Dissertations / Theses on the topic 'Analyse d'image médicale'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Analyse d'image médicale.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Dary, Christophe. "Analyse géométrique d'image : application à la segmentation multi-échelle des images médicales." Nantes, 1992. http://www.theses.fr/1992NANT07VS.
Full textRichard, Frédéric. "Modèles et analyses statistiques de l'image biomédicale." Habilitation à diriger des recherches, Université René Descartes - Paris V, 2009. http://tel.archives-ouvertes.fr/tel-00522704.
Full textLouazani, Samir. "Etude par analyse d'image de la désynchronisation d'une culture de cellules cardiaques sous l'influence de digitaliques." Lyon 1, 1998. http://www.theses.fr/1998LYO10190.
Full textLeteneur, Olivier. "Contribution à l'étude et à la réalisation d'une chaîne de reconstruction 3D du ventricule gauche en mouvement, à partir de séquences échocardiographiques sous incidences apicales : proposition d'une méthode analyse locale du mouvement de la paroi ventriculaire." Lille 1, 1997. http://www.theses.fr/1997LIL10108.
Full textFiot, Jean-Baptiste. "Méthodes mathématiques d'analyse d'image pour les études de population transversales et longitudinales." Phd thesis, Université Paris Dauphine - Paris IX, 2013. http://tel.archives-ouvertes.fr/tel-00952079.
Full textKharboutly, Zaher. "Etude de l'écoulement sanguin dans des fistules artério-veineuses reconstruites à partir d'images médicales." Compiègne, 2007. http://www.theses.fr/2007COMP1692.
Full textDuring the haemodialysis session, the blood is purified through an extracorporeal artificial kidney. High flow in the surgically created vascular access, arterio-venous fistula AVF, leads to a successful blood suction and reinjection. In order to understand the relation between the blood flow dynamics and the physiopathology, it is necessary to understand its characteristics in these vessels. Clinically it is possible to measure blond vectors using the colour echo Doppler. Nevertheless this method is has its limitations. Therefore we propose to use biomechanical model. In this work we have studied blood flow dynamics in patient specific AVF. The principal object was to define and validate a robust methodology capable of simulating blood flow in the AVF reconstructed from clinical examinations
Risser, Laurent. "Analyse quantitative de réseaux micro-vasculaires intra-corticaux." Toulouse 3, 2007. http://www.theses.fr/2007TOU30011.
Full textThis work is a quantitative investigation of intra-cortical micro-vascular networks using a new micro-tomography imaging protocol which permits a complete scan of the entire gray matter with a micron resolution. The first part of the PhD is devoted to the analysis of very large 3D images coming from healthy rats and marmosets primate cortex, as well as tumour implanted rats brains. Classical methods are used for binarisation and squeletonization of the images. The influence of the experimental protocol on the obtained images is evaluated. A fast and original method is proposed to fill the gaps of incompletely injected vessels the efficiency of which is tested and validated. The second part of the PhD is concerned by the statistical analysis of geometrical, local and topological properties of micro-vascular networks. Geometrical properties are related to the spatial distribution of vessels from studying the vascular density and the vessel/tissue distance map. We brought to the fore the multi-scale properties of those fields from fractal and spectral analysis up to a some cut-off which defines the typical length-scale of an elementary representative volume. We found that this length-scale significantly differ in normal and tumoral tissues. The local analysis of vessel's segment length systematically exhibits exponential distribution, which leads to some characteristic segments length. Those length significantly differ in adult and new-born primates tissues. This analysis is consistent with the result obtained on the vascular density and leads to the conclusion that developmental angiogenesis occurs mainly at the capillary scale. .
Moles, Lopez Xavier. "Characterization and Colocalization of Tissue-Based Biomarker Expression by Quantitative Image Analysis: Development and Extraction of Novel Features." Doctoral thesis, Universite Libre de Bruxelles, 2014. http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/209330.
Full textDoctorat en Sciences de l'ingénieur
info:eu-repo/semantics/nonPublished
Montagnat, Johan. "Traitement et analyse de grands ensembles d'images médicales." Habilitation à diriger des recherches, Université de Nice Sophia-Antipolis, 2006. http://tel.archives-ouvertes.fr/tel-00460766.
Full textCoulaud, Benjamin. "Construction d’un cadre statistique consistant pour l’analyse de surfaces au travers de processus généralisés : application à la classification de surfaces cérébrales extraites d’IRM." Thesis, Aix-Marseille, 2017. http://www.theses.fr/2017AIXM0295.
Full textThe main topic of this manuscript is surface statistic analysis. We define a new formalism that extends to a random framework the surface representation introduced by Glaunès and Vaillant (2005). This formalism is based on a notion of random linear form, which is inspired from the theory of generalized random process, developped by Itô (1954) and Gelfand and Vilenkin (1964). On this representation, we set a probabilistic model that describes the variability of surfaces ; by a transition from continuous to discrete, we extend it to an observation model that describes experimental data. We build estimators for the mean representant of a surface sample and for the autocovariance of the noise. We demonstrate that these estimators are consistent. We report some experiments in which we test our estimation method on simulated data. We apply our statistical framework to classification of brain surfaces from MRI, using a Bayesian classification procedure
Tran, Minh-Phuong. "Analyse d'images 3D par méthodes variationnelles et ondelettes : application à l'imagerie médicale." Phd thesis, Université d'Orléans, 2012. http://tel.archives-ouvertes.fr/tel-00772308.
Full textMontagnat, Johan. "Segmentation d'image médicales volumiques à l'aide de maillages déformables contraints." Phd thesis, École normale supérieure de Cachan - ENS Cachan, 1996. http://tel.archives-ouvertes.fr/tel-00691915.
Full textPham, Chi-Hieu. "Apprentisage profond pour la super-résolution et la segmentation d'images médicales." Thesis, Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2018. http://www.theses.fr/2018IMTA0124/document.
Full textIn this thesis, our motivation is dedicated to studying the behaviors of different image representations and developing a method for super-resolution, cross-modal synthesis and segmentation of medical imaging. Super-Resolution aims to enhance the image resolution using single or multiple data acquisitions. In this work, we focus on single image super-resolution (SR) that estimates the high-resolution (HR) image from one corresponding low-resolution (LR) image. Increasing image resolution through SR is a key to more accurate understanding of the anatomy. The applications of super-resolution have been shown that applying super-resolution techniques leads to more accurate segmentation maps. Sometimes, certain tissue contrasts may not be acquired during the imaging session because of time-consuming, expensive costor lacking of devices. One possible solution is to use medical image cross-modal synthesis methods to generate the missing subject-specific scans in the desired target domain from the given source image domain. The objective of synthetic images is to improve other automatic medical image processing steps such as segmentation, super-resolution or registration. In this thesis, convolutional neural networks are applied to super-resolution and cross-modal synthesis in the context of supervised learning. In addition, an attempt to apply generative adversarial networks for unpaired cross-modal synthesis brain MRI is described. Results demonstrate the potential of deep learning methods with respect to practical medical applications
Niepceron, Brad. "Développement d'une application d'aide au diagnostic basée sur les réseaux de neurones artificiels pour la détection de tumeurs cérébrales." Electronic Thesis or Diss., Amiens, 2021. http://www.theses.fr/2021AMIE0071.
Full textDuring the last decade, the study of brain tumor diagnosis systems brought a significant attention regarding to the fast growth of deep learning and the development of Artificial Neural Networks (ANNs). In the clinical field, deep learning based algorithms are being used to solve visual tasks such as the detection and segmentation of unhealthy tissues. These methods proved to be particularly efficient in the diagnosis of aggressive tumors like high grade gliomas. However, constrained by their important need in computational resources, these models cannot be realistically deployed on a large scale.In fact, their architecture becoming deeper with the improvement of their performances, their use and development entails significant material and energy costs as well as an important carbon dioxide emission. The optimization or replacement of these methods by solutions that are less dependent on the availability of high computational resources is thus critical. To respond to these problems, the compression of modern Convolutional Neural Networks (CNNs) for the creation of brain tumor segmentation applications on embedded systems is considered. Moreover, although many debates appeared concerning the efficiency of Deep Learning algorithms, some solutions based on Spiking Neural Networks (SNNs) are yet to be investigated in order to build fast and affordable medical image analysis systems.The objective of this work is thus to propose new ways to design medical image analysis systems, specifically for glioma tumors diagnosis. We aim to tackle the computational and energy cost issues of existing deep learning solutions to let their deployment be realistic in clinical settings. Hence, the first contribution presented in this manuscript firstly focuses on the adaptation of ANNs to devices with limited computational resources by the means of compression methods. Then, in a second contribution, non-trainable neural models for medical image analysis are investigated in order to respond to the cost problems induced by deep learning. Finally, our third contribution present a new method for the development of brain tumor diagnosis systems based on models of biological neurons
Stawiaski, Jean. "Morphologie mathématique et graphes : application à la segmentation interactive d'images médicales." Phd thesis, École Nationale Supérieure des Mines de Paris, 2008. http://pastel.archives-ouvertes.fr/pastel-00004807.
Full textSomphone, Oudom. "Recalage par éléments finis avec partition de l'unité : applications en imagerie médicale." Paris 9, 2009. https://bu.dauphine.psl.eu/fileviewer/index.php?doc=2009PA090032.
Full textIn this work, we present a Partition of Unity Finite Element Method (PUFEM) to compute the transformation between two images, which is represented by a non-rigid, locally polynomial displacement field. The partition of unity property offers an efficient optimization scheme by breaking down the global minimization of the mismatch energy into independent, local minimizations. We then introduce a conformity constraint between the local representations to provide a flexible way to control the globality of the deformation. We first apply our method to register 3D-CT images in order to estimate the respiratory motion; it is compared to four other methods with respect to quantitative and qualitative criteria. Secondly, we use our partition of unity representation for the purpose of two-phase, prior-based image segmentation. The crux is to register a binary prior shape to an image in order to segment it. The conformity constraint compels the solution to be compliant with the shape prior
Hatt, Mathieu. "Analyse et traitement d'images multi modales en oncologie." Habilitation à diriger des recherches, Université de Bretagne occidentale - Brest, 2012. http://tel.archives-ouvertes.fr/tel-00721743.
Full textRialle, Vincent. "Aide au diagnostic et à l'apprentissage dans un domaine médical incertain, incomplet et évolutif : étude des méthodes existantes et proposition d'une méthodologie nouvelle." Phd thesis, Grenoble 1, 1987. https://theses.hal.science/tel-00325679.
Full textRialle, Vincent. "Aide au diagnostic et à l'apprentissage dans un domaine médical incertain, incomplet et évolutif : étude des méthodes existantes et proposition d'une méthodologie nouvelle." Phd thesis, Université Joseph Fourier (Grenoble), 1987. http://tel.archives-ouvertes.fr/tel-00325679.
Full textMontagnat, Johan. "Modèles déformables pour la segmentation et la modélisation d'images médicales 3D et 4D." Phd thesis, Université de Nice Sophia-Antipolis, 1999. http://tel.archives-ouvertes.fr/tel-00683368.
Full textLopes, Renaud. "Analyses fractale et multifractale en imagerie médicale : outils, validations et applications." Thesis, Lille 1, 2009. http://www.theses.fr/2009LIL10100/document.
Full textFractal geometry is an emerging concept used in medical image analysis. The aim of this geometry is to measure global and local heterogeneities (1D, 2D or 3D). In medical imaging, it is often used to characterize 1D and 2D signals and restricted to discriminate between 2 states (healthy/pathological) by a global analysis of a signal. This thesis aims at providing 3D fractal geometry based tools for the measures of global (volume) and local (voxel) heterogeneities. Two indices are used: fractal dimension and multifractal spectrum (Hölder exponents). Since these algorithms estimate the theoretical value, fractal and multifractal synthetic volumes were used for the validation. This work also proposes texture segmentation tools. Two applications were studied; characterization of epileptic foci on single photon emission computed tomography images and the detection of prostatic tumors on T2-weighted MR images. The effectiveness of fractal and multifractal features are studied through a framework of supervised classification. The results for both applications demonstrate the usefulness of this geometry and its adaptability to several applications in medical imaging
Jiang, Zhifan. "Évaluation des mobilités et modélisation géométrique du système pelvien féminin par analyse d’images médicales." Thesis, Lille 1, 2017. http://www.theses.fr/2017LIL10003/document.
Full textThe better treatment of female pelvic mobility disorders has a social impact affecting particularly aged women. It is in this context that this thesis focuses on the development of methods in medical image analysis, for the evaluation of pelvic mobility and the geometric modeling of the pelvic organs. For this purpose, we provide solutions based on the registration of deformable models on Magnetic Resonance Images (MRI). All the results are able to detect the shape and quantify the movement of a part of the organs and to reconstruct their surfaces from patient-specific MRI. This work facilitates the simulation of the behavior of the pelvic organs using finite element method. The objective of these developed tools is to help to better understand the mechanism of the pathologies. They will finally allow to better predict the presence of certain diseases, as well as make surgical procedures more accurate and personalized
Afdel, Karim. "Conception d'outils d'analyse quantitative d'images pour la biologie moléculaire et la dermatologie." Aix-Marseille 3, 1994. http://www.theses.fr/1994AIX30072.
Full textBoucher, Arnaud. "Recalage et analyse d'un couple d'images : application aux mammographies." Phd thesis, Université René Descartes - Paris V, 2013. http://tel.archives-ouvertes.fr/tel-00798271.
Full textEude, Thierry. "Compression d'images médicales pour la transmission et l'archivage, par la transformée en cosinus discrète." Rouen, 1993. http://www.theses.fr/1993ROUES056.
Full textRakotomalala-Randrianarisoa, Vaoariniaina Vénérée. "Reconstruction bidimensionnelle de vaisseaux rétiniens par analyse d'images couleur de fond d'oeil." Lille 1, 1999. https://pepite-depot.univ-lille.fr/LIBRE/Th_Num/1999/50376-1999-359.pdf.
Full textBensemra-Zegadi, Nacera. "Analyse spectrale locale d'images texturées par transformation en ondelettes : application à la quantification de textures osseuses." Lyon, INSA, 1998. http://www.theses.fr/1998ISAL0042.
Full textTexture is naturally a multi-scale notion which is linked to a human observant. In its classical form, wavelet transform (WT) is a multi-scale representation. It permits a hierarchical texture observation, in a global and a local manner, similar at the human vision and which characterise spatial interactions into-scale. We focus also on a second interpretation of WT as a frequency analysis tool. Space-frequency transformations associate a local frequential spectrum to each point of the image. Thus, spectrogram, Gabor transform, Wigner-Ville transform and the quadratic form of WT can be defined for images in a class of energetic representations. Relationships between these transformations can be expressed by means of the Wigner-Ville transform, which plays a central theoretical role. A Mellin-Fourier transform based technique is proposed. The obtained spectral representation is well adapted to texture analysis. It allows extracting a large number of frequential parameters from local spectra. Moreover, parameters characterising orientation and anisotropy are proposed and illustrated with natural textures. WT is also well suited to estimate -the fractal dimension. This last parameter permits to characterise the roughness texture. The textural approach is a non invasive method which is particularly interesting to quantify structural variations due to vertebra aging. We have used local analysis methods and some global ones on radiological images of vertebra (obtained in high resolution tomography and in sagital micro-radiography), which contains different directional informations
Dellandréa, Emmanuel. "Analyse de signaux vidéos et sonores : application à l'étude de signaux médicaux." Tours, 2003. http://www.theses.fr/2003TOUR4031.
Full textThe work deals with the study of multimedia sequences containing images and sounds. The analysis of images sequences consists in the tracking of moving objects in order to allow the study of their properties. The investigations have to enable the understanding of sounds when correlated to events in the image sequence. One generic method, based on the combination of regions and contours tracking, and one method adapted to homogeneous objects, based on level set theory, are proposed. The analysis of audio data consists in the development of an identification system based on the study of the structure of signals thanks to their coding and Zipf laws modeling. These methods have been evaluated on medical sequences within the framework of the gastro-oesophageal reflux pathology study, in collaboration with the Acoustique et Motricité Digestive research team of the University of Tours
Foucher, Christophe. "Analyse et amélioration d'algorithmes neuronaux et non neuronaux de quantification vectorielle pour la compression d'images." Rennes 1, 2002. http://www.theses.fr/2002REN10120.
Full textFaucheux, Cyrille. "Segmentation supervisée d'images texturées par régularisation de graphes." Thesis, Tours, 2013. http://www.theses.fr/2013TOUR4050/document.
Full textIn this thesis, we improve a recent image segmentation algorithm based on a graph regularization process. The goal of this method is to compute an indicator function that satisfies a regularity and a fidelity criteria. Its particularity is to represent images with similarity graphs. This data structure allows relations to be established between similar pixels, leading to non-local processing of the data. In order to improve this approach, combine it with another non-local one: the texture features. Two solutions are developped, both based on Haralick features. In the first one, we propose a new fidelity term which is based on the work of Chan and Vese and is able to evaluate the homogeneity of texture features. In the second method, we propose to replace the fidelity criteria by the output of a supervised classifier. Trained to recognize several textures, the classifier is able to produce a better modelization of the problem by identifying the most relevant texture features. This method is also extended to multiclass segmentation problems. Both are applied to 2D and 3D textured images
Grezes-Besset, Louise. "Détection et analyse du mouvement respiratoire à partir d'images fluoroscopiques en radiothérapie." Phd thesis, INSA de Lyon, 2011. http://tel.archives-ouvertes.fr/tel-00735816.
Full textMichoud, Edouard. "Analyse d'images dynamiques en biologie et médecine : applications à la microcirculation clinique et expérimentale." Université Joseph Fourier (Grenoble), 1990. http://www.theses.fr/1990GRE19002.
Full textMvoulana, Amed. "Vers un ophtalmologiste "augmenté" : analyse d'images rétiniennes pour l'aide au diagnostic précoce du glaucome." Thesis, Université Gustave Eiffel, 2022. http://www.theses.fr/2022UEFL2007.
Full textOcular diseases are at the core of major public health issues. One of them, glaucoma, requires early screening to ensure effective treatment of affected patients, and prevent irreversible visual damages. The advent of so-called computer vision and deep learning approaches has led to a paradigm shift in the field of ophthalmology, providing unprecedented support in diagnostic and therapeutic choices. In this thesis, we propose new methods for the development of intelligent systems dedicated to the early detection of glaucoma from retinal images. In particular, we aim at deploying of mobile-based computer-aided diagnosis systems, for remote screening. Firstly, we proposed a method aiming at analyzing the optic nerve head, featured by morphological changes in the presence of glaucoma. Based on a precise algorithm for segmenting the structures of the optic disc and the cup within it, the method extracts clinically relevant measures such as the cup-to-disc ratio, the inferior-superior-nasal-temporal (ISNT) sectors and the neuroretinal rim area. A clinical protocol based on ophthalmic references is drawn to screen for glaucoma, and give indications about the stages of development of the neuropathy (early, moderate or advanced glaucoma). Although very accurate screening, with a performance rate of 94% on the evaluation base (DRISHTI-GS1), this method has highlighted the need to improve generalizability, particularly in the presence of glaucomatous nerve heads without excavation (false negatives) or large healthy nerve heads (false positives). Secondly, we proposed a method based on deep learning algorithms, allowing an automated interpretation of healthy or glaucomatous retinas. This work exploits state-of-the-art convolutional neural networks (VGG-16, ResNet50, Inception-v3, MobileNet and DenseNet121), and proposes an efficient transfer learning method to adapt these networks to the glaucoma screening. These models achieve an AUC of more than 0.97, however, this comparative study has identified the needs for developing efficient models for deployment in clinical conditions: 1) a consistent retinal image dataset in terms of size, inter-class balance, diagnostic reliability and clinical variability, 2) interpretable and explainable models, allowing specialists to understand and discuss the screening result.In this sense, we propose in a third step a method exploiting recent advances in semi-supervised learning, for the generation of synthetic retinal images. The proposed algorithm, BAGAN (for Balancing GAN), allows to produce from a reference image dataset (REFUGE), a new dataset filling the inter-class imbalance potentially responsible for diagnostic bias, while meeting the criteria of image quality and clinical diversity. We have demonstrated the relevance of such dataset in the further development of semi-supervised diagnosis algorithms. Finally, a brand new interface, available on desktop and mobile platforms, has been designed for ophthalmologists and health professionals. Smart and intuitive, it integrates various functionalities based on the developed algorithms, and allows real-time screening to contribute to the improvement of eye health care
BACHAR, KADDOUR. "Contributions en analyse factorielle et en classification ascendante hierarchique sous contrainte de contiguite. Applications a la segmentation d'images." Rennes 1, 1994. http://www.theses.fr/1994REN10201.
Full textAlvarez, padilla Francisco Javier. "AIMM - Analyse d'Images nucléaires dans un contexte Multimodal et Multitemporel." Thesis, Reims, 2019. http://www.theses.fr/2019REIMS017/document.
Full textThis work focuses on the proposition of cancerous tumor segmentation strategies in a multimodal and multitemporal context. Multimodal scope refers to coupling PET/CT data in order to jointly exploit both information sources with the purpose of improving segmentation performance. Multitemporal scope refers to the use of images acquired at different dates, which limits a possible spatial correspondence between them.In a first method, a tree is used to process and extract information dedicated to feed a random walker segmentation. A set of region-based attributes is used to characterize tree nodes, filter the tree and then project data into the image space for building a vectorial image. A random walker guided by vectorial tree data on image lattice is used to label voxels for segmentation.The second method is geared toward multitemporality problem by changing voxel-to-voxel for node-to-node paradigm. A tree structure is thus applied to model two hierarchical graphs from PET and contrast-enhanced CT, respectively, and compare attribute distances between their nodes to match those assumed similar whereas discarding the others.In a third method, namely an extension of the first one, the tree is directly involved as the data-structure for algorithm application. A tree structure is built on the PET image, and CT data is then projected onto the tree as contextual information. A node stability algorithm is applied to detect and prune unstable attribute nodes. PET-based seeds are projected into the tree to assign node seed labels (tumor and background) and propagate them by hierarchy. The uncertain nodes, with region-based attributes as descriptors, are involved in a vectorial random walker method to complete tree labeling and build the segmentation
Gorce, Jean-Marie. "Analyse spectrale locale par modélisation autoregressive spatialement régularisée : application aux images de radiofréquence en échocardiographie ultrasonore." Lyon, INSA, 1998. http://www.theses.fr/1998ISAL0050.
Full textLocal spectral analysis or time-frequency analysis of radio-frequency (RF) images in ultrasound echography is a difficult task due to their non-stationary and stochastic nature. These characteristics yield a high variability when conventional spectral estimation methods are used. Moreover, abrupt changes in the spectral content occur at interfaces between probed tissues. In this context, we propose a method based on autoregressive (AR) models spatially regularized in a Bayesian framework. The problem is expressed with respect to the reflection coefficients associated with AR models. This allows reducing the problem formulation to a conventional image restoration task where the reflection coefficients stand for the data to be recovered. A spatial regularization constraint (or smoothness constraint) is introduced, based on the Markovian Random Field modeling. Such constraint allows reducing the high variability of the local estimates while preserving a high spatial resolution. The use of non-quadratic potential functions pro vides a way for preserving abrupt changes (or discontinuities) in the spectral content. The behavior of several potential functions is -assessed and the influence of the Jonvexity of these functions on the results is emphasized. 1 We implement a deterministic minimization algorithm integrating both the graduated non-convexity and the half quadratic minimization principles. The solution in the sense of the Maximum a Posteriori is obtained by applying the proposed algorithm applied alternately to the reflection coefficients and the power term series. The performances of this approach are evaluated on numerical simulations and the method is applied to experimental ultrasound echocardiographic RF data
Menguy, Pierre-Yves. "Suivi longitudinal des endoprothèses coronaires par analyse de séquences d'images de tomographie par cohérence optique." Thesis, Clermont-Ferrand 1, 2016. http://www.theses.fr/2016CLF1MM30/document.
Full textThis thesis deals with the segmentation and characterization of coronary arteries and stents in Optical Coherence Tomography (OCT) imaging. OCT is a very high resolution imaging that can appreciate fine structures such as the intimal layer of the vascular wall and stitches (struts). The objective of this thesis is to propose software tools allowing the automatic analysis of an examination with a runtime compatible with an intraoperative use. This work follows Dubuisson's thesis in OCT, which proposed a first formalism for light segmentation and strut detection for metal stents. We revisited the treatment chain for these two problems and proposed a preliminary method for detecting bioabsorbable polymer stents. Surface modeling of the stent made it possible to estimate a series of clinical indices from the diameters, surfaces and volumes measured on each section or on the entire examination. Applying the stent to the wall is also measured and visualized in 3D with an intuitive color scale. The arterial lumen is delineated using a Fast Marching short path search algorithm. Its originality is to exploit the image in the native helical form of the acquisition. For the detection of the metallic stent, the local maxima of the image followed by a shadow zone have been detected and characterized by a vector of attributes calculated in their neighborhood (relative value of the maximum, slope in gray level, symmetry ...). Peaks corresponding to struts were discriminated from the surrounding speckle by a logistic regression step with learning from a field truth constructed by an expert. A probability of belonging to the peaks to struts is constructed from the combination of attributes obtained. The originality of the method lies in the fusion of the probabilities of the close elements before applying a decision criterion also determined from the ground truth. The method was evaluated on a database of 14 complete examinations, both at the level of pixels and struts detected. We have also extensively validated a method of non-rigid registration of OCT images using bitters matched by an expert on the source and target exams. The objective of this registration is to be able to compare cut-to-cut examinations and indices calculated at the same positions at different acquisition times. The reliability of the strain model was evaluated on a corpus of forty-four pairs of OCT exams from a Leave-One-Out cross validation technique
Lalys, Florent. "Automatic recognition of low-level and high-level surgical tasks in the operating room from video images." Phd thesis, Rennes 1, 2012. https://ecm.univ-rennes1.fr/nuxeo/site/esupversions/2186a1f7-f586-43c5-b037-6585b5c22aef.
Full textThe need for a better integration of new Computer-Assisted-Surgical systems in the Operating Room (OR) has been recently emphasized. One necessity to achieve this objective is to retrieve data from the OR with different sensors, then to derive models from these data for creating Surgical Process Models (SPMs). Recently, the use of videos from cameras in the OR has demonstrated its efficiency for advancing the creation of situation-aware CAS systems. The purpose of this thesis was to present a new method for the automatic detection of high-level (i. E. Surgical phases) and low-level surgical tasks (i. E. Surgical activities) from microscope video images only. The first step consisted in the detection of high-level surgical tasks. The idea was to combine state-of-the-art computer vision techniques with time series analysis. Image-based classifiers were implemented for extracting visual cues, therefore characterizing each frame of the video, and time-series algorithms were then applied to model time-varying data. The second step consisted in the detection of low-level surgical tasks. Information concerning surgical tools and anatomical structures were detected through an image-based approach and combined with the information of the current phase within a knowledge-based recognition system. Validated on neurosurgical and eye procedures, we obtained recognition rates of around 94% for the recognition of high-level tasks and 64% for low-level tasks. These recognition frameworks might be helpful for automatic post-operative report generation, learning/teaching purposes, and for future context-aware surgical systems
Lalys, Florent. "Automatic recognition of low-level and high-level surgical tasks in the Operating Room from video images." Phd thesis, Université Rennes 1, 2012. http://tel.archives-ouvertes.fr/tel-00695648.
Full textRavaut, Frédéric. "Analyse automatique des manifestations faciales cliniques par techniques de traitement d'images : application aux manifestations de l'épilepsie." Paris 5, 1999. http://www.theses.fr/1999PA05S027.
Full textWojak, Julien. "Analyse d'images multimodales TEP-TDM du thorax : Application à l'oncologie : segmentation de tumeurs, d'organes à risque et suivi longitudinal pour la radiothérapie." Paris, Télécom ParisTech, 2010. http://pastel.archives-ouvertes.fr/pastel-00567100.
Full textIn oncological thoracic imaging, computerized tomography (CT) and positron emission tomography (PET) are widely used jointly, for diagnosis or treatment planing. The development of combined scanners enables the acquisition of pairs of CT-PET volumes, allowing their joint exploitation in clinical routine, without the prerequisite for complex registration. One goal of this thesis work was to propose a segmentation method jointly exploiting PET and CT image information. The proposed methodology therefore focuses on a detailed segmentation of the CT images, using PET information to guide the tumor segmentation. The framework of variational segmentation methods is used to design our algorithms and the specific constraints based on PET information. In addition to target structures for radiotherapy (tumors, nodules), organs at risk which need to be preserved from radiations, must be segmented. An additional goal of this thesis is to provide segmentation methods for these organs. The methods rely on strong a priori knowledge on the non-parametric intensity distributions and on the shapes of the different organs. A final goal of the thesis is to propose a methodological framework for the segmentation of tumors in the context of longitudinal follow up of patients with registered images. The proposed segmentation methods were tested on multiple data sets. When manual tracing is available, quantitive comparisons of the segmentations are presented, demonstrating the performance and accuracy of the proposed segmentation framework
Lamy, Julien. "Calcul du chemin central du côlon pour une analyse locale des pathologies." Université Louis Pasteur (Strasbourg) (1971-2008), 2005. https://publication-theses.unistra.fr/public/theses_doctorat/2005/LAMY_Julien_2005.pdf.
Full textColon cancer is one of the most frequent cause of cancer, for both genders. The standard exam to detect cancerous or pre-cancerous structures is optical colonoscopy, which has a low acceptance among patients, and presents risks of colon perforation. It is moreover often impossible to reach the cæcum, which forbids a complete analysis of the colon. Virtual colonoscopy techniques, appeared in the last ten years, allow to replace the optical colonoscopy exam by a CT or MR exam. A physician can then navigate inside the colon, without the limitations due to optical colonoscopy:the navigation is no more limitted by the presence of the endoscope, the whole colon can thus be explored, and the structures can be viewed from every angle. The first part of this thesis present different methods to segment the colon lumen, based on photometric criteria. Global and local methods are presented, leading to a common segmentation framework for CT and MR images. The second part concerns the detection of the central path. We present a skeletonization and pruning algorithm of the colon, then an algorithm to remove the loops resulting from imperfections in the original image. The third part concerns the local detection of cancerous structures. So that we can work locally, we give an algorithm to cover the colon with sections that are orthogonal to its central path. These sections allow us to propose local detection methods for cancerous structures
Ghandour, Sarah. "Segmentation d'images couleurs par morphologie mathématique : application aux images microscopiques." Toulouse 3, 2010. http://thesesups.ups-tlse.fr/867.
Full textFuture architectures of communication systems will be more and more complex due to the need for reconfigurability in terms of frequency, emitted and received power, power consumption and reliability. One interesting and very promising technology comes under the name of RF-MEMS. In general MEMS component replaces and outperforms its counterparts. These structures will be yielded to electrostatic and/or electromagnetic strains that it is necessary to investigate and to understand the effects. Besides, power handling of those devices is one of the parameters that qualify its robustness. Since they have shown interesting functionalities for space applications, its sensitivity to radiation needs to be understood. The motivation of the thesis aims at analyzing the impact of those strains in the functional parameters (actuation voltages, switching times, insertion losses, isolation), using an appropriate reliability bench test. Clever analyses of the failure mechanisms that occur after stresses such as DC stress, ESD discharge, RF power qualification and radiation, have been performed. The stresses will be applied on various structures with various architectures and designs, in order to determine the robustness and the reliability of each technology. Finally, the validation and the new findings of these works present one design integrating ESD protection and an accelerated stress test circuit is also proposed. This thesis was being part of the framework of the European Network of Excellence AMICOM on RF Micro-systems where reliability has been defined to be a major challenge to its integration and its commercialization
Chesseboeuf, Clément. "Méthodes mathématiques et numériques pour la modélisation des déformations et l'analyse de texture. Applications en imagerie médicale." Thesis, Poitiers, 2017. http://www.theses.fr/2017POIT2285/document.
Full textWe present a numerical procedure for the matching of 3D MRI. The problem of image matching is addressed through the usual distinction between the deformation model and the matching criterion. The deformation model is based on the theory of computational anatomy and the set of deformations is a group of diffeomorphisms generated by integrating vector fields. The discrepancy between the two images is evaluated through comparisons of level lines represented by a differential current in the dual of a space of vector fields. This representation leads to a quickly computable non-local criterion. Then, the optimisation method is based on the minimization of the criterion following the idea of the so-called sub-optimal algorithm. We take advantage of the eulerian and periodical description of the algorithm to get an efficient numerical procedure. This algorithm can be used to deal with 3d MR images and numerical experiences are presented. In an other part, we focus on theoretical properties of the algorithm. We begin by simplifying the equation representing the evolution of the deformed image and we use the theory of viscosity solutions to study the simplified equation. The second issue we are interested in is the change-point estimation for a gaussian sequence with change in the variance parameter. The main feature of our model is that we work with infill data and the nature of the data can evolve jointly with the size of the sample. The usual approach suggests to introduce a contrast function and using the point of its maximum as a change-point estimator. We first get an information about the asymptotic fluctuations of the contrast function around its mean function. Then, we focus on the change-point estimator and more precisely on the convergence of this estimator. The most direct application concerns the detection of change in the Hurst parameter of a fractional brownian motion. The estimator depends on a parameter p > 0, generalizing the usual choice p = 2. We present some results illustrating the advantage of a parameter p < 2
Rey, David. "Détection et quantification automatiques de processus évolutifs dans des images médicales tridimensionnelles : application à la sclérose en plaques." Phd thesis, Université de Nice Sophia-Antipolis, 2002. http://tel.archives-ouvertes.fr/tel-00636176.
Full textMansi, Tommaso. "Modèles physiologiques et statistiques du cœur guidés par imagerie médicale : application à la tétralogie de Fallot." Phd thesis, École Nationale Supérieure des Mines de Paris, 2010. http://tel.archives-ouvertes.fr/tel-00530956.
Full textBanga, Mbom Calvin David. "L'approche bootstrap en analyse des images : application à la restitution de la cinétique de la fuite dans la choriorétinopathie séreuse centrale." Rennes 1, 1995. http://www.theses.fr/1995REN10016.
Full textThis work concerns the medical image analysis using statistical pattern recognition methods. These methods usually lead to classification and multivariage segmentation approaches that are more and more used in medical imaging for qualitative or quantitative analysis of tissue. However, statistical pattern reconigtion methods are well known to need high computing time. This assumption is not suitable for image sequences analysis. To get rid of this important problem, we suggest a bootstrap approach for two-dimensional image analysis. This model is based on the random sampling of blocks of observations in the original image. The correlation relationships are maintained in a given block, while the selected blocks are each other independent. Given an original image, we randomly select a small representative set of observations for image statistical parameters estimation. In this way, the bootstrap model improves the estimation and reduces the computing time due to the complexity of estimation algorithms used in statistical pattern recognition. The problem of the quantification of the serum leak kinetic in the Central Serous Choroiditis pathology is and important application in wich the bootstrap model we propose is fro a great need. The serum leak surface is mesures from the eye's fundus images sequence after an unsupervised segmentation sept using the bootstrap random sampling model wich we have proposed. Both a high-quality segmentation and a great reduction of etimation time are required for this application. A graph showing the serum leak surface versus the Fluorecein inection time is then plotted for helping the decision in ophtalmology. The bootstrap model wich we propose for image analysis shows the way to use the bootstrap approach for statistical parameters estimation in pattern recognition, notably in image analysis by invariance methods, in texture analysis and multivariate segmentation
Mcleod, Kristin. "Modèles statistiques réduits de la croissance cardiaque, du mouvement et de la circulation sanguine : application à la tétralogie de Fallot." Phd thesis, Université Nice Sophia Antipolis, 2013. http://tel.archives-ouvertes.fr/tel-00942556.
Full textOussena, Baya. "Recherche et parallélisation d'un algorithme de traitement et de compression d'images médicales avec sauvegarde des détails diagnostiques : application à la détection des microcalcifications dans les images mammographiques." Paris 6, 2005. http://www.theses.fr/2005PA066035.
Full textGlatard, Tristan. "Description, deployment and optimization of medical image analysis workflows on production grids." Nice, 2007. http://www.theses.fr/2007NICE4049.
Full textEn permettant le partage à grande échelle de données et d'algorithmes et en fournissant une quantité importante de puissance de calcul et de stockage, les grilles de calcul sont des plates-formes intéressantes pour les applications d'analyse d'images médicales. Dans cette thèse, nous étudions un problème d'analyse d'images médicales qui s'avère être une application dimensionnante pour les grilles, conduisant au développement de nouvelles méthodes et outils pour la description, l'implémentation et l'optimisation de flots de traitements. Le problème applicatif étudié est l'évaluation de la précision d'algorithmes de recalage d'images médicales en l'absence de vérité terrain. Nous faisons passer à l'échelle une méthode statistique d'évaluation de ces algorithmes et nous montrons des résultats de précision sur une base de données liée au suivi de la radiothérapie du cerveau. Ces résultats permettent notamment de détecter des défauts très légers au sein des données. Nous étendons ce schéma pour quantifier l'impact de la compression des images sur la qualité du recalage. Cette application étant représentative de problèmes typiques survenant sur les grilles, nous nous attachons à son déploiement et à son exécution sur ce type d'infrastructures. Pour faciliter une parallélisation transparente, nous adoptons un modèle générique de flots de traitements, dont nous proposons une nouvelle taxonomie. Pour répondre aux limitations de performance des moteurs d'exécution de flots existants, nous présentons MOTEUR, qui permet d'exploiter les différents types de parallélisme inhérents à ces applications. La définition d'un nouvel opérateur de composition de données facilite la description des applications d'analyse d'images médicales sur les grilles. Par une comparaison entre la grille de production EGEE et des grappes dédiées de Grid'5000, nous mettons en évidence l'importance de la variabilité de la latence sur une grille de production. En conséquence, nous proposons un modèle probabiliste du temps d'exécution d'un flot de traitement sur une grille. Ce modèle est centré sur l'utilisateur : il considère la grille toute entière comme une boîte noire introduisant une latence aléatoire sur le temps d'exécution d'une tâche. A partir de ce modèle, nous proposons trois stratégies d'optimisation visant à réduire l'impact de la latence et de sa variabilité : (1) dans un flot de traitement, grouper les tâches séquentiellement liées permet de réduire la latence moyenne rencontrée, (2) optimiser la valeur du délai d'expiration des tâches prémunit contre les valeurs extrêmes de la latence et (3) optimiser la granularité des tâches permet de réduire le risque de rencontrer de fortes latences. Des accélérations significatives sont ainsi obtenues