Portrait of Hervé Lombaert

Hervé Lombaert

Associate Academic Member
Associate Professor, Polytechnique Montréal, Department of Computer Engineering Department
Research Topics
Computer Vision
Learning on Graphs
Medical Machine Learning
Google Scholar

Biography

Hervé Lombaert is an associate professor in the Computer Engineering Department at Polytechnique Montréal, and the Canada Research Chair in Shape Analysis in Medical Imaging. His research focuses on the statistics and analysis of shapes in the context of machine learning and medical imaging. His work on graph analysis has impacted several applications in medical imaging, from early image segmentation with graph-cuts to recent surface analysis with spectral graph theory.

Lombaert has authored over seventy papers, holds five patents and has earned several awards, including the IPMI Erbsmann Prize. His students have also received best thesis awards with impactful publications in medical image computing. He is on the editorial board of Medical Image Analysis. He has also worked in a number of other research centres, including the INRIA Sophia-Antipolis (France), Microsoft Research (Cambridge, U.K.), Siemens Corporate Research (Princeton, NJ) and McGill University.

Current Students

Zeinab Abboud
PhD - Polytechnique Montréal
Github
Sukesh Adiga Vasudeva
PhD - Polytechnique Montréal
Website
Github
Google Scholar
Pierre Louis Benveniste
PhD - Polytechnique Montréal
Principal supervisor :
Julien Cohen-Adad
Website
Github
Google Scholar
Sahar Dastani Oghani
PhD - École de technologie suprérieure
Website
Github
Melanie Gaillochet
PhD - Polytechnique Montréal
Github

Publications

Sparse Bayesian Networks: Efficient Uncertainty Quantification in Medical Image Analysis
Zeinab Abboud
Hervé Lombaert
Samuel Kadoury
Efficiently quantifying predictive uncertainty in medical images remains a challenge. While Bayesian neural networks (BNN) offer predictive … (see more)uncertainty, they require substantial computational resources to train. Although Bayesian approximations such as ensembles have shown promise, they still suffer from high training and inference costs. Existing approaches mainly address the costs of BNN inference post-training, with little focus on improving training efficiency and reducing parameter complexity. This study introduces a training procedure for a sparse (partial) Bayesian network. Our method selectively assigns a subset of parameters as Bayesian by assessing their deterministic saliency through gradient sensitivity analysis. The resulting network combines deterministic and Bayesian parameters, exploiting the advantages of both representations to achieve high task-specific performance and minimize predictive uncertainty. Demonstrated on multi-label ChestMNIST for classification and ISIC, LIDC-IDRI for segmentation, our approach achieves competitive performance and predictive uncertainty estimation by reducing Bayesian parameters by over 95\%, significantly reducing computational expenses compared to fully Bayesian and ensemble methods.
2024-10-03
Lecture Notes in Computer Science (published)
doi.org
arxiv.org
Automating MedSAM by Learning Prompts with Weak Few-Shot Supervision
Mélanie Gaillochet
Christian Desrosiers
Hervé Lombaert
2024-09-28
Lecture Notes in Computer Science (published)
doi.org
arxiv.org
Neighbor-Aware Calibration of Segmentation Networks with Penalty-Based Constraints
Balamurali Murugesan
Sukesh Adiga Vasudeva
Bingyuan Liu
Hervé Lombaert
Ismail Ben Ayed
Jose Dolz
Ensuring reliable confidence scores from deep neural networks is of paramount significance in critical decision-making systems, particularly… (see more) in real-world domains such as healthcare. Recent literature on calibrating deep segmentation networks has resulted in substantial progress. Nevertheless, these approaches are strongly inspired by the advancements in classification tasks, and thus their uncertainty is usually modeled by leveraging the information of individual pixels, disregarding the local structure of the object of interest. Indeed, only the recent Spatially Varying Label Smoothing (SVLS) approach considers pixel spatial relationships across classes, by softening the pixel label assignments with a discrete spatial Gaussian kernel. In this work, we first present a constrained optimization perspective of SVLS and demonstrate that it enforces an implicit constraint on soft class proportions of surrounding pixels. Furthermore, our analysis shows that SVLS lacks a mechanism to balance the contribution of the constraint with the primary objective, potentially hindering the optimization process. Based on these observations, we propose NACL (Neighbor Aware CaLibration), a principled and simple solution based on equality constraints on the logit values, which enables to control explicitly both the enforced constraint and the weight of the penalty, offering more flexibility. Comprehensive experiments on a wide variety of well-known segmentation benchmarks demonstrate the superior calibration performance of the proposed approach, without affecting its discriminative power. Furthermore, ablation studies empirically show the model agnostic nature of our approach, which can be used to train a wide span of deep segmentation networks.
2024-01-25
ArXiv (preprint)
doi.org
arxiv.org
Real-time simulation of viscoelastic tissue behavior with physics-guided deep learning
Mohammad Karami
Hervé Lombaert
David Rivest‐henault
2023-03-01
Computerized Medical Imaging and Graphics (published)
doi.org
arxiv.org
Medial Spectral Coordinates for 3D Shape Analysis
Morteza Rezanejad
Mohammad Khodadad
Hamidreza Mahyar
Hervé Lombaert
Michael Gruninger
Dirk B. Walther
Kaleem Siddiqi
In recent years there has been a resurgence of interest in our community in the shape analysis of 3D objects repre-sented by surface meshes,… (see more) their voxelized interiors, or surface point clouds. In part, this interest has been stimulated by the increased availability of RGBD cameras, and by applications of computer vision to autonomous driving, medical imaging, and robotics. In these settings, spectral co-ordinates have shown promise for shape representation due to their ability to incorporate both local and global shape properties in a manner that is qualitatively invariant to iso-metric transformations. Yet, surprisingly, such coordinates have thus far typically considered only local surface positional or derivative information. In the present article, we propose to equip spectral coordinates with medial (object width) information, so as to enrich them. The key idea is to couple surface points that share a medial ball, via the weights of the adjacency matrix. We develop a spectral feature using this idea, and the algorithms to compute it. The incorporation of object width and medial coupling has direct benefits, as illustrated by our experiments on object classification, object part segmentation, and surface point correspondence.
2022-06-18
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (published)
doi.org
arxiv.org
Medial Spectral Coordinates for 3D Shape Analysis
Morteza Rezanejad
Mohammad Khodadad
H. Mahyar
Hervé Lombaert
M. Gruninger
Dirk. B. Walther
Kaleem Siddiqi
In recent years there has been a resurgence of interest in our community in the shape analysis of 3D objects repre-sented by surface meshes,… (see more) their voxelized interiors, or surface point clouds. In part, this interest has been stimulated by the increased availability of RGBD cameras, and by applications of computer vision to autonomous driving, medical imaging, and robotics. In these settings, spectral co-ordinates have shown promise for shape representation due to their ability to incorporate both local and global shape properties in a manner that is qualitatively invariant to iso-metric transformations. Yet, surprisingly, such coordinates have thus far typically considered only local surface positional or derivative information. In the present article, we propose to equip spectral coordinates with medial (object width) information, so as to enrich them. The key idea is to couple surface points that share a medial ball, via the weights of the adjacency matrix. We develop a spectral feature using this idea, and the algorithms to compute it. The incorporation of object width and medial coupling has direct benefits, as illustrated by our experiments on object classification, object part segmentation, and surface point correspondence.
2021-11-26
ArXiv (preprint)
doi.org
arxiv.org
Medical Imaging with Deep Learning: MIDL 2020 - Short Paper Track
Tal Arbel
Ismail Ben Ayed
Marleen de Bruijne
Maxime Descoteaux
Hervé Lombaert
Chris Pal
This compendium gathers all the accepted extended abstracts from the Third International Conference on Medical Imaging with Deep Learning (M… (see more)IDL 2020), held in Montreal, Canada, 6-9 July 2020. Note that only accepted extended abstracts are listed here, the Proceedings of the MIDL 2020 Full Paper Track are published in the Proceedings of Machine Learning Research (PMLR).
2020-06-29
ArXiv (preprint)
arxiv.org
arxiv.org