Hervé Delingette

Hervé Delingette
National Institute for Research in Computer Science and Control | INRIA

About

433
Publications
45,592
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
15,173
Citations
Citations since 2016
83 Research Items
5097 Citations
20162017201820192020202120220200400600800
20162017201820192020202120220200400600800
20162017201820192020202120220200400600800
20162017201820192020202120220200400600800

Publications

Publications (433)
Preprint
Full-text available
Image registration is an essential but challenging task in medical image computing, especially for echocardiography, where the anatomical structures are relatively noisy compared to other imaging modalities. Traditional (non-learning) registration approaches rely on the iterative optimization of a similarity metric which is usually costly in time c...
Article
Full-text available
The robust delineation of the cochlea and its inner structures combined with the detection of the electrode of a cochlear implant within these structures is essential for envisaging a safer, more individualized, routine image-guided cochlear implant therapy. We present Nautilus—a web-based research platform for automated pre- and post-implantation...
Chapter
The extraction of consensus segmentations from several binary or probabilistic masks is important to solve various tasks such as the analysis of inter-rater variability or the fusion of several neural network outputs. One of the most widely used method to obtain such a consensus segmentation is the STAPLE algorithm. In this paper, we first demonstr...
Article
Purpose: To train and assess the performance of a deep learning-based network designed to detect, localize, and characterize focal liver lesions (FLLs) in the liver parenchyma on abdominal US images. Materials and methods: In this retrospective, multicenter, institutional review board-approved study, two object detectors, Faster region-based con...
Article
The fusion of probability maps is required when trying to analyse a collection of image labels or probability maps produced by several segmentation algorithms or human raters. The challenge is to weight the combination of maps correctly, in order to reflect the agreement among raters, the presence of outliers and the spatial uncertainty in the cons...
Article
Full-text available
Better models to identify individuals at low risk of ventricular arrhythmia (VA) are needed for implantable cardioverter-defibrillator (ICD) candidates to mitigate the risk of ICD-related complications. We designed the CERTAINTY study (CinE caRdiac magneTic resonAnce to predIct veNTricular arrhYthmia) with deep learning for VA risk prediction from...
Article
Incorporating shape information is essential for the delineation of many organs and anatomical structures in medical images. While previous work has mainly focused on parametric spatial transformations applied to reference template shapes, in this paper, we address the Bayesian inference of parametric shape models for segmenting medical images with...
Conference Paper
Landmark detection in medical images is important for many clinical applications. Learning-based landmark detection is successful at solving some problems but it usually requires a large number of the annotated datasets for the training stage. In addition, traditional methods usually fail for the landmark detection of fine objects. In this paper, w...
Article
Metal Artifacts creates often difficulties for a high quality visual assessment of post-operative imaging in computed tomography (CT). A vast body of methods have been proposed to tackle this issue, but these methods were designed for regular CT scans and their performance is usually insufficient when imaging tiny implants. In the context of post-o...
Preprint
Image registration as an important basis in signal processing task often encounter the problem of stability and efficiency. Non-learning registration approaches rely on the optimization of the similarity metrics between the fix and moving images. Yet, those approaches are usually costly in both time and space complexity. The problem can be worse wh...
Article
Research into artificial intelligence (AI) has made tremendous progress over the past decade. In particular, the AI-powered analysis of images and signals has reached human-level performance in many applications owing to the efficiency of modern machine learning methods, in particular deep learning using convolutional neural networks. Research into...
Article
We propose to learn a probabilistic motion model from a sequence of images for spatio-temporal registration. Our model encodes motion in a low-dimensional probabilistic space – the motion matrix – which enables various motion analysis tasks such as simulation and interpolation of realistic motion patterns allowing for faster data acquisition and da...
Article
Full-text available
We perform unsupervised analysis of image-derived shape and motion features extracted from 3,822 cardiac Magnetic resonance imaging (MRIs) of the UK Biobank. First, with a feature extraction method previously published based on deep learning models, we extract from each case 9 feature values characterizing both the cardiac shape and motion. Second,...
Preprint
We propose to learn a probabilistic motion model from a sequence of images for spatio-temporal registration. Our model encodes motion in a low-dimensional probabilistic space - the motion matrix - which enables various motion analysis tasks such as simulation and interpolation of realistic motion patterns allowing for faster data acquisition and da...
Patent
Systems and methods for performing a medical imaging analysis task using a machine learning based motion model are provided. One or more medical images of an anatomical structure are received. One or more feature vectors are determined. The one or more feature vectors are mapped to one or more motion vectors using the machine learning based motion...
Preprint
Variational autoencoder (VAE) as one of the well investigated generative model is very popular in nowadays neural learning research works. To leverage VAE in practical tasks which have high dimensions and huge dataset often face the problem of low variance evidence lower bounds construction. Markov chain Monte Carlo (MCMC) is an effective approach...
Conference Paper
Full-text available
Signed distance map (SDM) is a common representation of surfaces in medical image analysis and machine learning. The computational complexity of SDM for 3D parametric shapes is often a bottleneck in many applications, thus limiting their interest. In this paper, we propose a learning based SDM generation neural network which is demonstrated on a tr...
Preprint
Signed distance map (SDM) is a common representation of surfaces in medical image analysis and machine learning. The computational complexity of SDM for 3D parametric shapes is often a bottleneck in many applications, thus limiting their interest. In this paper, we propose a learning based SDM generation neural network which is demonstrated on a tr...
Article
Full-text available
Planning of radiotherapy involves accurate segmentation of a large number of organs at risk (OAR), i.e., organs for which irradiation doses should be minimized to avoid important side effects of the therapy. We propose a deep learning method for segmentation of OAR inside the head, from magnetic resonance images (MRIs). Our system performs segmenta...
Article
Full-text available
In this paper, we propose to use new 3D-printed meso-structured materials to build soft robots and we present a modeling pipeline for design assistance and control. These meta-materials can be programmed before printing to target specific mechanical properties, in particular heterogeneous stiffness and anisotropic behaviour. Without changing the ex...
Chapter
We propose to learn a probabilistic motion model from a sequence of images. Besides spatio-temporal registration, our method offers to predict motion from a limited number of frames, useful for temporal super-resolution. The model is based on a probabilistic latent space and a novel temporal dropout training scheme. This enables simulation and inte...
Chapter
This paper presents a method for frame-based finite element models in order to develop fast personalised cardiac electromechanical models. Its originality comes from the choice of the deformation model: it relies on a reduced number of degrees of freedom represented by affine transformations located at arbitrary control nodes over a tetrahedral mes...
Article
Full-text available
The presented data set consists of images, labels and surface models of 23 human bony labyrinths. For each specimen clinical computed tomography (CT) and co-registered high-resolution micro-CT images were acquired. Using the images, the bony labyrinth was segmented and 3D surface models were generated. Each specimen is accompanied by a description...
Chapter
The cochlea, the auditory part of the inner ear, is a spiral-shaped organ with large morphological variability. An individualized assessment of its shape is essential for clinical applications related to tonotopy and cochlear implantation. To unambiguously reference morphological parameters, reliable recognition of the cochlear modiolar axis in com...
Chapter
To assess the quality of insertion of Cochlear Implants (CI) after surgery, it is important to analyze the positions of the electrodes with respect to the cochlea based on post-operative CT imaging. Yet, these images suffer from metal artifacts which often entail a difficulty to make any analysis. In this work, we propose a 3D metal artifact reduct...
Article
Full-text available
Most of the current state-of-the-art methods for tumor segmentation are based on machine learning models trained on manually segmented images. This type of training data is particularly costly, as manual delineation of tumors is not only time-consuming but also requires medical expertise. On the other hand, images with a provided global label (indi...
Article
We propose a method to classify cardiac pathology based on a novel approach to extract image derived features to characterize the shape and motion of the heart. An original semi-supervised learning procedure, which makes efficient use of a large amount of non-segmented images and a small amount of images segmented manually by experts, is developed...
Preprint
We propose to learn a probabilistic motion model from a sequence of images. Besides spatio-temporal registration, our method offers to predict motion from a limited number of frames, useful for temporal super-resolution. The model is based on a probabilistic latent space and a novel temporal dropout training scheme. This enables simulation and inte...
Patent
For registration of medical images with deep learning, a neural network is designed to include a diffeomorphic layer in the architecture. The network may be trained using supervised or unsupervised approaches. By enforcing the diffeomorphic characteristic in the architecture of the network, the training of the network and application of the learned...
Preprint
Planning of radiotherapy involves accurate segmentation of a large number of organs at risk, i.e. organs for which irradiation doses should be minimized to avoid important side effects of the therapy. We propose a deep learning method for segmentation of organs at risk inside the brain region, from Magnetic Resonance (MR) images. Our system perform...
Preprint
The cochlea, the auditory part of the inner ear, is a spiral-shaped organ with large morphological variability. An individualized assessment of its shape is essential for clinical applications related to tonotopy and cochlear implantation. To unambiguously reference morphological parameters, reliable recognition of the cochlear modiolar axis in com...
Preprint
In this study we propose a deformation-based framework to jointly model the influence of aging and Alzheimer's disease (AD) on the brain morphological evolution. Our approach combines a spatio-temporal description of both processes into a generative model. A reference morphology is deformed along specific trajectories to match subject specific morp...
Article
In this study we propose a deformation-based framework to jointly model the influence of aging and Alzheimer's disease (AD)on the brain morphological evolution. Our approach combines a spatio-temporal description of both processes into a generative model. A reference morphology is deformed along specific trajectories to match subject specific morph...
Preprint
We perform unsupervised analysis of image-derived shape and motion features extracted from 3822 cardiac 4D MRIs of the UK Biobank. First, with a feature extraction method previously published based on deep learning models, we extract from each case 9 feature values characterizing both the cardiac shape and motion. Second, a feature selection is per...
Article
We present an efficient deep learning approach for the challenging task of tumor segmentation in multisequence MR images. In recent years, Convolutional Neural Networks (CNN) have achieved state-of-the-art performances in a large variety of recognition tasks in medical imaging. Because of the considerable computational cost of CNNs, large volumes s...
Article
Full-text available
Objective The Multidomain Alzheimer Preventive Trial (MAPT) was designed to assess the effect of omega-3 supplementation and multidomain intervention on cognitive decline of subjects with subjective memory complaint. In term of cognitive testing, no significant effect was found. In this paper, we evaluate the effect of the interventions on the brai...
Preprint
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 similar deformations close to each other in an encoding space. It enables to compare deformations, generate normal or pathological deformations for any new image or to tr...
Preprint
Full-text available
Most of the current state-of-the-art methods for tumor segmentation are based on machine learning models trained on manually segmented images. This type of training data is particularly costly, as manual delineation of tumors is not only time-consuming but also requires medical expertise. On the other hand, images with a provided global label (indi...
Preprint
Full-text available
Radiological imaging offers effective measurement of anatomy, which is useful in disease diagnosis and assessment. Previous study has shown that the left atrial wall remodeling can provide information to predict treatment outcome in atrial fibrillation. Nevertheless, the segmentation of the left atrial structures from medical images is still very t...
Preprint
We propose a method to classify cardiac pathology based on a novel approach to extract image derived features to characterize the shape and motion of the heart. An original semi-supervised learning procedure, which makes efficient use of a large amount of non-segmented images and a small amount of images segmented manually by experts, is developed...
Article
OBJECTIVE Neurovascular coupling reflects the link between neural activity and changes in cerebral blood flow. Despite many technical advances in functional exploration of the brain, including functional MRI, there are only a few reports of direct evidence of neurovascular coupling in humans. The authors aimed to explore, for the first time in huma...
Article
Full-text available
Personalised cardiac models are a virtual representation of the patient heart, with parameter values for which the simulation fits the available clinical measurements. Models usually have a large number of parameters while the available data for a given patient is typically limited to a small set of measurements, thus the parameters cannot be estim...
Chapter
We propose a deformable registration algorithm based on unsupervised learning of a low-dimensional probabilistic parameterization of deformations. We model registration in a probabilistic and generative fashion, by applying a conditional variational autoencoder (CVAE) network. This model enables to also generate normal or pathological deformations...
Preprint
We present an efficient deep learning approach for the challenging task of tumor segmentation in multisequence MR images. In recent years, Convolutional Neural Networks (CNN) have achieved state-of-the-art performances in a large variety of recognition tasks in medical imaging. Because of the considerable computational cost of CNNs, large volumes s...
Article
Full-text available
Goal: Non-invasive cardiac electrophysiology (EP) model personalisation has raised interest for instance in the scope of predicting EP cardiac resynchronization therapy (CRT) response. However, the restricted clinical applicability of current methods is due in particular to the limitation to simple situations and the important computational cost....
Article
Studying organ motion or pathology progression is an important task in diagnosis and therapy of various diseases. Typically, this task is approached by deformable registration of successive images followed by the analysis of the resulting deformation field(s). Most registration methods require prior knowledge in the form of regularization of the im...
Article
Full-text available
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 (around the apex). At each iteration, a novel variant of U-net is applied to propagate the segmentation of a slice to the adjacent slice below it. In other words, the predicti...
Article
Full-text available
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 can be directly used for mesh generation. Two specific neural networks with multi-scale coarse-to-fine prediction structure are proposed to cope with the small training d...
Article
Full-text available
Personalised computational models of the heart are of increasing interest for clinical applications due to their discriminative and predictive abilities. However, the simulation of a single heartbeat with a 3D cardiac electromechanical model can be long and computationally expensive, which makes some practical applications, such as the estimation o...
Chapter
Understanding and modeling the liver biomechanics represent a significant challenge because of the organ's complex nature.While many studies have been performed to fit hyperelastic constitutive laws on rheological experiments, they tend to agree about the importance of strain rate in the liver mechanical behavior. Furthermore, because the liver is...
Conference Paper
Robust image registration in medical imaging is essential for comparison or fusion of images, acquired from various perspectives, modalities or at different times. Typically, an objective function needs to be minimized assuming specific a priori deformation models and predefined or learned similarity measures. However, these approaches have difficu...
Conference Paper
Full-text available
Personalised 3D modelling of the heart is of increasing interest in order to better characterise pathologies and predict evolution. The personalisation consists in estimating the parameter values of an electromechanical model in order to reproduce the observed cardiac motion. However, the number of parameters in these models can be high and their e...
Article
Collecting large databases of annotated medical images is crucial for the validation and testing of feature extraction, statistical analysis and machine learning algorithms. Recent advances in cardiac electromechanical modeling and image synthesis provided a framework to generate synthetic images based on realistic mesh simulations. Nonetheless, th...
Conference Paper
In the scope of modelling cardiac electrophysiology (EP) for understanding pathologies and predicting the response to therapies, patient-specific model parameters need to be estimated. Although personalisation from non-invasive data (body surface potential mapping, BSPM) has been investigated on simple cases mostly with a single pacing site, there...
Conference Paper
Computer models of the heart are of increasing interest for clinical applications due to their discriminative and predictive abilities. However the number of simulation parameters in these models can be high and expert knowledge is required to properly design studies involving these models, and analyse the results. In particular it is important to...
Article
The aim of this study is to define an automated and reproducible framework for cochlear anatomical analysis from high-resolution segmented images and to provide a comprehensive and objective shape variability study suitable for cochlear implant design and surgery planning. For the scala tympani (ST), the scala vestibuli (SV) and the whole cochlea,...
Conference Paper
Estimating regional deformation of the myocardium from Cine MRI has the potential to locate abnormal tissue. Regional deformation of the left ventricle is commonly estimated using either segmentation or 3D + t registration. Segmentation is often performed at each instant separately from the others. It can be tedious and does not guarantee temporal...
Conference Paper
Modelling the cardiac electrophysiology (EP) can help understand pathologies and predict the response to therapies such as cardiac resynchronization. To this end, estimating patient-specific model parameters is crucial. In the case of patients with bundle branch blocks (BBB), part of the Purkinje system is often affected. The aim of this work is to...
Article
Purpose: We aim at developing a framework for the validation of a subject-specific multi-physics model of liver tumor radiofrequency ablation (RFA). Methods: The RFA computation becomes subject specific after several levels of personalization: geometrical and biophysical (hemodynamics, heat transfer and an extended cellular necrosis model). We p...
Article
Modelling cardiac electrophysiology (EP) can help understand pathologies and predict the response to therapies. Moreover, estimating patient-specific parameters of the EP model is crucial to obtain personalised information. The novelty of this paper is to use non-invasive data (body surface potential mapping, BSPM) in order to personalise the main...
Article
In this article, we propose a proof of concept for the automatic planning of personalized radiotherapy for brain tumors. A computational model of glioblastoma growth is combined with an exponential cell survival model to describe the effect of radiotherapy. The model is personalized to the magnetic resonance images (MRIs) of a given patient. It tak...
Article
We investigate uncertainty quantification under a sparse Bayesian model of medical image registration. Bayesian modelling has proven powerful to automate the tuning of registration hyperparameters, such as the trade-off between the data and regularization functionals. Sparsity-inducing priors have recently been used to render the parametrization it...
Conference Paper
Cochlear implants (CI) are used to treat severe hearing loss by surgically inserting an electrode array into the cochlea. Since current electrodes are designed with various insertion depth, ENT surgeons must choose the implant that will maximise the insertion depth without causing any trauma based on preoperative CT images. In this paper, we propos...