Search

International audience; Semi-supervised learning (SSL) uses unlabeled data to compensate for the scarcity of annotated images and the lack of method generalization to unseen domains, two usual problems in medical segmentation tasks. In this work, we propose POPCORN, a novel method combining consistency regularization and pseudo-labeling designed for image segmentation. The proposed framework uses high-level regularization to constrain our segmentation model to use similar latent features for images with similar segmentations. POPCORN estimates a proximity graph to select data from easiest ones to more difficult ones, in order to ensure accurate pseudo-labeling and to limit confirmation bias. Applied to multiple sclerosis lesion segmentation, our method demonstrates competitive results compared to other state-of-the-art SSL strategies.

[EN] The prediction of subjects with mild cognitive impairment (MCI) who will progress to Alzheimer¿s disease (AD) is clinically relevant, and may above all have a significant impact on accelerating the development of new treatments. In this paper, we present a new MRI-based biomarker that enables us to accurately predict conversion of MCI subjects to AD. In order to better capture the AD signature, we introduce two main contributions. First, we present a new graph-based grading framework to combine inter-subject similarity features and intra-subject variability features. This framework involves patch-based grading of anatomical structures and graph-based modeling of structure alteration relationships. Second, we propose an innovative multiscale brain analysis to capture alterations caused by AD at different anatomical levels. Based on a cascade of classifiers, this multiscale approach enables the analysis of alterations of whole brain structures and hippocampus subfields at the same time. During our experiments using the ADNI-1 dataset, the proposed multiscale graph-based grading method obtained an area under the curve (AUC) of 81% to predict conversion of MCI subjects to AD within three years. Moreover, when combined with cognitive scores, the proposed method obtained 85% of AUC. These results are competitive in comparison to state-of-the-art methods evaluated on the same dataset., This work benefited from the support of the project DeepvolBrain of the French National Research Agency (ANR-18-CE450013). This study was achieved within the context of the Laboratory of Excellence TRAIL ANR-10-LABX-57 for the BigDataBrain project. Moreover, we thank the Investments for the future Program IdEx Bordeaux (ANR-10-IDEX-03-02, HL-MRI Project), Cluster of excellence CPU and the CNRS. Finally, this work was also supported by the NIH grants R01-NS094456 and U01-NS106845. Data collection and sharing for this project was funded by the Alzheimer's Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01-AG024904) and by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through generous contributions from the following: AbbVie, Alzheimer's Biogen; Bristol-Myes Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffman-La Roche Ltd and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Pharmaceutical Research & Development LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical providing funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health (www.fnih.org).The grantee organization is the Northern California Institute of Research and Education, and the study is coordinated by the Alzheimer's Therapeutic Research Institute at the University of Southern California. ADNI data are disseminated by the Laboratory for Neuro Imaging at the University of Southern California.

Recently, segmentation methods based on Convolutional Neural Networks (CNNs) showed promising performance in automatic Multiple Sclerosis (MS) lesions segmentation. These techniques have even outperformed human experts in controlled evaluation conditions such as Longitudinal MS Lesion Segmentation Challenge (ISBI Challenge). However state-of-the-art approaches trained to perform well on highly-controlled datasets fail to generalize on clinical data from unseen datasets. Instead of proposing another improvement of the segmentation accuracy, we propose a novel method robust to domain shift and performing well on unseen datasets, called DeepLesionBrain (DLB). This generalization property results from three main contributions. First, DLB is based on a large group of compact 3D CNNs. This spatially distributed strategy ensures a robust prediction despite the risk of generalization failure of some individual networks. Second, DLB includes a new image quality data augmentation to reduce dependency to training data specificity (e.g., acquisition protocol). Finally, to learn a more generalizable representation of MS lesions, we propose a hierarchical specialization learning (HSL). HSL is performed by pre-training a generic network over the whole brain, before using its weights as initialization to locally specialized networks. By this end, DLB learns both generic features extracted at global image level and specific features extracted at local image level. DLB generalization was validated in cross-dataset experiments on MSSEG'16, ISBI challenge, and in-house datasets. During experiments, DLB showed higher segmentation accuracy, better segmentation consistency and greater generalization performance compared to state-of-the-art methods. Therefore, DLB offers a robust framework well-suited for clinical practice.

International audience

[EN] Whole brain segmentation of fine-grained structures using deep learning (DL) is a very challenging task since the number of anatomical labels is very high compared to the number of available training images. To address this problem, previous DL methods proposed to use a single convolution neural network (CNN) or few independent CNNs. In this paper, we present a novel ensemble method based on a large number of CNNs processing different overlapping brain areas. Inspired by parliamentary decision-making systems, we propose a framework called AssemblyNet, made of two "assemblies" of U-Nets. Such a parliamentary system is capable of dealing with complex decisions, unseen problem and reaching a relevant consensus. AssemblyNet introduces sharing of knowledge among neighboring U-Nets, an "amendment" procedure made by the second assembly at higher-resolution to refine the decision taken by the first one, and a final decision obtained by majority voting. During our validation, AssemblyNet showed competitive performance compared to state-of-the-art methods such as U-Net, Joint label fusion and SLANT. Moreover, we investigated the scan-rescan consistency and the robustness to disease effects of our method. These experiences demonstrated the reliability of AssemblyNet. Finally, we showed the interest of using semi-supervised learning to improve the performance of our method., This work benefited from the support of the project DeepvolBrain of the French National Research Agency (ANR-18-CE45-0013). This study was achieved within the context of the Laboratory of Excellence TRAIL ANR-10-LABX-57 for the BigDataBrain project. Moreover, we thank the Investments for the future Program IdEx Bordeaux (ANR-10-IDEX-0 3-02, HL-MRI Project), Cluster of excellence CPU and the CNRS/INSERM for the DeepMultiBrain project. This study has been also supported by the DPI2017-87743-R grant from the Spanish Ministerio de Economia, Industria Competitividad. The C-MIND data used in the preparation of this article were obtained from the C-MIND Data Repository (accessed in Feb 2015) created by the C-MIND study of Normal Brain Development. This is a multisite, longitudinal study of typically developing children from ages newborn through young adulthood conducted by Cincinnati Children's Hospital Medical Center and UCLA and supported by the National Institute of Child Health and Human Development (Contract #s HHSN275200900018C). The NDAR data used in the preparation of this manuscript were obtained from the NIH-supported National Database for Autism Research (NDAR). This is a multisite, longitudinal study of typically developing children from ages newborn through young adulthood conducted by the Brain Development Cooperative Group and supported by the National Institute of Child Health and Human Development, the National Institute on Drug Abuse, the National Institute of Mental Health, and the National Institute of Neurological Disorders and Stroke (Contract #s N01- HD02-3343, N01-MH9-0002, and N01-NS-9-2314, -2315, -2316, -2317, -2319 and -2320). A listing of the participating sites and a complete listing of the study investigators can be found at http://pediatricmri.nih.gov/nihpd/info/participating_centers.html. The ADNI data used in the preparation of this manuscript were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904). ADNI data are disseminated by the Laboratory for NeuroImaging at the University of California, Los Angeles. This research was also supported by NIH grants P30AG010129, K01 AG030514 and the Dana Foundation. The OASIS data used in the preparation of this manuscript were obtained from the OASIS project funded by grants P50 AG05681, P01 AG03991, R01 AG021910, P50 MH071616, U24 RR021382, R01 MH56584. The AIBL data used in the preparation of this manuscript were obtained from the AIBL study of ageing funded by the Common-wealth Scientific Industrial Research Organization (CSIRO; a publicly funded government research organization), Science Industry Endowment Fund, National Health and Medical Research Council of Australia (project grant 1011689), Alzheimer's Association, Alzheimer's Drug Discovery Foundation, and an anonymous foundation. The ICBM data used in the preparation of this manuscript were supported by Human Brain Project grant PO1MHO52176-11 (ICBM, P.I. Dr John Mazziotta) and Canadian Institutes of Health Research grant MOP-34996. The IXI data used in the preparation of this manuscript were supported by the U.K. Engineering and Physical Sciences Research Council (EPSRC) GR/S21533/02. ABIDE primary support for the work by Adriana Di Martino was provided by the NIMH (K23MH087770) and the Leon Levy Foundation. Primary support for the work by Michael P. Milham and the INDI team was provided by gifts from Joseph P. Healy and the Stavros Niarchos Foundation to the Child Mind Institute, as well as by an NIMH award to MPM (R03MH096321).

Traffic control systems are imperative to the everyday function and quality of life for society. The current methods, such as; SCATS, SCOOT and InSync, provide this solution, but with limited flexibility. With the advances in context-aware technologies and wireless vehicular communication as discussed by Maglaras, and the rise of the Internet of Things allowing inexpensive networking of devices current technologies are becoming rapidly outdated. Some examples of such vehicle technologies are discussed in recent studies, namely, social internet of vehicles, and wireless sensing technologies. As the smart city landscape develops, some of these technological advances can be adapted into smart traffic control systems, improving the transport\ud efficiency throughout the road network, while reducing levels of traffic congestion, amount of air pollution, improving quality of life. Although air pollution can be somewhat mitigated with technologies like Stop-Start, Hybrid or Electric, traffic congestion still has negative effect on the quality of life for the drivers, as well as the residence in the affected areas. As it has been outlined before by Glaesar, reducing traffic congestion remains a crucial goal of these future vehicle technologies.\ud Addressing the traffic congestion problem, this chapter reviews existing technologies and future vehicle concepts that can be a good starting point for future studies of implementing a Smart Traffic Control System (STCS), starting by looking at the importance of STCSs, reviewing existing technologies in use with a focus on the most common, and identifying their shortcomings. Afterward, three potential vehicular technologies; V2X (Vehicle-to-X) communication, vehicle cloud\ud computing (VCC) and vehicle social networks (VSNs) , will be reviewed based on previous works, with their applicability in\ud STCSs based on potential efficiency, security and privacy aspects.

Superpixel decomposition methods are widely used in computer vision and image processing applications. By grouping homogeneous pixels, the accuracy can be increased and the decrease of the number of elements to process can drastically reduce the computational burden. For most superpixel methods, a trade-off is computed between 1) color homogeneity, 2) adherence to the image contours and 3) shape regularity of the decomposition. In this paper, we propose a framework that jointly enforces all these aspects and provides accurate and regular Superpixels with Contour Adherence using Linear Path (SCALP). During the decomposition, we propose to consider color features along the linear path between the pixel and the corresponding superpixel barycenter. A contour prior is also used to prevent the crossing of image boundaries when associating a pixel to a superpixel. Finally, in order to improve the decomposition accuracy and the robustness to noise, we propose to integrate the pixel neighborhood information, while preserving the same computational complexity. SCALP is extensively evaluated on standard segmentation dataset, and the obtained results outperform the ones of the state-of-the-art methods. SCALP is also extended for supervoxel decomposition on MRI images., Computer Vision and Image Understanding (CVIU), 2018

International audience; Whole brain segmentation using deep learning (DL) is a very challenging task since the number of anatomical labels is very high compared to the number of available training images. To address this problem, previous DL methods proposed to use a global convolution neural network (CNN) or few independent CNNs. In this paper, we present a novel ensemble method based on a large number of CNNs processing different overlapping brain areas. Inspired by parliamentary decision-making systems, we propose a framework called Assem-blyNet, made of two "assemblies" of U-Nets. Such a parliamentary system is capable of dealing with complex decisions and reaching a consensus quickly. AssemblyNet introduces sharing of knowledge among neighboring U-Nets, an "amendment" procedure made by the second assembly at higher-resolution to refine the decision taken by the first one, and a final decision obtained by majority voting. When using the same 45 training images, AssemblyNet outperforms global U-Net by 28% in terms of the Dice metric, patch-based joint label fusion by 15% and SLANT-27 by 10%. Finally, AssemblyNet demonstrates high capacity to deal with limited training data to achieve whole brain segmentation in practical training and testing times.

Applying vehicular (V2X) communications in detecting traffic congestion is a promising approach, as smart and self-driving vehicles are equipped with sensors that can be used to detect an incident anywhere in real-time. Unfortunately, without appropriate security measures and careful design the communication can be vulnerable to malicious attacks, causing even more damage on the roads. Addressing these problems, we propose a high-level system architecture and a security protocol specifically designed for congestion detection based on vehicle-to-infrastructure (V2I) type communication. The security properties of our proposed approach are formally verified using the ProVerif tool, and its efficiency compared to the traditional traffic light systems is demonstrated through simulations with the Veins framework. Results show that our system is secure against a large set of attacks, and can have lower total travelling time compared to three traditional traffic light approaches based on induction loop, lane area detector/camera (installed near the junctions), and static lights.

[EN] Alzheimer's disease is a neurodegenerative process leading to irreversible mental dysfunctions. To date, diagnosis is established after incurable brain structure alterations. The development of new biomarkers is crucial to perform an early detection of this disease. With the recent improvement of magnetic resonance imaging, numerous methods were proposed to improve computer-aided detection. Among these methods, patch-based grading framework demonstrated state-of-the-art performance. Usually, methods based on this framework use intensity or grey matter maps. However, it has been shown that texture filters improve classification performance in many cases. The aim of this work is to improve performance of patch-based grading framework with the development of a novel texture-based grading method. In this paper, we study the potential of multi-directional texture maps extracted with 3D Gabor filters to improve patch-based grading method. We also proposed a novel patch-based fusion scheme to efficiently combine multiple grading maps. To validate our approach, we study the optimal set of filters and compare the proposed method with different fusion schemes. In addition, we also compare our new texture-based grading biomarker with state-of-the-art methods. Experiments show an improvement of AD detection and prediction accuracy. Moreover, our method obtains competitive performance with 91.3% of accuracy and 94.6% of area under a curve for AD detection. (C) 2018 Elsevier Ltd. All rights reserved., This study has been carried out with financial support from the French State, managed by the French National Research Agency (ANR) in the frame of the Investments for the future Program IdEx Bordeaux (HL-MRI ANR-10-IDEX-03-02), Cluster of excellence CPU and TRAIL (BigDataBrain ANR-10-LABX-57).

In this paper, we address the security properties of automated road congestion detection systems. SCATS, SCOOT and InSync are three examples of Adaptive Traffic Control Systems (ATCSs) widely deployed today. ATCSs minimize the unused green time and reduce traffic congestion in urban areas using different methods such as induction loops and camcorders installed at intersections. The main drawback of these system is that they cannot capture incidents outside the range of these camcorders or induction loops. To overcome this hurdle, theoretical concepts for automated road congestion alarm systems including the system architecture, communication protocol, and algorithms are proposed. These concepts incorporate secure wireless vehicle-to-infrastructure (V2I) communications. The security properties of this new system are presented and then analyzed using the ProVerif protocol verification tool.

National audience; Les superpixels sont devenus très populaires dans de nombreuses applications de vision par ordinateur. Néanmoins, ils restent sous-exploités du fait de l'irrégularité des décompositions qui diffèrent selon les images. Dans ce travail, nous introduisons d'abord une nouvelle structure, un patch de superpixels, appelée SuperPatch. La structure proposée, basée sur le voisinage du superpixel, définit un descripteur robuste incluant les relations spatiales entre superpixels voisins. La généralisation de la méthode de recherche de correspondance PatchMatch aux SuperPatchs, nommée SuperPatchMatch, est alors introduite. Enfin, nous proposons une adaptation de la méthodè a l'étiquetage automatique depuis une bibliothèque d'images d'exemples. Nous démontrons alors le potentiel de notre approche en obtenant des résultats supérieurs à ceux d'approches basées apprentissages, sur des expériences d'étiquetage de visages.

Alzheimer’s disease is the most common dementia leading to an irreversible neurodegenerative process. To date, subject revealed advanced brain structural alterations when the diagnosis is established. Therefore, an earlier diagnosis of this dementia is crucial although it is a challenging task. Recently, many studies have proposed biomarkers to perform early detection of Alzheimer’s disease. Some of them have proposed methods based on inter-subject similarity while other approaches have investigated framework using intra-subject variability. In this work, we propose a novel framework combining both approaches within an efficient graph of brain structures grading. Subsequently, we demonstrate the competitive performance of the proposed method compared to state-of-the-art methods.

Numerous methods have been proposed to capture early hippocampus alterations caused by Alzheimer’s disease. Among them, patch-based grading approach showed its capability to capture subtle structural alterations. This framework applied on hippocampus obtains state-of-the-art results for AD detection but is limited for its prediction compared to the same approaches based on whole-brain analysis. We assume that this limitation could come from the fact that hippocampus is a complex structure divided into different subfields. Indeed, it has been shown that AD does not equally impact hippocampal subfields. In this work, we propose a graph-based representation of the hippocampal subfields alterations based on patch-based grading feature. The strength of this approach comes from better modeling of the inter-related alterations through the different hippocampal subfields. Thus, we show that our novel method obtains similar results than state-of-the-art approaches based on whole-brain analysis with improving by 4 percent points of accuracy patch-based grading methods based on hippocampus.

IEEE International Conference on Image Processing (ICIP) 2017; International audience; In this work, we propose a fast superpixel-based color transfer method (SCT) between two images. Superpixels enable to decrease the image dimension and to extract a reduced set of color candidates. We propose to use a fast approximate nearest neighbor matching algorithm in which we enforce the match diversity by limiting the selection of the same superpixels. A fusion framework is designed to transfer the matched colors, and we demonstrate the improvement obtained over exact matching results. Finally, we show that SCT is visually competitive compared to state-of-the-art methods.

International audience; In this paper, we address the problem of recovering a color image from a grayscale one. The input color data comes from a source image considered as a reference image. Reconstructing the missing color of a grayscale pixel is here viewed as the problem of automatically selecting the best color among a set of colors candidates while simultaneously ensuring the local spatial coherency of the reconstructed color information. To solve this problem, we propose a variational approach where a specific energy is designed to model the color selection and the spatial constraint problems simultaneously. The contributions of this paper are twofold: first, we introduce a variational formulation modeling the color selection problem under spatial constraints and propose a minimization scheme which allows computing a local minima of the defined non-convex energy. Second, we combine different patch-based features and distances in order to construct a consistent set of possible color candidates. This set is used as input data and our energy minimization allows to automatically select the best color to transfer for each pixel of the grayscale image. Finally, experiments illustrate the potentiality of our simple methodology and show that our results are very competitive with respect to the state-of-the-art methods.

In the superpixel literature, the comparison of state-of-the-art methods can be biased by the non-robustness of some metrics to decomposition aspects, such as the superpixel scale. Moreover, most recent decomposition methods allow to set a shape regularity parameter, which can have a substantial impact on the measured performances. In this paper, we introduce an evaluation framework, that aims to unify the comparison process of superpixel methods. We investigate the limitations of existing metrics, and propose to evaluate each of the three core decomposition aspects: color homogeneity, respect of image objects and shape regularity. To measure the regularity aspect, we propose a new global regularity measure (GR), which addresses the non-robustness of state-of-the-art metrics. We evaluate recent superpixel methods with these criteria, at several superpixel scales and regularity levels. The proposed framework reduces the bias in the comparison process of state-of-the-art superpixel methods. Finally, we demonstrate that the proposed GR measure is correlated with the performances of various applications., Journal of Electronic Imaging (JEI), 2017 Special issue on Superpixels for Image Processing and Computer Vision

Superpixels have become very popular in many computer vision applications. Nevertheless, they remain underexploited since the superpixel decomposition may produce irregular and non stable segmentation results due to the dependency to the image content. In this paper, we first introduce a novel structure, a superpixel-based patch, called SuperPatch. The proposed structure, based on superpixel neighborhood, leads to a robust descriptor since spatial information is naturally included. The generalization of the PatchMatch method to SuperPatches, named SuperPatchMatch, is introduced. Finally, we propose a framework to perform fast segmentation and labeling from an image database, and demonstrate the potential of our approach since we outperform, in terms of computational cost and accuracy, the results of state-of-the-art methods on both face labeling and medical image segmentation., Comment: IEEE Transactions on Image Processing (TIP), 2017 Selected for presentation at IEEE International Conference on Image Processing (ICIP) 2017

International audience; This paper deals with the difficult problem of video colorization. Methods in the literature are generally based on spatio-temporal video blocks, or on frame to frame color propagation methods, each technique having its own advantages and drawbacks. In this paper , we present both a novel automatic frame-to-frame propagation approach and an interactive correction method within a variational framework. The proposed method propagates colors from an initial colorized frame to the whole grayscale video sequence. The automatic propagation results may be visually unsuitable in some cases. To overcome this limitation, a spatio-temporal functional with a user-guided correction is introduced. Two primal-dual algorithms are designed to solve the proposed variational models. Numerical results show the efficiency and the potentiality of the proposed approach in comparison with state-of-the-art methods.