Explanipedia

Uncertain but Useful: Leveraging CNN Variability into Data Augmentation Open

Inés Gonzalez-Pepe, Vinuyan Sivakolunthu, Yohan Chatelain, Tristan Glatard · 2025

Deep learning (DL) is rapidly advancing neuroimaging by achieving state-of-the-art performance with reduced computation times. Yet the numerical stability of DL models -- particularly during training -- remains underexplored. While inferen…

Numerical Uncertainty in Linear Registration: An Experimental Study Open

Niusha Mirhakimi, Tristan Glatard, Jean‐Baptiste Poline · 2025

While linear registration is a critical step in MRI preprocessing pipelines, its numerical uncertainty is understudied. Using Monte-Carlo Arithmetic (MCA) simulations, we assessed the most commonly used linear registration tools within maj…

Styx: A multi-language API Generator for Command-Line Tools Open

Florian Rupprecht, Jason Kai, Biraj Shrestha, Steven Giavasis, Ting Xu , et al. · 2025

In numerous scientific domains, established tools have often been developed with complex command-line interfaces. Such is the case for brain imaging and bioinformatics, making the use of powerful legacy tools in modern workflow paradigms c…

Open-source tools and platforms to investigate analytical variability in neuroimaging Open

Jacob Sanz-Robinson, Michelle Wang, Brent McPherson, Tristan Glatard, Jean‐Baptiste Poline · 2025

Researchers in brain imaging have access to a multitude of analysis tools, many of which carry out the same or similar tasks but yield different results when applied to the same data. This analytical flexibility often undermines reproducib…

Predicting Parkinson’s disease trajectory using clinical and functional MRI features: A reproduction and replication study Open

Élodie Germani, Nikhil Bhagwat, Mathieu Dugré, Rémi Gau, Albert Montillo , et al. · 2025

Parkinson’s disease (PD) is a common neurodegenerative disorder with a poorly understood physiopathology and no established biomarkers for the diagnosis of early stages and for prediction of disease progression. Several neuroimaging biomar…

Open-source platforms to investigate analytical flexibility in neuroimaging Open

Jacob Sanz-Robinson, Michelle Wang, Brent McPherson, Yohan Chatelain, David W. Kennedy , et al. · 2025

Researchers in brain imaging have access to a multitude of analysis tools, many of which carry out the same or similar tasks but yield different results when applied to the same data. This analytical flexibility often undermines reproducib…

Advances in Power Consumption Model For Data Centers: Analytical Formulas vs. Machine Learning Models Open

Sebastian Racedo, Brigitte Jaumard, Tristan Glatard, Oscar Delgado, Meysam Masoudi · 2025

The impact of FreeSurfer versions on structural neuroimaging analyses of Parkinson’s disease Open

Andrzej Sokołowski, Nikhil Bhagwat, Dimitrios Kirbizakis, Yohan Chatelain, Mathieu Dugré , et al. · 2024

Image processing software impacts the quantification of brain measures, playing an important role in the search for clinical biomarkers. We investigated the impact of the variability between FreeSurfer releases on the estimation of structu…

An analysis of performance bottlenecks in MRI preprocessing Open

Mathieu Dugré, Yohan Chatelain, Tristan Glatard · 2024

Magnetic resonance imaging (MRI) preprocessing is a critical step for neuroimaging analysis. However, the computational cost of MRI preprocessing pipelines is a major bottleneck for large cohort studies and some clinical applications. Whil…

Why experimental variation in neuroimaging should be embraced Open

Gregory Kiar, Jeanette A. Mumford, Ting Xu, Joshua T Vogelstein, Tristan Glatard , et al. · 2024

Training Compute-Optimal Vision Transformers for Brain Encoding Open

Sana Ahmadi, Francois Paugam, Tristan Glatard, Pierre Bellec · 2024

The optimal training of a vision transformer for brain encoding depends on three factors: model size, data size, and computational resources. This study investigates these three pillars, focusing on the effects of data scaling, model scali…

Registered report: Age-preserved semantic memory and the CRUNCH effect manifested as differential semantic control networks: An fMRI study Open

Niobe Haitas, Jade Dubuc, Camille Massé-Leblanc, Vincent Chamberland, Mahnoush Amiri , et al. · 2024

Semantic memory representations are generally well maintained in aging, whereas semantic control is thought to be more affected. To explain this phenomenon, this study tested the predictions of the Compensation-Related Utilization of Neura…

The Impact of Hardware Variability on Applications Packaged with Docker and Guix: a Case Study in Neuroimaging Open

Gaël Vila, Emmanuel Medernach, Inés Gonzalez, Axel Bonnet, Yohan Chatelain , et al. · 2024

Submitted at https://acm-rep.github.io/2024/

An Analysis of Performance Bottlenecks in MRI Pre-Processing Open

Mathieu Dugré, Yohan Chatelain, Tristan Glatard · 2024

Magnetic Resonance Image (MRI) pre-processing is a critical step for neuroimaging analysis. However, the computational cost of MRI pre-processing pipelines is a major bottleneck for large cohort studies and some clinical applications. Whil…

Open-source tools and platforms to investigate analytical variability in neuroimaging Open

Jacob Sanz-Robinson, Michelle Wang, Brent McPherson, Tristan Glatard, Jean‐Baptiste Poline · 2024

Analytical variability often undermines the reproducibility of neuroimaging studies. Researchers have access to a multitude of analysis tools, many of which carry out the same tasks but yield different results when applied to the same data…

Hierarchical storage management in user space for neuroimaging applications Open

Valérie Hayot-Sasson, Tristan Glatard · 2024

Neuroimaging open-data initiatives have led to increased availability of large scientific datasets. While these datasets are shifting the processing bottleneck from compute-intensive to data-intensive, current standardized analysis tools h…

Scaling up ridge regression for brain encoding in a massive individual fMRI dataset Open

Sana Ahmadi, Pierre Bellec, Tristan Glatard · 2024

Brain encoding with neuroimaging data is an established analysis aimed at predicting human brain activity directly from complex stimuli features such as movie frames. Typically, these features are the latent space representation from an ar…

Predicting Parkinson's disease trajectory using clinical and functional MRI features: a reproduction and replication study Open

Élodie Germani, Nikhil Baghwat, Mathieu Dugré, Rémi Gau, Albert Montillo , et al. · 2024

Parkinson's disease (PD) is a common neurodegenerative disorder with a poorly understood physiopathology and no established biomarkers for the diagnosis of early stages and for prediction of disease progression. Several neuroimaging biomar…

Longitudinal brain structure changes in Parkinson’s disease: A replication study Open

Andrzej Sokołowski, Nikhil Bhagwat, Yohan Chatelain, Mathieu Dugré, Alexandru Hanganu , et al. · 2024

Context An existing major challenge in Parkinson’s disease (PD) research is the identification of biomarkers of disease progression. While magnetic resonance imaging is a potential source of PD biomarkers, none of the magnetic resonance im…

Numerical stability of DeepGOPlus inference Open

Inés Gonzalez Pepe, Yohan Chatelain, Gregory Kiar, Tristan Glatard · 2024

Convolutional neural networks (CNNs) are currently among the most widely-used deep neural network (DNN) architectures available and achieve state-of-the-art performance for many problems. Originally applied to computer vision tasks, CNNs w…

Open Data Governance at the Canadian Open Neuroscience Platform (CONP): From the Walled Garden to the Arboretum Open

Alexander Bernier, Bartha Maria Knoppers, Patrick Bermudez, Michael J. S. Beauvais, Adrian Thorogood , et al. · 2024

Scientific research communities pursue dual imperatives in implementing strategies to share their data. These communities attempt to maximize the accessibility of biomedical data for downstream research use, in furtherance of open science …

Monte Carlo Arithmetic Instrumented DeepGOPlus Protein Function Predictions Open

Inés Gonzalez Pepe, Yohan Chatelain, Gregory Kiar, Tristan Glatard · 2023

This dataset contains the perturbed protein function predictions by the DeepGOPlus model excluding the Diamond tool component. The model was perturbed with Verrou, an implementation of Monte Carlo Arithmetic (MCA), a stochastic arithmetic …

Monte Carlo Arithmetic Instrumented DeepGOPlus Protein Function Predictions Open

Inés Gonzalez Pepe, Yohan Chatelain, Gregory Kiar, Tristan Glatard · 2023

This dataset contains the perturbed protein function predictions by the DeepGOPlus model excluding the Diamond tool component. The model was perturbed with Verrou, an implementation of Monte Carlo Arithmetic (MCA), a stochastic arithmetic …

Classification of Anomalies in Telecommunication Network KPI Time Series Open

Korantin Bordeau-Aubert, J. A. Whatley, Sylvain Nadeau, Tristan Glatard, Brigitte Jaumard · 2023

The increasing complexity and scale of telecommunication networks have led to a growing interest in automated anomaly detection systems. However, the classification of anomalies detected on network Key Performance Indicators (KPI) has rece…

Numerical Uncertainty of Convolutional Neural Networks Inference for Structural Brain MRI Analysis Open

Inés Gonzalez Pepe, Vinuyan Sivakolunthu, Hae Lang Park, Yohan Chatelain, Tristan Glatard · 2023

This paper investigates the numerical uncertainty of Convolutional Neural Networks (CNNs) inference for structural brain MRI analysis. It applies Random Rounding -- a stochastic arithmetic technique -- to CNN models employed in non-linear …

Registered report: Age-preserved semantic memory and the CRUNCH effect manifested as differential semantic control networks: an fMRI study Open

Niobe Haitas, Jade Dubuc, Camille Massé-Leblanc, Vincent Chamberland, Mahnoush Amiri , et al. · 2023

Semantic memory representations are generally well maintained in aging, whereas semantic control is thought to be more affected. To explain this phenomenon, this study tested the predictions of the Compensation-Related Utilization of Neura…

A numerical variability approach to results stability tests and its application to neuroimaging Open

Yohan Chatelain, Loïc Tetrel, Christopher J. Markiewicz, Mathias Goncalves, Gregory Kiar , et al. · 2023

Ensuring the long-term reproducibility of data analyses requires results stability tests to verify that analysis results remain within acceptable variation bounds despite inevitable software updates and hardware evolutions. This paper intr…

Predicting Parkinson’s disease progression using MRI-based white matter radiomic biomarker and machine learning: a reproducibility and replicability study Open

Mohanad Arafe, Nikhil Bhagwat, Yohan Chatelain, Mathieu Dugré, Andrzej Sokołowski , et al. · 2023

Background The availability of reliable biomarkers of Parkinson’s disease (PD) progression is critical to the understanding of the disease and development of treatment options. Magnetic Resonance Imaging (MRI) provides a promising source o…

Longitudinal brain structure changes in Parkinson’s disease: a replication study Open

Andrzej Sokołowski, Nikhil Bhagwat, Yohan Chatelain, Mathieu Dugré, Alexandru Hanganu , et al. · 2023

Context An existing major challenge in Parkinson’s disease (PD) research is the identification of biomarkers of disease progression. While Magnetic Resonance Imaging (MRI) is a potential source of PD biomarkers, none of the MRI measures of…

Reproducibility of Tumor Segmentation Outcomes with a Deep Learning Model Open

Morgane Des Ligneris, Axel Bonnet, Yohan Chatelain, Tristan Glatard, Michaël Sdika , et al. · 2023

International audience

Tristan Glatard YOU? Author Swipe