Tesis sobre el tema "Imagerie computationnelle"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte los 22 mejores tesis para su investigación sobre el tema "Imagerie computationnelle".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Explore tesis sobre una amplia variedad de disciplinas y organice su bibliografía correctamente.
Debarnot, Valentin. "Microscopie computationnelle". Thesis, Toulouse 3, 2020. http://www.theses.fr/2020TOU30156.
Texto completoThe contributions of this thesis are numerical and theoretical tools for the resolution of blind inverse problems in imaging. We first focus in the case where the observation operator is unknown (e.g. microscopy, astronomy, photography). A very popular approach consists in estimating this operator from an image containing point sources (microbeads or fluorescent proteins in microscopy, stars in astronomy). Such an observation provides a measure of the impulse response of the degradation operator at several points in the field of view. Processing this observation requires robust tools that can rapidly use the data. We propose a toolbox that estimates a degradation operator from an image containing point sources. The estimated operator has the property that at any location in the field of view, its impulse response is expressed as a linear combination of elementary estimated functions. This makes it possible to estimate spatially invariant (convolution) and variant (product-convolution expansion) operators. An important specificity of this toolbox is its high level of automation: only a small number of easily accessible parameters allows to cover a large majority of practical cases. The size of the point source (e.g. bead), the background and the noise are also taken in consideration in the estimation. This tool, coined PSF-estimator, comes in the form of a module for the Fiji software, and is based on a parallelized implementation in C++. The operators generated by an optical system are usually changing for each experiment, which ideally requires a calibration of the system before each acquisition. To overcome this, we propose to represent an optical system not by a single operator (e.g. convolution blur with a fixed kernel for different experiments), but by subspace of operators. This set allows to represent all the possible states of a microscope. We introduce a method for estimating such a subspace from a collection of low rank operators (such as those estimated by the toolbox PSF-Estimator). We show that under reasonable assumptions, this subspace is low-dimensional and consists of low rank elements. In a second step, we apply this process in microscopy on large fields of view and with spatially varying operators. This implementation is possible thanks to the use of additional methods to process real images (e.g. background, noise, discretization of the observation).The construction of an operator subspace is only one step in the resolution of blind inverse problems. It is then necessary to identify the degradation operator in this set from a single observed image. In this thesis, we provide a mathematical framework to this operator identification problem in the case where the original image is constituted of point sources. Theoretical conditions arise from this work, allowing a better understanding of the conditions under which this problem can be solved. We illustrate how this formal study allows the resolution of a blind deblurring problem on a microscopy example.[...]
Pizzolato, Marco. "IRM computationnelle de diffusion et de perfusion en imagerie cérébrale". Thesis, Université Côte d'Azur (ComUE), 2017. http://www.theses.fr/2017AZUR4017/document.
Texto completoDiffusion and Perfusion Magnetic Resonance Imaging (dMRI & pMRI) represent two modalities that allow sensing important and different but complementary aspects of brain imaging. This thesis presents a theoretical and methodological investigation on the MRI modalities based on diffusion-weighted (DW) and dynamic susceptibility contrast (DSC) images. For both modalities, the contributions of the thesis are related to the development of new methods to improve and better exploit the quality of the obtained signals. With respect to contributions in diffusion MRI, the nature of the complex DW signal is investigated to explore a new potential contrast related to tissue microstructure. In addition, the complex signal is exploited to correct a bias induced by acquisition noise of DW images, thus improving the estimation of structural scalar metrics. With respect to contributions in perfusion MRI, the DSC signal processing is revisited in order to account for the bias due to bolus dispersion. This phenomenon prevents the correct estimation of perfusion metrics but, at the same time, can give important insights about the pathological condition of the brain tissue. The contributions of the thesis are presented within a theoretical and methodological framework, validated on both synthetical and real images
Tondo, Yoya Ariel Christopher. "Imagerie computationnelle active et passive à l’aide d’une cavité chaotique micro-ondes". Thesis, Rennes 1, 2018. http://www.theses.fr/2018REN1S130/document.
Texto completoThe broad topic of the presented Ph.D focuses on active and passive microwave computational imaging. The use of a chaotic cavity as a compressive component is studied both theoretically (mathematical model, algorithmic resolution of the inverse problem) and experimentally. The underlying idea is to replace an array of antennas with a single reverberant cavity with an array of openings on the front panel that encodes the spatial information of a scene in the temporal response of the cavity. The reverberation of electromagnetic waves inside the cavity provides the degrees of freedom necessary to reconstruct an image of the scene. Thus it is possible to create a high-resolution image of a scene in real time from a single impulse response. Applications include security or imaging through walls. In this work, the design and characterization of an open chaotic cavity is performed. Using this device, active computational imaging is demonstrated to produce images of targets of various shapes. The number of degrees of freedom is further improved by changing the boundary conditions with the addition of commercial fluorescent lamps. The interaction of the waves with these plasma elements allows new cavity configurations to be created, thus improving image resolution. Compressive imaging is next applied to the passive detection and localization of natural thermal radiation from noise sources, based on the correlation of signals received over two channels. Finally, an innovative method of interferometric target imaging is presented. It is based on the reconstruction of the impulse response between two antennas from the microwave thermal noise emitted by a network of neon lamps. This work constitutes a step towards for future imaging systems
Filipis, Luiza. "Etude optique et computationnelle de la fonction des canaux ioniques neuronaux". Thesis, Université Grenoble Alpes (ComUE), 2019. http://www.theses.fr/2019GREAY078.
Texto completoThe physiology of ion channels is a major topic of interest in modern neuroscience since the functioning of these molecules is the biophysical ground of electrical and chemical behaviour of neurons. Ion channels are diverse membrane proteins that allow the selective passage of ions across the lipid bilayer of cells. They are involved in a variety of fundamental physiological processes from electrical signal integration, action potential generation and propagation to cell growth and even apoptosis, while their dysfunction is the cause of several diseases. Ion channels have extensively studied using electrode methods, in particular the patch-clamp technique, but these approaches are limited in studying native channels during physiological activity in situ. In particular, electrodes give limited spatial information while it is recognised that the contribution of channels in all different processes is a function not only of their discrete biophysical properties but also of their distribution across the neurons surface at the different compartments. Optical techniques, in particular those involving fluorescence imaging, can overcome intrinsic limitations of electrode techniques as they allow to record electrical and ionic signals with high spatial and temporal resolution. Finally, the ability of optical techniques combined with neuronal modelling can potentially give pivotal information significantly advancing our understanding on how neurons work.The ambitious goal of my thesis was to progress in this direction by developing novel approaches to combine cutting-edge imaging techniques with modelling to extract ion currents and channel kinetics in specific neuronal regions. The body of this work was divided in three methodological pieces, each of them described in a dedicated chapter
Skitioui, Salah. "Développement de radars millimétriques innovants". Electronic Thesis or Diss., Limoges, 2024. http://www.theses.fr/2024LIMO0017.
Texto completoThis research is part of a CIFRE thesis aimed at developing technologies to simplify and reduce costs associated with a body scanners dedicated to security applications, while improving the refresh rate of reconstructed images. The fundamental objective is to devise an affordable real-time imaging system. Research efforts are focused on leveraging analog multiplexing techniques based on frequency diversity, integrated into an FMCW architecture, to overcome temporal limitations inherent in existing approaches. To this end, a prototype of a leaky reverberation cavity has been conceptualized, subjected to laboratory testing, and subsequently integrated into an industrial measurement bench. This accomplishment represents a significant advancement in the evolution of a real-time imaging system utilizing an analog multiplexing device
Duan, Liuyun. "Modélisation géométrique de scènes urbaines par imagerie satellitaire". Thesis, Université Côte d'Azur (ComUE), 2017. http://www.theses.fr/2017AZUR4025.
Texto completoAutomatic city modeling from satellite imagery is one of the biggest challenges in urban reconstruction. The ultimate goal is to produce compact and accurate 3D city models that benefit many application fields such as urban planning, telecommunications and disaster management. Compared with aerial acquisition, satellite imagery provides appealing advantages such as low acquisition cost, worldwide coverage and high collection frequency. However, satellite context also imposes a set of technical constraints as a lower pixel resolution and a wider that challenge 3D city reconstruction. In this PhD thesis, we present a set of methodological tools for generating compact, semantically-aware and geometrically accurate 3D city models from stereo pairs of satellite images. The proposed pipeline relies on two key ingredients. First, geometry and semantics are retrieved simultaneously providing robust handling of occlusion areas and low image quality. Second, it operates at the scale of geometric atomic regions which allows the shape of urban objects to be well preserved, with a gain in scalability and efficiency. Images are first decomposed into convex polygons that capture geometric details via Voronoi diagram. Semantic classes, elevations, and 3D geometric shapes are then retrieved in a joint classification and reconstruction process operating on polygons. Experimental results on various cities around the world show the robustness, scalability and efficiency of the proposed approach
Domenech, Philippe. "Une approche neuro-computationnelle de la prise de décision et de sa régulation contextuelle". Phd thesis, Université Claude Bernard - Lyon I, 2011. http://tel.archives-ouvertes.fr/tel-00847494.
Texto completoFeydy, Jean. "Analyse de données géométriques, au delà des convolutions". Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPASN017.
Texto completoGeometric data analysis, beyond convolutionsTo model interactions between points, a simple option is to rely on weighted sums known as convolutions. Over the last decade, this operation has become a building block for deep learning architectures with an impact on many applied fields. We should not forget, however, that the convolution product is far from being the be-all and end-all of computational mathematics.To let researchers explore new directions, we present robust, efficient and principled implementations of three underrated operations: 1. Generic manipulations of distance-like matrices, including kernel matrix-vector products and nearest-neighbor searches.2. Optimal transport, which generalizes sorting to spaces of dimension D > 1.3. Hamiltonian geodesic shooting, which replaces linear interpolation when no relevant algebraic structure can be defined on a metric space of features.Our PyTorch/NumPy routines fully support automatic differentiation and scale up to millions of samples in seconds. They generally outperform baseline GPU implementations with x10 to x1,000 speed-ups and keep linear instead of quadratic memory footprints. These new tools are packaged in the KeOps (kernel methods) and GeomLoss (optimal transport) libraries, with applications that range from machine learning to medical imaging. Documentation is available at: www.kernel-operations.io/keops and /geomloss
Örsvuran, Rıdvan. "Vers des modèles anisotropes et anélastiques de la Terre globale : Observables et la paramétrisation de l'inversion des formes d'ondes complètes". Thesis, Université Côte d'Azur, 2021. http://www.theses.fr/2021COAZ4015.
Texto completoSeismic waves are our primary tools to see the Earth’s interior and draw inferences on its structural, thermal and chemical properties. Seismic tomography, similar to medical tomography, is a powerful technique to obtain 3D computed tomography scan (CT scan) images of the Earth’s interior using seismic waves generated by seismic sources such as earthquakes, ambient noise or controlled explosions. It is crucial to improve the resolution of tomographic images to better understand the internal dynamics of our planet driven by the mantle convection, that directly control surface processes, such as plate tectonics. To this end, at the current resolution of seismic tomography, full physics of (an)elastic wave propagation must be taken into account.The adjoint method is an efficient full-waveform inversion (FWI) technique to take 3D seismic wave propagation into account in tomography to construct high-resolution seismic images. In this thesis, I develop and demonstrate new measurements for global-scale adjoint inversions such as the implementation of double-difference traveltime and waveform misfits. Furthermore, I investigate different parameterizations to better capture Earth’s physics in the inverse problem, such as addressing the azimuthal anisotropy and anelasticity in the Earth’s mantle.My results suggest that double-difference misfits applied to dense seismic networks speed up the convergence of FWI and help increase the resolution underneath station clusters. I further observe that double-difference measurements can also help reduce the bias in data coverage towards the cluster of stations.Earth’s lithosphere and upper mantle show significant evidence of anisotropy as a result of its composition and deformation. Starting from the recent global adjoint tomography model GLAD-M25, which is the successor of GLAD-M15 and transversely isotropic in the upper mantle, my goal is to construct an azimuthally anisotropic global model of the upper mantle. I performed 10 iterations using the multitaper traveltimes combined with double difference measurements made on paired stations of minor- and major-arc surface waves. The results after 10 iterations, in general, show the global anisotropic pattern consistent with plate motions and achieve higher resolution in areas with dense seismic coverage such as in North America and Europe.Attenuation is also another key parameter for determining the partial melt, water content and thermal variations in the mantle. In the last chapter, I investigate anelastic adjoint inversions to ultimately construct a global attenuation mantle model by the simultaneous inversion of elastic and anelastic parameters assimilating both the phase and amplitude information, which will lead to exact FWI at the global scale. I investigate the trade-off between elastic and anelastic parameters based on 2D synthetic tests to define a strategy for 3D global FWIs. I also explore the effect of different measurements for simultaneously and sequentially inverted elastic and anelastic parameters. The 2D test results suggest that the envelope misfit performs best at earlier iterations by reducing the nonlinearity of the FWI. After analyzing the effect of different radially-symmetric attenuation models on seismic waveforms by performing forward simulations in various 1D and 3D elastic/anelastic models, the results suggest the necessity of simultaneous elastic/anelastic inversions to also improve the elastic structure as attenuation cause not only amplitude anomalies but also significant physical dispersion, particularly on surface waves. I performed one global simultaneous iteration of elastic and anelastic parameters using GLAD-M25 and its 1D anelastic model QRF12 as the starting models with a dataset of 253 earthquakes. The preliminary results are promising depicting, for instance, the high and low attenuation in the West and East coasts of North America
Cuingnet, Rémi. "Contributions à l'apprentissage automatique pour l'analyse d'images cérébrales anatomiques". Phd thesis, Université Paris Sud - Paris XI, 2011. http://tel.archives-ouvertes.fr/tel-00602032.
Texto completoBabayan, Bénédicte. "Unraveling the neural circuitry of sequence-based navigation using a combined fos imaging and computational approach". Thesis, Paris 5, 2014. http://www.theses.fr/2014PA05T059/document.
Texto completoSpatial navigation is a complex function requiring the combination of external and self-motion cues to build a coherent representation of the external world and drive optimal behaviour directed towards a goal. This multimodal integration suggests that a large network of cortical and subcortical structures interacts with the hippocampus, a key structure in navigation. I have studied navigation in mice through this global approach and have focused on one particular type of navigation, which consists in remembering a sequence of turns, named sequence-based navigation or sequential egocentric strategy. This navigation specifically relies on the temporal organization of movements at spatially distinct choice points. We first showed that sequence-based navigation learning required the hippocampus and the dorsomedial striatum. Our aim was to identify the functional network underlying sequence-based navigation using Fos imaging and computational approaches. The functional networks dynamically changed across early and late learning stages. The early stage network was dominated by a highly inter-connected cortico-striatal cluster. The hippocampus was activated alongside structures known to be involved in self-motion processing (cerebellar cortices), in mental representation of space manipulations (retrosplenial, parietal, entorhinal cortices) and in goal-directed path planning (prefrontal-basal ganglia loop). The late stage was characterized by the emergence of correlated activity between the hippocampus, the cerebellum and the cortico-striatal structures. Conjointly, we explored whether path integration, model-based or model-free reinforcement learning algorithms could explain mice’s learning dynamics. Only the model-free system, as long as a retrospective memory component was added to it, was able to reproduce both the group learning dynamics and the individual variability observed in the mice. These results suggest that a unique model-free reinforcement learning algorithm was sufficient to learn sequence-based navigation and that the multiple structures this learning required adapted their functional interactions across learning
Eickenberg, Michael. "Évaluation de modèles computationnels de la vision humaine en imagerie par résonance magnétique fonctionnelle". Thesis, Paris 11, 2015. http://www.theses.fr/2015PA112206/document.
Texto completoBlood-oxygen-level dependent (BOLD) functional magnetic resonance imaging (fMRI) makes it possible to measure brain activity through blood flow to areas with metabolically active neurons. In this thesis we use these measurements to evaluate the capacity of biologically inspired models of vision coming from computer vision to represent image content in a similar way as the human brain. The main vision models used are convolutional networks.Deep neural networks have made unprecedented progress in many fields in recent years. Even strongholds of biological systems such as scene analysis and object detection have been addressed with enormous success. A body of prior work has been able to establish firm links between the first and last layers of deep convolutional nets and brain regions: The first layer and V1 essentially perform edge detection and the last layer as well as inferotemporal cortex permit a linear read-out of object category. In this work we have generalized this correspondence to all intermediate layers of a convolutional net. We found that each layer of a convnet maps to a stage of processing along the ventral stream, following the hierarchy of biological processing: Along the ventral stream we observe a stage-by-stage increase in complexity. Between edge detection and object detection, for the first time we are given a toolbox to study the intermediate processing steps.A preliminary result to this was obtained by studying the response of the visual areas to presentation of visual textures and analysing it using convolutional scattering networks.The other global aspect of this thesis is “decoding” models: In the preceding part, we predicted brain activity from the stimulus presented (this is called “encoding”). Predicting a stimulus from brain activity is the inverse inference mechanism and can be used as an omnibus test for presence of this information in brain signal. Most often generalized linear models such as linear or logistic regression or SVMs are used for this task, giving access to a coefficient vector the same size as a brain sample, which can thus be visualized as a brain map. However, interpretation of these maps is difficult, because the underlying linear system is either ill-defined and ill-conditioned or non-adequately regularized, resulting in non-informative maps. Supposing a sparse and spatially contiguous organization of coefficient maps, we build on the convex penalty consisting of the sum of total variation (TV) seminorm and L1 norm (“TV+L1”) to develop a penalty grouping an activation term with a spatial derivative. This penalty sets most coefficients to zero but permits free smooth variations in active zones, as opposed to TV+L1 which creates flat active zones. This method improves interpretability of brain maps obtained through cross-validation to determine the best hyperparameter.In the context of encoding and decoding models, we also work on improving data preprocessing in order to obtain the best performance. We study the impulse response of the BOLD signal: the hemodynamic response function. To generate activation maps, instead of using a classical linear model with fixed canonical response function, we use a bilinear model with spatially variable hemodynamic response (but fixed across events). We propose an efficient optimization algorithm and show a gain in predictive capacity for encoding and decoding models on different datasets
Gerardin, Emilie. "Morphometry of the human hippocampus from MRI and conventional MRI high field". Phd thesis, Université Paris Sud - Paris XI, 2012. http://tel.archives-ouvertes.fr/tel-00856589.
Texto completoSun, Roger. "Utilisation de méthodes radiomiques pour la prédiction des réponses à l’immunothérapie et combinaisons de radioimmunothérapie chez des patients atteints de cancers Radiomics to Assess Tumor Infiltrating CD8 T-Cells and Response to Anti-PD-1/PD-L1 Immunotherapy in Cancer Patients: An Imaging Biomarker Multi-Cohort Study Imagerie médicale computationnelle (radiomique) et potentiel en immuno-oncologie Radiomics to Predict Outcomes and Abscopal Response of Cancer Patients Treated with Immunotherapy Combined with Radiotherapy Using a Validated Signature of CD8 Cells". Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPASL023.
Texto completoWith the advent of immune checkpoint inhibitors, immunotherapy has profoundly changed the therapeutic strategy of many cancers. However, despite constant therapeutic progress and combinations of treatments such as radiotherapy and immunotherapy, the majority of patients treated do not benefit from these treatments. This explains the importance of research into innovative biomarkers of response to immunotherapyComputational medical imaging, known as radiomics, analyzes and translates medical images into quantitative data with the assumption that imaging reflects not only tissue architecture, but also cellular and molecular composition. This allows an in-depth characterization of tumors, with the advantage of being non-invasive allowing evaluation of tumor and its microenvironment, spatial heterogeneity characterization and longitudinal assessment of disease evolution.Here, we evaluated whether a radiomic approach could be used to assess tumor infiltrating lymphocytes and whether it could be associated with the response of patients treated with immunotherapy. In a second step, we evaluated the association of this radiomic signature with clinical response of patients treated with radiotherapy and immunotherapy, and we assessed whether it could be used to assess tumor spatial heterogeneity.The specific challenges raised by high-dimensional imaging data in the development of clinically applicable predictive tools are discussed in this thesis
Jurczuk, Krzysztof. "Calcul parallèle pour la modélisation d'images de résonance magnétique nucléaire". Thesis, Rennes 1, 2013. http://www.theses.fr/2013REN1S089.
Texto completoThis PhD thesis concerns computer modeling of magnetic resonance imaging (MRI). The main attention is centered on imaging of vascular structures. Such imaging is influenced not only by vascular geometries but also by blood flow which has to been taken into account in modeling. Next to the question about the quality of developed models, the challenge lies also in the demand for high performance computing. Thus, in order to manage computationally complex problems, parallel computing is in use. In the thesis three solutions are proposed. The first one concerns parallel algorithms of vascular network modeling. Algorithms for different architectures are proposed. The first algorithm is based on the message passing model and thus, it is suited for distributed memory architectures. It parallelizes the process of connecting new parts of tissue to existing vascular structures. The second algorithm is designed for shared memory machines. It also parallelizes the perfusion process, but individual processors perform calculations concerning different vascular trees. The third algorithm combines message passing and shared memory approaches providing solutions for hybrid parallel architectures. Developed algorithms are able to substantially speed up the time-demanded simulations of growth of complex vascular networks. As a result, more elaborate and precise vascular structures can be simulated in a reasonable period of time. It can also help to extend the vascular model and to test multiple sets of parameters. Secondly, a new approach in computational modeling of magnetic resonance (MR) flow imaging is proposed. The approach combines the flow computation by lattice Boltzmann method, MRI simulation by following discrete local magnetizations in time and a new magnetization transport algorithm together. Results demonstrate that such an approach is able to naturally incorporate the flow influence in MRI modeling. As a result, in the proposed model, no additional mechanism (unlike in prior works) is needed to consider flow artifacts, what implies its easy extensibility. In combination with its low computational complexity and efficient implementation, the solution is a user-friendly and manageable at different levels tool which facilitates running series of simulations with different physiological and imaging parameters. The goal of the third solution is to apply the proposed MR flow imaging model on complex vascular networks. To this aim, models of vascular networks, flow behavior and MRI are combined together. In all the model components, computations are adapted to be performed at various parallel architectures. The model potential and possibilities of simulations of flow and MRI in complex vascular structures are shown. The model aims at explaining and exploring MR image formation and appearance by the combined knowledge from many processes and systems, starting from vascular geometry, through flow patterns and ending on imaging technology
Bône, Alexandre. "Learning adapted coordinate systems for the statistical analysis of anatomical shapes. Applications to Alzheimer's disease progression modeling". Electronic Thesis or Diss., Sorbonne université, 2020. http://www.theses.fr/2020SORUS273.
Texto completoThis thesis aims to build coordinate systems for shapes i.e. finite-dimensional metric spaces where shapes are represented by vectors. The goal of building such coordinate systems is to allow and facilitate the statistical analysis of shape data sets. The end-game motivation of our work is to predict and sub-type Alzheimer’s disease, based in part on knowledge extracted from banks of brain medical images. Even if these data banks are longitudinal, their variability remains mostly due to the large and normal inter-individual variability of the brain. The variability due to the progression of pathological alterations is of much smaller amplitude. The central objective of this thesis is to develop a coordinate system adapted for the statistical analysis of longitudinal shape data sets, able to disentangle these two sources of variability. As shown in the literature, the parallel transport operator can be leveraged to achieve this desired disentanglement, for instance by defining the notion of exp-parallel curves on a manifold. Using this tool on shape spaces comes however with theoretical and computational challenges, tackled in the first part of this thesis. Finally, if shape spaces are commonly equipped with a manifold-like structure in the field of computational anatomy, the underlying classes of diffeomorphisms are however most often largely built and parameterized without taking into account the data at hand. The last major objective of this thesis is to build deformation-based coordinate systems where the parameterization of deformations is adapted to the data set of interest
Cuingnet, Rémi. "Contributions à l’apprentissage automatique pour l’analyse d’images cérébrales anatomiques". Thesis, Paris 11, 2011. http://www.theses.fr/2011PA112033/document.
Texto completoBrain image analyses have widely relied on univariate voxel-wise methods. In such analyses, brain images are first spatially registered to a common stereotaxic space, and then mass univariate statistical tests are performed in each voxel to detect significant group differences. However, the sensitivity of theses approaches is limited when the differences involve a combination of different brain structures. Recently, there has been a growing interest in support vector machines methods to overcome the limits of these analyses.This thesis focuses on machine learning methods for population analysis and patient classification in neuroimaging. We first evaluated the performances of different classification strategies for the identification of patients with Alzheimer's disease based on T1-weighted MRI of 509 subjects from the ADNI database. However, these methods do not take full advantage of the spatial distribution of the features. As a consequence, the optimal margin hyperplane is often scattered and lacks spatial coherence, making its anatomical interpretation difficult. Therefore, we introduced a framework to spatially regularize support vector machines for brain image analysis based on Laplacian regularization operators. The proposed framework was then applied to the analysis of stroke and of Alzheimer's disease. The results demonstrated that the proposed classifier generates less-noisy and consequently more interpretable feature maps with no loss of classification performance
Qin, Yingying. "Early breast anomalies detection with microwave and ultrasound modalities". Electronic Thesis or Diss., université Paris-Saclay, 2021. http://www.theses.fr/2021UPASG058.
Texto completoImaging of the breast for early detec-tion of tumors is studied by associating microwave (MW) and ultrasound (US) data. No registration is enforced since a free pending breast is tackled. A 1st approach uses prior information on tissue boundaries yielded from US reflection data. Regularization incorporates that two neighboring pixels should exhibit similar MW properties when not on a boundary while a jump allowed otherwise. This is enforced in the distorted Born iterative and the contrast source inversion methods. A 2nd approach involves deterministic edge preserving regularization via auxiliary variables indicating if a pixel is on an edge or not, edge markers being shared by MW and US parameters. Those are jointly optimized from the last parameter profiles and guide the next optimization as regularization term coefficients. Alternate minimization is to update US contrast, edge markers and MW contrast. A 3rd approach involves convolutional neural networks. Estimated contrast current and scattered field are the inputs. A multi-stream structure is employed to feed MW and US data. The network outputs the maps of MW and US parameters to perform real-time. Apart from the regression task, a multi-task learning strategy is used with a classifier that associates each pixel to a tissue type to yield a segmentation image. Weighted loss assigns a higher penalty to pixels in tumors when wrongly classified. A 4th approach involves a Bayesian formalism where the joint posterior distribution is obtained via Bayes’ rule; this true distribution is then approximated by a free-form separable law for each set of unknowns to get the estimate sought. All those solution methods are illustrated and compared from a wealth of simulated data on simple synthetic models and on 2D cross-sections of anatomically-realistic MRI-derived numerical breast phantoms in which small artificial tumors are inserted
Fadili, Jalal M. "Une exploration des problèmes inverses par les représentations parcimonieuses et l'optimisation non lisse". Habilitation à diriger des recherches, Université de Caen, 2010. http://tel.archives-ouvertes.fr/tel-01071774.
Texto completoLabatut, Vincent. "Réseaux causaux probabilistes à grande échelle : un nouveau formalisme pour la modélisation du traitement de l'information cérébrale". Phd thesis, Université Paul Sabatier - Toulouse III, 2003. http://tel.archives-ouvertes.fr/tel-00005190.
Texto completoWirsich, Jonathan. "EEG-fMRI and dMRI data fusion in healthy subjects and temporal lobe epilepsy : towards a trimodal structure-function network characterization of the human brain". Thesis, Aix-Marseille, 2016. http://www.theses.fr/2016AIXM5040.
Texto completoThe understanding human brain structure and the function patterns arising from it is a central challenge to better characterize brain network pathologies such as temporal lobe epilepsies, which could help to improve the clinical predictability of epileptic surgery outcome.Brain functioning can be accessed by both electroencephalography (EEG) or functional magnetic resonance imaging (fMRI), while brain structure can be measured with diffusion MRI (dMRI). We use these modalities to measure brain functioning during a face recognition task and in rest in order to link the different modalities in an optimal temporal and spatial manner. We discovered disruption of the network processing famous faces as well a disruption of the structure-function relation during rest in epileptic patients.This work broadened the understanding of epilepsy as a network disease that changes the brain on a large scale not limited to a local epileptic focus. In the future these results could be used to guide clinical intervention during epilepsy surgery but also they provide new approaches to evaluate pharmacological treatment on its functional implications on a whole brain scale
Hansen, Enrique carlos. "Modeling non-stationary resting-state dynamics in large-scale brain models". Thesis, Aix-Marseille, 2015. http://www.theses.fr/2015AIXM4011/document.
Texto completoThe complexity of human cognition is revealed in the spatio-temporal organization of brain dynamics. We can gain insight into this organization through the analysis of blood oxygenation-level dependent (BOLD) signals, which are obtained from functional magnetic resonance imaging (fMRI). In BOLD data we can observe statistical dependencies between brain regions. This phenomenon is known as functional connectivity (FC). Computational models are being developed to reproduce the FC of the brain. As in previous empirical studies, these models assume that FC is stationary, i.e. the mean and the covariance of the BOLD time series used for the FC are constant over time. Nevertheless, recent empirical studies focusing on the dynamics of FC at different time scales show that FC is variable in time. This feature is not reproduced in the simulated data generated by some previous computational models. Here we have enhanced the non-linearity of local dynamics in a large-scale computational model. By enhancing this non-linearity, our model is able to reproduce the variability of the FC found in empirical data