250 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Université Côte d'AzurFR9 papers
- Institut national de recherche en sciences et technologies du numériqueFR4 papers
- EURECOMFR3 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- Communauté d'universités et d'établissements Université Côte d'AzurFR2 papers
- École Nationale de l’Aviation CivileFR2 papers
- Institut de Biologie ValroseFR2 papers
- University College LondonGB2 papers
- Accenture (Ireland)IE1 paper
- ARGO: Apprentissage, graphes et optimisation distribuéeFR1 paper
- Assistance Publique – Hôpitaux de ParisFR1 paper
- Athinoula A. Martinos Center for Biomedical ImagingUS1 paper
19 papers
SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization
Yann Fraboni, Martin Van Waerebeke, Kevin Scaman +3
Machine Unlearning (MU) is an increasingly important topic in machine learning safety, aiming at removing the contribution of a given data point from a training procedure. Federate…
A geometric framework for asymptotic inference of principal subspaces in PCA
Dimbihery Rabenoro, Xavier Pennec
In this article, we develop an asymptotic method for constructing confidence regions for the set of all linear subspaces arising from PCA, from which we derive hypothesis tests on…
A General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updates
Yann Fraboni, Richard Vidal, Laetitia Kameni +1
We propose a novel framework to study asynchronous federated learning optimization with delays in gradient updates. Our theoretical framework extends the standard FedAvg aggregatio…
Privacy Preserving Image Registration
Riccardo Taiello, Melek Önen, Francesco Capano +2
Image registration is a key task in medical imaging applications, allowing to represent medical images in a common spatial reference frame. Current approaches to image registration…
Low-rank optimization methods based on projected projected-gradient descent that accumulate at Bouligand stationary points
Guillaume Olikier, Kyle A. Gallivan, P. -A. Absil
This paper considers the problem of minimizing a differentiable function with locally Lipschitz continuous gradient on the algebraic variety of real matrices of upper-bounded rank.…
Robust joint registration of multiple stains and MRI for multimodal 3D histology reconstruction: Application to the Allen human brain atlas
Adrià Casamitjana, Marco Lorenzi, Sebastiano Ferraris +6
Joint registration of a stack of 2D histological sections to recover 3D structure (``3D histology reconstruction'') finds application in areas such as atlas building and validation…
Vessel-CAPTCHA: an efficient learning framework for vessel annotation and segmentation
Vien Ngoc Dang, Francesco Galati, Rosa Cortese +7
Deep learning techniques for 3D brain vessel image segmentation have not been as successful as in the segmentation of other organs and tissues. This can be explained by two factors…
Joint data imputation and mechanistic modelling for simulating heart-brain interactions in incomplete datasets
Jaume Banus, Maxime Sermesant, Oscar Camara +1
The use of mechanistic models in clinical studies is limited by the lack of multi-modal patients data representing different anatomical and physiological processes. For example, ne…
Free-rider Attacks on Model Aggregation in Federated Learning
Yann Fraboni, Richard Vidal, Marco Lorenzi
Free-rider attacks against federated learning consist in dissimulating participation to the federated learning process with the goal of obtaining the final aggregated model without…
Classifying histograms of medical data using information geometry of beta distributions
Alice Le Brigant, Nicolas Guigui, Sana Rebbah +1
In this paper, we use tools of information geometry to compare, average and classify histograms. Beta distributions are fitted to the histograms and the corresponding Fisher inform…
Exploration of Balanced Metrics on Symmetric Positive Definite Matrices
Yann Thanwerdas, Xavier Pennec
Symmetric Positive Definite (SPD) matrices have been used in many fields of medical data analysis. Many Riemannian metrics have been defined on this manifold but the choice of the…
Learning a Probabilistic Model for Diffeomorphic Registration
Julian Krebs, Hervé Delingette, Boris Mailhé +2
We propose to learn a low-dimensional probabilistic deformation model from data which can be used for registration and the analysis of deformations. The latent variable model maps…
Math in the Black Forest: Workshop on New Directions in Shape Analysis
Martin Bauer, Nicolas Charon, Philipp Harms +9
These are the proceedings of the workshop "Math in the Black Forest", which brought together researchers in shape analysis to discuss promising new directions. Shape analysis is an…
Multi-Channel Stochastic Variational Inference for the Joint Analysis of Heterogeneous Biomedical Data in Alzheimer's Disease
Luigi Antelmi, Nicholas Ayache, Philippe Robert +1
The joint analysis of biomedical data in Alzheimer's Disease (AD) is important for better clinical diagnosis and to understand the relationship between biomarkers. However, jointly…
Parallel Transport with Pole Ladder: a Third Order Scheme in Affine Connection Spaces which is Exact in Affine Symmetric Spaces
Xavier Pennec
Parallel transport is an important step in many discrete algorithms for statistical computing on manifolds. Numerical methods based on Jacobi fields or geodesics parallelograms are…
3D Consistent & Robust Segmentation of Cardiac Images by Deep Learning with Spatial Propagation
Qiao Zheng, Hervé Delingette, Nicolas Duchateau +1
We propose a method based on deep learning to perform cardiac segmentation on short axis MRI image stacks iteratively from the top slice (around the base) to the bottom slice (arou…
Learning Myelin Content in Multiple Sclerosis from Multimodal MRI through Adversarial Training
Wen Wei, Emilie Poirion, Benedetta Bodini +4
Multiple sclerosis (MS) is a demyelinating disease of the central nervous system (CNS). A reliable measure of the tissue myelin content is therefore essential for the understanding…
3D Consistent Biventricular Myocardial Segmentation Using Deep Learning for Mesh Generation
Qiao Zheng, Hervé Delingette, Nicolas Duchateau +1
We present a novel automated method to segment the myocardium of both left and right ventricles in MRI volumes. The segmentation is consistent in 3D across the slices such that it…
Constraining the Dynamics of Deep Probabilistic Models
Marco Lorenzi, Maurizio Filippone
We introduce a novel generative formulation of deep probabilistic models implementing "soft" constraints on their function dynamics. In particular, we develop a flexible methodolog…