour
Andreas Schindele
Isaac Shiri
Emiliano Spezi
Stephanie Tanadini-Lang
Florent Tixier
Taman Upadhaya
Vincenzo Valentini
Joost J. M. van Griethuysen
Fereshteh Yousefirizi
Habib Zaidi
Henning Müller
Martin Vallières
Adrien Depeursinge
2024-01-31
Radiology (publié)
doi.org
The State of Artificial Intelligence in Pediatric Surgery: A Systematic Review
Mohamed Elahmedi
Riya Sawhney
Elena Guadagno
Fabio Botelho
Dan Poenaru
2024-01-31
Journal of Pediatric Surgery (publié)
doi.org
Understanding metric-related pitfalls in image analysis validation
Annika Reinke
Minu D. Tizabi
Michael Baumgartner
Matthias Eisenmann
DOREEN HECKMANN-NÖTZEL
A. EMRE KAVUR
TIM RÄDSCH
Carole H. Sudre
Laura Acion
Michela Antonelli
Tal Arbel
Spyridon Bakas
Arriel Benis
Arriel Benis
Matthew B. Blaschko
Florian Buettner
M. Jorge Cardoso
Veronika Cheplygina
Jianxu Chen
Evangelia Christodoulou … (voir 59 de plus)
BETH A. CIMINI
Keyvan Farahani
LUCIANA FERRER
Gary S. Collins
Adrian Galdran
Bram van Ginneken
Ben Glocker
PATRICK GODAU
Daniel A. Hashimoto
Michael M. Hoffman
Robert Haase
Merel Huisman
Fabian Isensee
Pierre Jannin
CHARLES E. KAHN
Dagmar Kainmueller
BERNHARD KAINZ
Alexandros Karargyris
Jens Kleesiek
Florian Kofler
Thijs Kooi
Annette Kopp-Schneider
Alan Karthikesalingam
Hannes Kenngott
Michal Kozubek
Anna Kreshuk
Tahsin Kurc
Bennett A. Landman
GEERT LITJENS
Amin Madani
Klaus Maier-Hein
Anne L. Martel
Erik Meijering
Bjoern Menze
Karel G.M. Moons
Henning Müller
Brennan Nichyporuk
Felix Nickel
Peter Mattson
Jens Petersen
Susanne M. Rafelski
Nasir Rajpoot
Mauricio Reyes
MICHAEL A. RIEGLER
Nicola Rieke
Julio Saez-Rodriguez
Clara I. Sánchez
Shravya Shetty
Ronald M. Summers
Abdel A. Taha
Aleksei Tiulpin
Sotirios A. Tsaftaris
Ben Van Calster
Gael Varoquaux
Amin Madani
Ziv R. Yaniv
PAUL F. JÄGER
Lena Maier-Hein
Anne L. Martel
Validation metrics are key for the reliable tracking of scientific progress and for bridging the current chasm between artificial intelligen… (voir plus)ce (AI) research and its translation into practice. However, increasing evidence shows that particularly in image analysis, metrics are often chosen inadequately in relation to the underlying research problem. This could be attributed to a lack of accessibility of metric-related knowledge: While taking into account the individual strengths, weaknesses, and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multi-stage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides the first reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. Focusing on biomedical image analysis but with the potential of transfer to other fields, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. To facilitate comprehension, illustrations and specific examples accompany each pitfall. As a structured body of information accessible to researchers of all levels of expertise, this work enhances global comprehension of a key topic in image analysis validation.
2024-01-31
Nature Methods (publié)
doi.org
arxiv.org
Using Artificial Intelligence to Label Free-Text Operative and Ultrasound Reports for Grading Pediatric Appendicitis.
Waseem Abu-Ashour
Sister Mary Emil
Sherif Emil
Dan Poenaru
2024-01-31
Journal of Pediatric Surgery (publié)
doi.org
Nonreciprocal synchronization in embryonic oscillator ensembles
Christine Ho
Laurent Jutras-Dubé
Michael L. Zhao
Gregor Mönke
István Z. Kiss
Paul François
Alexander Aulehla
Synchronization of coupled oscillators is a universal phenomenon encountered across different scales and contexts e.g., chemical wave patter… (voir plus)ns, superconductors and the unison applause we witness in concert halls. The existence of common underlying coupling rules define universality classes, revealing a fundamental sameness between seemingly distinct systems. Identifying rules of synchronization in any particular setting is hence of paramount relevance. Here, we address the coupling rules within an embryonic oscillator ensemble linked to vertebrate embryo body axis segmentation. In vertebrates, the periodic segmentation of the body axis involves synchronized signaling oscillations in cells within the presomitic mesoderm (PSM), from which somites, the pre-vertebrae, form. At the molecular level, it is known that intact Notch-signaling and cell-to-cell contact is required for synchronization between PSM cells. However, an understanding of the coupling rules is still lacking. To identify these, we develop a novel experimental assay that enables direct quantification of synchronization dynamics within mixtures of oscillating cell ensembles, for which the initial input frequency and phase distribution are known. Our results reveal a “winner-takes-it-all” synchronization outcome i.e., the emerging collective rhythm matches one of the input rhythms. Using a combination of theory and experimental validation, we develop a new coupling model, the “Rectified Kuramoto” (ReKu) model, characterized by a phase-dependent, non-reciprocal interaction in the coupling of oscillatory cells. Such non-reciprocal synchronization rules reveal fundamental similarities between embryonic oscillators and a class of collective behaviours seen in neurons and fireflies, where higher level computations are performed and linked to non-reciprocal synchronization.
2024-01-30
bioRxiv (prépublication)
doi.org
Blockwise Self-Supervised Learning at Scale
Shoaib Ahmed Siddiqui
David M. Krueger
Yann Lecun
Stephane Deny
2024-01-29
TMLR (accepté)
doi.org
openreview.net
Integrating accompanying patients into clinical oncology teams: limiting and facilitating factors
Marie-Pascale Pomey
Jesseca Paquette
Monica Iliescu Nelea
Cécile Vialaron
Rim Mourad
Karine Bouchard
Louise Normandin
Marie-Andrée Côté
Mado Desforges
Pénélope Pomey-Carpentier
Israël Fortin
Isabelle Ganache
Catherine Régis
Zeev Rosberger
Danielle Charpentier
Marie-France Vachon
Lynda Bélanger
Michel Dorval
Djahanchah P. Ghadiri
Mélanie Lavoie-Tremblay … (voir 5 de plus)
Antoine Boivin
Jean-François Pelletier
Nicolas Fernandez
Alain M. Danino
Michèle de Guise
Objectives Since 2018, four establishments in Quebec have been instrumental in implementing the PAROLE-Onco program, which introduced accomp… (voir plus)anying patients (APs) in healthcare teams to improve cancer patients’ experience. APs are patient advisors who have acquired specific experiential knowledge related to living with cancer, using services, and interacting with healthcare professionals. They are therefore in a unique and reliable position to be able to provide emotional, informational, cognitive and navigational support to patients dealing with cancer. We aimed to explore APs’ perspectives regarding the limiting and facilitating factors in terms of how they are integrated into the clinical oncology teams. Methods A qualitative study based on semi-structured interviews and focus groups was conducted with 20 APs at the beginning of their intervention (T1) and two years afterwards (T2). Limiting and facilitating factors of APs’ integration into clinical teams were analyzed in terms of governance, culture, resources and tools. Results The most significant limiting factors raised by APs to be integrated into clinical teams were: governance involvement, organizational boundaries, team members' availabilities, and confusion about the specific roles played by APs. Communication challenges were also raised, leading to inadequate promotion of the program to patients. The lack of time, space and compensation were also mentioned as limiting factors. Creating opportunities for team members to meet APs, building trust and teaching team members how APs’ activities are complementary to theirs were enhancing factors. Other facilitators include APs being involved in decision-making committees, being leaders in the PAROLE-Onco program promotion to patients and clinical team members and creating opportunities to communicate with team members to help enhance their work and provide feedback to improve patient services. Awareness of APs’ added value for the team and patients is also a key facilitator. Regarding tools, offering accompanying services by telephone allows both patients and APs to benefit from the flexibility they need. Conclusion Over time, APs were able to identify the best factors for successful implementation. Recommendations include APs and professionals working in co-construction on organization, leadership, resources, and status factors. This could help catalyze a change in culture within health establishments and allow people dealing with cancer to benefit from the experiential knowledge of other patients within their clinical team.
2024-01-29
BMC Health Services Research (publié)
doi.org
Learning self-supervised molecular representations for drug–drug interaction prediction
Rogia Kpanou
Patrick Dallaire
Elsa Rousseau
J. Corbeil
2024-01-29
BMC Bioinformatics (publié)
doi.org
PERFUMES: pipeline to extract RNA functional motifs and exposed structures
Arnaud Chol
Roman Sarrazin-Gendron
Éric Lécuyer
Mathieu Blanchette
Jérôme Waldispühl
Abstract Motivation Up to 75% of the human genome encodes RNAs. The function of many non-coding RNAs relies on their ability to fold into 3D… (voir plus) structures. Specifically, nucleotides inside secondary structure loops form non-canonical base pairs that help stabilize complex local 3D structures. These RNA 3D motifs can promote specific interactions with other molecules or serve as catalytic sites. Results We introduce PERFUMES, a computational pipeline to identify 3D motifs that can be associated with observable features. Given a set of RNA sequences with associated binary experimental measurements, PERFUMES searches for RNA 3D motifs using BayesPairing2 and extracts those that are over-represented in the set of positive sequences. It also conducts a thermodynamics analysis of the structural context that can support the interpretation of the predictions. We illustrate PERFUMES’ usage on the SNRPA protein binding site, for which the tool retrieved both previously known binder motifs and new ones. Availability and implementation PERFUMES is an open-source Python package (https://jwgitlab.cs.mcgill.ca/arnaud_chol/perfumes).
2024-01-29
Bioinform. (publié)
doi.org
The Effects of a Digital Game Simulator versus a Traditional Intervention on Paramedics’ Neonatal Resuscitation Performance
Maria Cutumisu
Georg M. Schmölzer
2024-01-29
Children (publié)
doi.org
Unsupervised Discovery of Steerable Factors When Graph Deep Generative Models Are Entangled
Shengchao Liu
Chengpeng Wang
Jiarui Lu
Weili Nie
Hanchen Wang
Zhuoxinran Li
Bolei Zhou
Jian Tang
2024-01-29
TMLR (accepté)
openreview.net
openreview.net
Asymmetric stimulus representations bias visual perceptual learning
Pooya Laamerad
Asmara Awada
Christopher C. Pack
Shahab Bakhtiari
The primate visual cortex contains various regions that exhibit specialization for different stimulus properties, such as motion, shape, and… (voir plus) color. Within each region, there is often further specialization, such that particular stimulus features, such as horizontal and vertical orientations, are over-represented. These asymmetries are associated with well-known perceptual biases, but little is known about how they influence visual learning. Most theories would predict that learning is optimal, in the sense that it is unaffected by these asymmetries. However, other approaches to learning would result in specific patterns of perceptual biases. To distinguish between these possibilities, we trained human observers to discriminate between expanding and contracting motion patterns, which have a highly asymmetrical representation in the visual cortex. Observers exhibited biased percepts of these stimuli, and these biases were affected by training in ways that were often suboptimal. We simulated different neural network models and found that a learning rule that involved only adjustments to decision criteria, rather than connection weights, could account for our data. These results suggest that cortical asymmetries influence visual perception and that human observers often rely on suboptimal strategies for learning.
2024-01-28
Journal of Vision (publié)
doi.org