La délimitation précise du contour des lésions pigmentées sur des images est une première étape importante pour le diagnostic assisté par ordinateur du mélanome. Cette thèse présente une nouvelle approche de la détection automatique du contour des lésions pigmentaires sur des images couleurs ou multispectrales de la peau. Nous présentons d'abord la notion de minimisation d'énergie par coupes de graphes en terme de Maxima A-Posteriori d'un champ de Markov. Après un rapide état de l'art, nous étudions l'influence des paramètres de l'algorithme sur les contours d'images couleurs. Dans ce cadre, nous proposons une fonction d'énergie basée sur des classifieurs performants (Machines à support de vecteurs et Forêts aléatoires) et sur un vecteur de caractéristiques calculé sur un voisinage local. Pour la segmentation de mélanomes, nous estimons une carte de concentration des chromophores de la peau, indices discriminants du mélanomes, à partir d'images couleurs ou multispectrales, et intégrons ces caractéristiques au vecteur. Enfin, nous détaillons le schéma global de la segmentation automatique de mélanomes, comportant une étape de sélection automatique des "graines" utiles à la coupure de graphes ainsi que la sélection des caractéristiques discriminantes. Cet outil est comparé favorablement aux méthodes classiques à base de coupure de graphes en terme de précision et de robustesse. / Accurate border delineation of pigmented skin lesion (PSL) images is a vital first step in computer-aided diagnosis (CAD) of melanoma. This thesis presents a novel approach of automatic PSL border detection on color and multispectral skin images. We first introduce the concept of energy minimization by graph cuts in terms of maximum a posteriori estimation of a Markov random field (MAP-MRF framework). After a brief state of the art in interactive graph-cut based segmentation methods, we study the influence of parameters of the segmentation algorithm on color images. Under this framework, we propose an energy function based on efficient classifiers (support vector machines and random forests) and a feature vector calculated on a local neighborhood. For the segmentation of melanoma, we estimate the concentration maps of skin chromophores, discriminating indices of melanomas from color and multispectral images, and integrate these features in a vector. Finally, we detail an global framework of automatic segmentation of melanoma, which comprises two main stages: automatic selection of "seeds" useful for graph cuts and the selection of discriminating features. This tool is compared favorably to classic graph-cut based segmentation methods in terms of accuracy and robustness.

Caractériser les propriétés mécaniques de la neige est un défi majeur pour la prévision et la prédétermination du risque d’avalanche. Du fait du grand nombre de types de neige et de la difficulté à effectuer des mesures sur ce matériau très fragile, la compréhension de la relation entre la microstructure de la neige et ses propriétés mécaniques est encore incomplète. Cette thèse aborde ce problème par le biais d’une approche de modélisation mécanique basée sur la microstructure tridimensionnelle de neige obtenue par microtomographie aux rayons X. Tout d’abord, afin d’automatiser et améliorer la segmentation des images microtomographiques, un nouvel algorithme tirant profit de la minimisation de l’énergie de surface de la neige a été développé et évalué. L’image air-glace est ensuite utilisée comme entrée géométrique d’un modèle éléments finis où la glace est supposée élastique fragile. Ce modèle permet de reproduire le comportement fragile en traction et révèle le comportement pseudoplastique apparent causé par l’endommagement microscopique, ainsi que la forte hétérogénéité des contraintes dans la matrice de glace. Pour reproduire les grandes déformations impliquant le ré-arrangement de grains, un modèle par éléments discrets a ensuite été développé. Les grains sont identifiés dans la microstructure en utilisant des critères géométriques dont la pertinence mécanique a été démontrée, et décrits dans le modèle par des blocs rigides de sphères. Le comportement simulé en compression est dominé par le rôle de la densité mais révèle également des différences liées au type de neige. Enfin, pour distinguer le degré de cohésion entre les types de neige, un indicateur microstructurel a été développé et s’est avéré être fortement corrélé aux propriétés mécaniques et physiques du matériau. / Characterizing the complex microstructure of snow and its mechanics is a major challenge for avalanche forecasting and hazard mapping. While the effect of environmental conditions on the snow metamorphism, which leads to numerous snow types, is fairly known, the relation between snow microstructure and mechanical properties is poorly understood because of the very fragile nature of snow. In order to decipher this relation for dry snow, this thesis presents a modeling approach of snow mechanics based on the three-dimensional microstructure of snow captured by X-ray microtomography and the properties of ice. First, in order to automatically process the microtomographic data, we take advantage of the minimization of the snow surface energy through metamorphism to efficiently binary segment grayscale images. Second, assuming an elastic brittle behavior of the ice matrix, the tensile strength of snow is modeled via a finite element approach. The model reveals an apparent pseudo-plastic behavior caused by damage, and the highly heterogenous stress distribution in the ice matrix. Third, we develop a discrete element model, accounting for grain-rearrangements and the creation/failure of inter-granular contacts. The grains, geometric input of the model, are detected in the microstructure with mechanically-relevant criteria and described as rigid clumps of spheres. The model evidences that the compression behavior of snow is mainly controlled by density but that the first stage of deformation is also sensible to the snow type. Last, the inter-granular bonds, recognized to be critical for the mechanical properties, are characterized through a new microstructural indicator, which effectively highly correlates with the simulated mechanical and physical properties.

Consumer segmentation based on expenditure are usually done by using observedcharacteristics, such as age and income. This thesis highlights the problem with negativeexternalities which Venice suffers from, due to mass tourism. This thesis aims to assesswhether unobservable heterogeneity can be used to detect latent classes within tourismexpenditure. Segmenting the tourism market using this approach is valuable for policy making.Segmenting is also useful for the actors in the market to identify and attract high spenders. Inthat way, a destination may uphold a sustainable level of tourism instead of increasing touristnumbers. The method used for this approach is finite mixture modelling (FMM), which is notmuch used within consumer markets and therefore this thesis also contributes to tourismexpenditure methodology. This thesis adds to the literature by increasing the knowledge aboutthe importance of unobserved factors when segmenting visitors.The results show that four latent classes are found in tourism expenditure. Some of thevariables, which are significant in determining tourism expenditure, are shown to affectexpenditure differently in different classes while some are shown not to be significant. Theconclusions are that segmenting tourism expenditure, using unobserved heterogeneity, issignificant and that variables, which are barely significant in determining the expenditure ofthe population, can be strongly significant in determining the expenditure for a certain class.

Submitted by Fernando Souza (fernandoafsou@gmail.com) on 2017-09-20T13:22:58Z No. of bitstreams: 1 arquivototal.pdf: 6673725 bytes, checksum: 5a6f8ff251599fe900848838a3d9ced8 (MD5) / Made available in DSpace on 2017-09-20T13:22:58Z (GMT). No. of bitstreams: 1 arquivototal.pdf: 6673725 bytes, checksum: 5a6f8ff251599fe900848838a3d9ced8 (MD5) Previous issue date: 2017-04-07 / This study has the purpose presenting the result of a research on unconventional segmentations of words performed with children of the second year of elementary school. Because it is a work developed with children in the process of literacy and thinking about the contribution to a more significant study, we decided to use parlendas, as well as working through children's popular games, it greatly facilitates the study of nonconventional segmentation: hyper segmentation and hypo segmentation because parlendas are attractive texts and have small verses, easy to memorize. We observed that, in the literacy process, students have a lot of difficulty in segmenting words, and therefore end up joining or separating words differently from the ones proposed by the standard, precisely because they transpose the knowledge of orality into writing without any or few teacher's intervention. The separation between the words of a sentence can cause doubts in students who are beginning to have contact with the written language, therefore, are difficulties that once unresolved in the base, in the initial years, can be dragged into the later school years. We understand, based on Kleiman (1996); Soares (2009); Ferreiro (1999; 2011); PCN (1997), that exploits the reading and writing through playful activities, directed to the initial years, helps the students' learning, since it allows the adequate contact with the textual diversity since the first steps in the work with writing. And, in fact, we could verify that of the total of 10 children who participated in our practice, 06 understood the formalization of the segmentation in writing after the sequence of activities applied. / Este estudo tem como propósito apresentar o resultado de uma pesquisa sobre segmentações não convencionais de palavras realizadas com crianças do 2º ano do ensino fundamental. Por ser um trabalho desenvolvido com crianças no processo de alfabetização e pensando em contribuir com um estudo mais significativo, resolvemos utilizar o gênero parlenda, pois além de trabalhar a linguagem através das brincadeiras populares infantis, facilita bastante o estudo da segmentação não convencional: hipersegmentação e hipossegmentação, já que as parlendas são textos atrativos e que possuem versos pequenos, fáceis de memorizar. Observamos que, no processo de alfabetização, os alunos apresentam muita dificuldade de segmentação de palavras, e, por isso, terminam juntando ou separando as palavras de forma distinta do proposto pelo padrão, justamente porque transpõem os conhecimentos da oralidade para escrita sem nenhuma ou pouca intervenção do professor. A separação entre as palavras de uma frase pode causar dúvidas nos alunos que estão começando a ter contato com a língua escrita, portanto, são dificuldades que uma vez não solucionadas na base, nos anos iniciais, poderão ser arrastadas para as os anos escolares posteriores. Entendemos, com base em Kleiman (1996); Soares (2009); Ferreiro (1999; 2011); PCN (1997), que explorar a leitura e a prática da escrita por meio de atividades lúdicas, voltadas aos anos iniciais, auxilia a aprendizagem dos alunos, uma vez que possibilita o adequado contato com a diversidade textual desde os primeiros passos no trabalho com a escrita. E, de fato, pudemos comprovar que do total de 10 crianças que participaram da nossa prática, 06 conseguiram compreender melhor a formalização da segmentação na escrita após a sequência de atividades aplicadas em sala.

This thesis proposes a probabilistic level set method to be used in segmentation of tumors with heterogeneous intensities. It models the intensities of the tumor and surrounding tissue using Gaussian mixture models. Through a contour based initialization procedure samples are gathered to be used in expectation maximization of the mixture model parameters. The proposed method is compared against a threshold-based segmentation method using MRI images retrieved from The Cancer Imaging Archive. The cases are manually segmented and an automated testing procedure is used to find optimal parameters for the proposed method and then it is tested against the threshold-based method. Segmentation times, dice coefficients, and volume errors are compared. The evaluation reveals that the proposed method has a comparable mean segmentation time to the threshold-based method, and performs faster in cases where the volume error does not exceed 40%. The mean dice coefficient and volume error are also improved while achieving lower deviation.

Nous présentons dans cette thèse un nouveau modèle statistique de forme et l'utilisons pour la segmentation d'images avec a priori. Ce modèle est représenté par un champ de Markov. Les noeuds du graphe correspondent aux points de contrôle situés sur le contour de la forme géométrique, et les arêtes du graphe représentent les dépendances entre les points de contrôle. La structure du champ de Markov est déterminée à partir d'un ensemble de formes, en utilisant des techniques d'apprentissage de variétés et de groupement non-supervisé. Les contraintes entre les points sont assurées par l'estimation des fonctions de densité de probabilité des longueurs de cordes normalisées. Dans une deuxième étape, nous construisons un algorithme de segmentation qui intègre le modèle statistique de forme, et qui le relie à l'image grâce à un terme région, à travers l'utilisation de diagrammes de Voronoi. Dans cette approche, un contour de forme déformable évolue vers l'objet à segmenter. Nous formulons aussi un algorithme de segmentation basé sur des détecteurs de points d'intérêt, où le terme de régularisation est lié à l'apriori de forme. Dans ce cas, on cherche à faire correspondre le modèle aux meilleurs points candidats extraits de l'image par le détecteur. L'optimisation pour les deux algorithmes est faite en utilisant des méthodes récentes et efficaces. Nous validons notre approche à travers plusieurs jeux de données en 2D et en 3D, pour des applications de vision par ordinateur ainsi que l'analyse d'images médicales. / In this thesis, we introduce a new statistical shape model and use it for knowledge-based image segmentation. The model is represented by a Markov Random Field (MRF). The vertices of the graph correspond to landmarks lying on the shape boundary, whereas the edges of the graph encode the dependencies between the landmarks. The MRF structure is determined from a training set of shapes using manifold learning and unsupervised clustering techniques. The inter-point constraints are enforced using the learnedprobability distribution function of the normalized chord lengths.This model is used as a basis for knowledge-based segmentation. We adopt two approaches to incorporate the data support: one is based on landmark correspondences and the other one uses image region information. In the first case, correspondences between the model and the image are obtained through detectors and the optimal configuration is achieved through combination of detector responses and prior knowledge. The second approach consists of minimizing an energy that discriminates the object from the background while accounting for the shape prior. A Voronoi decomposition is used to express this objective function in a distributed manner using the landmarks of the model. Both algorithms are optimized using state-of-the art eficient optimization methods. We validate our approach on various 2D and 3D datasets of images, for computer vision applications as well as medical image analysis.

Les séquences de maillages sont de plus en plus utilisées. Cette augmentation des besoins entraîne un développement des méthodes de génération de séquences de maillages. Ces méthodes de générations peuvent produire des séquences de maillages de natures différentes. Le nombre d’applications utilisant ces séquences s’est également accru, avec par exemple la compression et le transfert de pose. Ces applications nécessitent souvent de calculer une partition de la séquence. Dans cette thèse, nous nous intéressons plus particulièrement à la segmentation en composantes rigides de séquences de maillages. Dans un premier temps, nous formalisons la notion de séquence de maillages et proposons donc une classification permettant de désigner quelles sont les propriétés attachées à un type de séquence, et ainsi de décrire précisément quel type de séquence est nécessaire pour une application donnée. Dans un second temps, nous formalisons la notion de segmentation de séquence de maillages, et présentons également l’état de l’art des méthodes de segmentation sur les séquences de maillages. Ensuite, nous proposons une première méthode de type globale pour les séquences stables de maillages, fondée sur la fusion de régions. Par la suite, nous présentons deux autres méthodes, reposant sur la classification spectrale. La première, produit un ensemble de segmentations globales, tandis que la seconde génère une segmentation globale ou une segmentation temporellement variable. Nous mettons également en place un système d’évaluation quantitative des segmentations. Enfin, nous présentons les différentes perspectives liées à la segmentation. / Mesh sequences are becoming a common tool in computer graphics as can be seen in video games or medical imaging. As a consequence, mesh sequences generation’s methods have been developed. Sequences can be created using a modeler or by multicameras acquisition. These methods can generate sequences which have different properties. Moreover, different applications using mesh sequences have been proposed such as compression or pose transfer. Most of these applications require to compute a segmentation as a pre-processing step. This thesis deals with mesh sequence segmentation into rigid components. First, we formalize the notion of mesh sequence, and propose a nomenclature, allowing us to design the properties attached to each kind of mesh sequence, and to describe precisely what kind of sequence an algorithm requires as input. Next, we propose a formalization of mesh sequence segmentation by providing different definitions of segmentation.We then present mesh sequences segmentation state of the art. We then propose a first segmentation method, producing a global segmentationand taking as input a stable mesh sequence. This method is based on a region-growing process. Next, we present two segmentation methods, both based on spectral clustering and taking as input an unconstrained mesh sequence. The former method produces a set of global segmentations, while the latter generate either a global segmentation or a timevarying segmentation. We also propose a quantitative segmentation evaluation system. Finally, we provide future work leads on mesh sequence segmentation.

Os sarcomas ósseos representam uma proporção significativa de tumores na faixa etária pediátrica, ainda apresentando um quadro desafiador devido a sua significativa taxa de morbimortalidade. Pesquisas para o desenvolvimento de novas modalidades terapêuticas e para o desenvolvimento de métodos que identifiquem características da doença que possam permitir melhor estratificação dos pacientes através de dados clinicamente relevantes para individualizar as condutas clínicas são necessárias. Dentro deste contexto surge o conceito de radiômica, que visa extrair dados clinicamente relevantes a partir de imagens médicas. Entretanto, para colocar a radiômica em prática, é necessário selecionar, nas imagens médicas, as áreas de interesse referentes às patologias estudadas, e este processo se denomina segmentação. O objetivo primário deste estudo foi avaliar a reprodutibilidade intra e inter-observador da segmentação manual de sarcomas ósseos em imagens de ressonância magnética (RM). Como objetivo secundário, foi avaliada a capacidade da segmentação semiautomática em reduzir o tempo necessário para segmentação, mantendo similaridade com a segmentação manual. O estudo foi realizado de forma retrospectiva com inclusão de pacientes com diagnóstico de osteossarcoma ou sarcoma de Ewing confirmado por estudo histopatológico e que tivessem imagens de RM realizadas no Hospital Universitário de nossa Instituição realizadas previamente a qualquer intervenção terapêutica. Três médicos radiologistas, de forma independente e às cegas em relação as demais segmentações e em relação ao resultado histopatológico, realizaram a segmentação manual dos contornos destes tumores utilizando o software 3DSlicer, permitindo que fosse realizada avaliação da reprodutibilidade interobservador. Um dos radiologistas realizou uma segunda segmentação manual dos mesmos casos, possibilitando a avaliação da reprodutibilidade intraobservador, e, ainda, uma terceira segmentação foi realizada, utilizando metodologia semiautomática, disponível no software mencionado. Para a análise estatística, foi utilizado o coeficiente de similaridade de Dice (DICE), a distância Hausdorff (DH), comparações de volumes e análises dos intervalos de tempo necessários para realização das segmentações. Os parâmetros avaliados demonstraram haver boa reprodutibilidade intraobservador, com DICE variando entre 0,83 a 0,97; e distância Hausdorff variando entre 3,37 a 28,73 mm. Também foi demonstrada boa reprodutibilidade interobservador com DICE variando entre 0,73 a 0,97; e distância Hausdorff variando entre 3,93 a 33,40 mm. A segmentação semiautomática demonstrou boa similaridade em relação à segmentação manual (DICE variando entre 0,71 a 0,96 e DH variando entre 5,38 a 31,54 mm), havendo redução significativa do tempo necessário para segmentação. Entre todas as situações comparadas, os volumes não apresentaram diferenças estatisticamente significativas (p-valor>0,05). / Bone sarcomas represent a significant proportion of tumors in the pediatric age group and they still are a challenge due to their significant morbidity and mortality rates. Reseaches are important for the development of new therapeutic modalities and for the development of methods that identify features that allow better stratification of the patients with theses diseases for individualization of their treatments. In this context emerges the concept of radiomics, which is the process of extraction of clinically relevant data from medical images. It is important to segment the areas of interest im medical images for the pratice of this process. The primary objective of this study was to evaluate the intra- and interobserver reproducibility of manual segmentation of bone sarcomas on magnetic resonance imaging (MRI). As a secondary objective, it was evaluated if the semiautomatic segmentation could be similar to manual segmentation and if the semiautomatic method could reduce the time required for segmentation. The study was performed retrospectively with the inclusion of patients with osteosarcoma or Ewing sarcoma confirmed by histopathological study and who had MRI performed at the University Hospital of our Institution prior to any therapeutic intervention. Three radiologists, independently and blindly in relation to the other segmentations and in relation to the histopathological results, performed the manual segmentation of the contours of these tumors using 3DSlicer software, allowing an interobserver reproducibility evaluation. One of the radiologists performed a second manual segmentation of the same cases, allowing the evaluation of intraobserver reproducibility. A third segmentation was performed, using semi-automatic methodology, available in the mentioned software. For the statistical analysis, Dice similarity coefficient (DICE), Hausdorff distance (DH), comparisons between volumes and time intervals for segmentations were used. The parameters evaluated demonstrated a good intraobserver reproducibility, with DICE ranging from 0.83 to 0.97 and Hausdorff distance ranging from 3.37 to 28.73 mm. Good interobserver reproducibility was also demonstrated with DICE ranging from 0.73 to 0.97 and Hausdorff distance ranging from 3.93 to 33.40 mm. Semiautomatic segmentation demonstrated good similarity to manual segmentation (DICE ranging from 0.71 to 0.96 and HD ranging from 5.38 to 31.54mm), and there was significant reduction in the time required for segmentation. Among all the situations compared, the volumes did not present significant statistical differences (p-value> 0.05).

Orientadores: Alexandre Campane Vidal, Alexandre Xavier Falcão / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Mecânica e Instituto de Geociências / Made available in DSpace on 2018-08-22T17:02:26Z (GMT). No. of bitstreams: 1 MingireanovFilho_Ivan_M.pdf: 33856245 bytes, checksum: 516137beeec348cf169f06272d16b0cb (MD5) Previous issue date: 2013 / Resumo: A caracterização de reservatórios é fundamental na construção do modelo geológico para a produção do campo. O melhoramento de técnicas matemáticas, que auxiliam a interpretação geológica, influencia diretamente o plano de desenvolvimento e gerenciamento dos poços. Nesse sentido, este trabalho utiliza uma aplicação inédita na caracterização de reservatórios da técnica de Transformada Imagem Floresta (Image Foresting Transform - IFT) em segmentação de imagens de rocha para a análise petrofísica. A técnica interpreta a imagem como um grafo, onde os pixels são os nós e os arcos são definidos por uma relação de adjacência entre os pixels. O custo de um caminho no grafo é determinado por uma função que depende das propriedades locais da imagem. As raízes da floresta surgem de um conjunto de pixels escolhidos como sementes e a IFT atribui um caminho de custo mínimo das sementes a cada pixel da imagem para gerar uma Floresta de Caminhos Ótimos (Optimum-Path Forest - OPF). Com isso, nas imagens de lâminas de arenito, os grãos são segmentados em relação ao poro e os grãos em contato são separados entre si. Com os resultados obtidos é possível o estudo da morfologia dos grãos e porosidade da amostra. O método consiste de dois processos principais, um totalmente automático para segmentar a imagem e outro que utiliza uma interface gráfica para permitir correções dos erros de classificação gerados pelo processo automático. A acurácia é medida comparando a imagem corrigida por interação do usuário com a segmentada automaticamente. Outra aplicação inédita apresentada no trabalho é a utilização do classificador supervisionado baseado em OPF para a classificação de dados de perfilagem geofísica do campo de Namorado / Abstract: The reservoir characterization is fundamental in the construction process of geological model for field production. The improvement of mathematical techniques that assist the geological interpretation, has a directly influence in the development plan and management of the wells. Accordingly, this study uses a novel application in reservoir characterization, Image Foresting Forest (IFT) technique to image segmentation of rock for petrophysical analysis. The IFT interprets an image as a graph, whose nodes are the image pixels, the arcs are defined by an adjacency relation between pixels, and the paths are valued by a connectivity function. The roots of forest are a set of pixels selected as seeds and the IFT assigns a minimum path-cost to each image pixel generation an Optimum-Path Forest (OPF). The result is a segmentation of grains from pore in sandstone thin section images and the separation of the touching grains automatically. This allows the study of grain morphology and sample porosity. The method consists of two major processes: first, a totally automatic image segmentation and second and user interaction to correct misclassified grains. The accuracy is computed comparing the corrected image by the user with the image segmented automatically. Another novel application presented in the work is the use of supervised classification based on OPF for classification of geophysical logging data from Campo de Namorado / Mestrado / Reservatórios e Gestão / Mestre em Ciências e Engenharia de Petróleo

L’arthrose est un véritable problème de santé publique. Plus de dix millions de personnes sont atteintes en France et 35 millions aux États-Unis. L’arthrose du genou représente 35% du nombre total d’arthrose avec plus de 1,3 million de patients en Europe. Il existe de nos jours plusieurs solutions permettant de traiter l’arthrose du genou, suivant le caractère dégénératif de la maladie, allant du traitement chirurgical conservateur, tel que l’ostéotomie supérieure du tibia, jusqu’au traitement chirurgical prothétique, tel que l’arthroplastie totale du genou. Le succès à long terme de ces interventions repose (1) sur le contrôle de l’alignement du membre inférieur au cours de l’intervention, réalisé par l’intermédiaire de l’angle HKA entre les centres hanche, genou et cheville, et (2) sur une planification chirurgicale permettant de préparer l’intervention, et notamment, définir la position optimale des coupes osseuses pour la mise en place d’une prothèse à partir de modèles 3D de l’os du patient issus d’images tomodensitométriques (TDM) ou IRM. Nous nous sommes intéressés, dans un premier temps, à l’étude et l’évaluation, dans un contexte clinique, de la précision et la robustesse des techniques utilisées en chirurgie assistée par ordinateur pour la localisation du centre hanche, nécessaire au calcul de l’angle HKA. Nous avons ainsi proposé une nouvelle méthode, mini-invasive, et particulièrement adaptée pour l’ostéotomie supérieure du tibia. Nous nous sommes ensuite intéressés aux méthodes de segmentation permettant d’extraire la surface osseuse du genou à partir d’IRM pour la phase de planification. Nous avons également proposé une nouvelle approche, automatique, qui se base sur des modèles actifs de forme ou Active Shape Model (ASM). Compte tenu des résultats très encourageants, l’intégration de nos contributions en routine clinique pourrait, potentiellement, améliorer le service médical rendu pour le traitement de l’arthrose du genou. / Osteoarthritis is a real public health problem. More than ten million people are affected by osteoarthritis in France and 35 million in the United States. Knee Osteoarthritis represents 35% of the total number of osteoarthritis with more than 1.3 million patients in Europe. Today, there are several solutions to treat knee osteoarthritis depending on the degenerative nature of the disease : from conservative surgical treatment, such as High tibia Osteotomy (HTO), to prosthetic surgical treatment, such as Total Knee arthroplasty (TKA). The long-term success of these interventions is (1) the control of the lower limb alignment, during the intervention, which can be obtained by measuring the HKA angle between the hip, the knee and the ankle centers, and (2) the surgical planning allowing the preparation of the intervention, and for instance, the definition of the optimal cuts for the placement of a knee prosthesis based on the 3D model of the patient bone obtained from computerized tomography (CT) or MRI. We were interested, first, in the study and evaluation, in a clinical context, of the accuracy and precision of the methods used in computer-assisted orthopedic surgery for the localization of the hip center. We have thus proposed a new minimally invasive method especially adapted to HTO. We were interested, then, to the segmentation methods allowing the extraction of the knee bony surface from MRI for the surgical planning. We have also proposed a new automatic approach based on active shape models (ASM). Given the very encouraging results, the integration of our contributions in the clinical routine could, potentially, improve the medical benefits for the treatment of knee osteoarthritis.