Portrait de Hervé Lombaert

Hervé Lombaert

Membre académique associé
herve.lombaert@mila.quebec
Professeur agrégé, Polytechnique Montréal, Département de génie informatique
Sujets de recherche
Apprentissage automatique médical
Apprentissage sur graphes
Vision par ordinateur
Google Scholar

Biographie

Hervé Lombaert est professeur agrégé à Montréal, où il est titulaire d'une Chaire de recherche du Canada sur l’analyse de formes en imagerie médicale. Ses recherches portent sur les statistiques et l'analyse des formes dans le contexte de l'apprentissage automatique et de l'imagerie médicale. Ses travaux sur l'analyse de graphes ont eu une influence sur plusieurs applications en imagerie médicale, depuis les premières segmentations d'images par graph cuts jusqu'aux récentes analyses de surface par théorie de graphes spectraux. Hervé Lombaert est l'auteur de plus de 70 articles. Il détient 5 brevets et a remporté plusieurs prix, dont le prix Erbsmann de l’Information Processing in Medical Imaging (IPMI). Ses étudiant·e·s ont également reçu des prix de la meilleure thèse pour des publications marquantes en imagerie médicale. Il est éditeur associé de Medical Image Analysis. Il a aussi eu la chance de travailler dans plusieurs centres, dont Inria Sophia-Antipolis (France), Microsoft Research (Cambridge, Royaume-Uni), Siemens Corporate Research (Princeton, NJ, É-U), l’Université McGill et Polytechnique Montréal.

Étudiants actuels

Publications

Variational Visible Layers: A Practical Framework for Uncertainty Estimation
Zeinab Abboud
Hervé Lombaert
Samuel Kadoury
2025-09-19
Lecture Notes in Computer Science (publié)
doi.org
Spectral State Space Model for Rotation-Invariant Visual Representation Learning
Sahar Dastani
Ali Bahri
Moslem Yazdanpanah
Mehrdad Noori
David Osowiechi
Gustavo Adolfo Vargas Hakim
Farzad Beizaee
Milad Cheraghalikhani
Arnab Kumar Mondal
Hervé Lombaert
Christian Desrosiers
State Space Models (SSMs) have recently emerged as an alternative to Vision Transformers (ViTs) due to their unique ability of modeling glob… (voir plus)al relationships with linear complexity. SSMs are specifically designed to capture spatially proximate relationships of image patches. However, they fail to identify relationships between conceptually related yet not adjacent patches. This limitation arises from the non-causal nature of image data, which lacks inherent directional relationships. Additionally, current vision-based SSMs are highly sensitive to transformations such as rotation. Their predefined scanning directions depend on the original image orientation, which can cause the model to produce inconsistent patch-processing sequences after rotation. To address these limitations, we introduce Spectral VMamba, a novel approach that effectively captures the global structure within an image by leveraging spectral information derived from the graph Laplacian of image patches. Through spectral decomposition, our approach encodes patch relationships independently of image orientation, achieving rotation invariance with the aid of our Rotational Feature Normalizer (RFN) module. Our experiments on classification tasks show that Spectral VMamba outperforms the leading SSM models in vision, such as VMamba, while maintaining invariance to rotations and a providing a similar runtime efficiency.
2025-06-12
IEEE/CVF Conference on Computer Vision and Pattern Recognition (Accept)
doi.org
arxiv.org
ToothForge: Automatic Dental Shape Generation using Synchronized Spectral Embeddings
Tibor Kubik
Franccois Guibault
Michal vSpanvel
Hervé Lombaert
We introduce ToothForge, a spectral approach for automatically generating novel 3D teeth, effectively addressing the sparsity of dental shap… (voir plus)e datasets. By operating in the spectral domain, our method enables compact machine learning modeling, allowing the generation of high-resolution tooth meshes in milliseconds. However, generating shape spectra comes with the instability of the decomposed harmonics. To address this, we propose modeling the latent manifold on synchronized frequential embeddings. Spectra of all data samples are aligned to a common basis prior to the training procedure, effectively eliminating biases introduced by the decomposition instability. Furthermore, synchronized modeling removes the limiting factor imposed by previous methods, which require all shapes to share a common fixed connectivity. Using a private dataset of real dental crowns, we observe a greater reconstruction quality of the synthetized shapes, exceeding those of models trained on unaligned embeddings. We also explore additional applications of spectral analysis in digital dentistry, such as shape compression and interpolation. ToothForge facilitates a range of approaches at the intersection of spectral analysis and machine learning, with fewer restrictions on mesh structure. This makes it applicable for shape analysis not only in dentistry, but also in broader medical applications, where guaranteeing consistent connectivity across shapes from various clinics is unrealistic. The code is available at https://github.com/tiborkubik/toothForge.
2025-06-02
ArXiv (prépublication)
doi.org
arxiv.org
GeoLS: an Intensity-based, Geodesic Soft Labeling for Image Segmentation
Sukesh Adiga Vasudeva
Jose Dolz
Hervé Lombaert
Soft-label assignments have emerged as prominent strategies in training dense prediction problems, such as image segmentation. These approac… (voir plus)hes mitigate the limitations of hard labels, such as inter-class relationships in the data and spatial relationships between a given pixel and its neighbors. Nevertheless, most existing methods rely only on ground-truth masks and ignore the underlying image context associated with each label. For instance, image intensities convey information that could potentially clear ambiguities in the annotation. This paper, therefore, proposes a Geodesic Label Smoothing (GeoLS) approach that incorporates image intensity information within the soft labeling process. Specifically, we leverage the geodesic distance transform to capture the intensity variations between pixels. The generated maps geodesically modify the hard labels to obtain new intensity-based soft labels. The resulting geodesic soft labels better model spatial and class-wise relationships as they capture the variations of image gradients across classes and anatomy. The benefits of our intensity-based geodesic soft labels are assessed on three diverse sets of publicly accessible segmentation datasets. Our experimental results show that the proposed method consistently improves the segmentation accuracy compared to state-of-the-art soft-labeling techniques in terms of the Dice similarity and Hausdorff distance.
2025-04-17
Machine Learning for Biomedical Imaging (publié)
doi.org
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 … (voir plus)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.
2024-10-02
Lecture Notes in Computer Science (publié)
doi.org
arxiv.org
Automating MedSAM by Learning Prompts with Weak Few-Shot Supervision
Melanie Gaillochet
Christian Desrosiers
Hervé Lombaert
2024-09-27
Lecture Notes in Computer Science (publié)
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… (voir plus) 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.
2024-01-24
ArXiv (prépublication)
doi.org
arxiv.org
Real-time simulation of viscoelastic tissue behavior with physics-guided deep learning
Mohammad Karami
Hervé Lombaert
David Rivest‐henault
2023-02-28
Computerized Medical Imaging and Graphics (publié)
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,… (voir plus) 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.
2022-06-17
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (publié)
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… (voir plus)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).
2020-06-28
arXiv (Cornell University) (prépublication)
doi.org
arxiv.org