Search

The 3D reconstruction of an accurate face model is essential for delivering reliable feedback for clinical decision support. Medical imaging and specific depth sensors are accurate but not suitable for an easy-to-use and portable tool. The recent development of deep learning (DL) models opens new challenges for 3D shape reconstruction from a single image. However, the 3D face shape reconstruction of facial palsy patients is still a challenge, and this has not been investigated. The contribution of the present study is to apply these state-of-the-art methods to reconstruct the 3D face shape models of facial palsy patients in natural and mimic postures from one single image. Three different methods (3D Basel Morphable model and two 3D Deep Pre-trained models) were applied to the dataset of two healthy subjects and two facial palsy patients. The reconstructed outcomes were compared to the 3D shapes reconstructed using Kinect-driven and MRI-based information. As a result, the best mean error of the reconstructed face according to the Kinect-driven reconstructed shape is 1.5±1.1mm. The best error range is 1.9±1.4mm when compared to the MRI-based shapes. Before using the procedure to reconstruct the 3D faces of patients with facial palsy or other facial disorders, several ideas for increasing the accuracy of the reconstruction can be discussed based on the results. This present study opens new avenues for the fast reconstruction of the 3D face shapes of facial palsy patients from a single image. As perspectives, the best DL method will be implemented into our computer-aided decision support system for facial disorders.

Facial expression recognition plays an essential role in human conversation and human-computer interaction. Previous research studies have recognized facial expressions mainly based on 2D image processing requiring sensitive feature engineering and conventional machine learning approaches. The purpose of the present study was to recognize facial expressions by applying a new class of deep learning called geometric deep learning directly on 3D point cloud data. Two databases (Bosphorus and SIAT-3DFE) were used. The Bosphorus database includes sixty-five subjects with seven basic expressions (i.e., anger, disgust, fearness, happiness, sadness, surprise, and neutral). The SIAT-3DFE database has 150 subjects and 4 basic facial expressions (neutral, happiness, sadness, and surprise). First, preprocessing procedures such as face center cropping, data augmentation, and point cloud denoising were applied on 3D face scans. Then, a geometric deep learning model called PointNet++ was applied. A hyperparameter tuning process was performed to find the optimal model parameters. Finally, the developed model was evaluated using the recognition rate and confusion matrix. The facial expression recognition accuracy on the Bosphorus database was 69.01% for 7 expressions and could reach 85.85% when recognizing five specific expressions (anger, disgust, happiness, surprise, and neutral). The recognition rate was 78.70% with the SIAT-3DFE database. The present study suggested that 3D point cloud could be directly processed for facial expression recognition by using geometric deep learning approach. In perspectives, the developed model will be applied for facial palsy patients to guide and optimize the functional rehabilitation program.

International audience; Simulating deformations of soft tissues is a complex engineering task, and it is even more difficult when facing the constraint between computation speed and system accuracy. However, literature lacks of a holistic review of all necessary aspects (computational approaches, interaction devices, system architectures, and clinical validations) for developing an effective system of soft-tissue simulations. This paper summarizes and analyses recent achievements of resolving these issues to estimate general trends and weakness for future developments. A systematic review process was conducted using the PRISMA protocol with three reliable scientific search engines (ScienceDirect, PubMed, and IEEE). Fifty-five relevant papers were finally selected and included into the review process, and a quality assessment procedure was also performed on them. The computational approaches were categorized into mesh, meshfree, and hybrid approaches. The interaction devices concerned about combination between virtual surgical instruments and force-feedback devices, 3D scanners, biomechanical sensors, human interface devices, 3D viewers, and 2D/3D optical cameras. System architectures were analysed based on the concepts of system execution schemes and system frameworks. In particular, system execution schemes included distribution-based, multithread-based, and multimodel-based executions. System frameworks are grouped into the input and output interaction frameworks, the graphic interaction frameworks, the modelling frameworks, and the hybrid frameworks. Clinical validation procedures are ordered as three levels: geometrical validation, model behavior validation, and user acceptability/safety validation. The present review paper provides useful information to characterize how real-time medical simulation systems with soft-tissue deformations have been developed. By clearly analysing advantages and drawbacks in each system development aspect, this review can be used as a reference guideline for developing systems of soft-tissue simulations.

International audience; Background and Objective: Head and facial mimic animations play important roles in various fields such as human-machine interactions, internet communications, multimedia applications, and facial mimic analysis. Numerous studies have been trying to simulate these animations. However, they hardly achieved all requirements of full rigid head and non-rigid facial mimic animations in a subject-specific manner with real-time framerates. Consequently, this present study aimed to develop a real-time computer vision system for tracking simultaneously rigid head and non-rigid facial mimic movements. Methods: Our system was developed using the system of systems approach. A data acquisition sub-system was implemented using a contactless Kinect sensor. A subject-specific model generation sub-system was designed to create the geometrical model from the Kinect sensor without texture information. A subject-specific texture generation sub-system was designed for enhancing the reality of the generated model with texture information. A head animation sub-system with graphical user interfaces was also developed. Model accuracy and system performances were analyzed. Results: The comparison with MRI-based model shows a very good accuracy level (distance deviation of similar to 1 mm in neutral position and an error range of [2-3 mm] for different facial mimic positions) for the generated model from our system. Moreover, the system speed can be optimized to reach a high framerate (up to 60 fps) during different head and facial mimic animations. Conclusions: This study presents a novel computer vision system for tracking simultaneously subject-specific rigid head and non-rigid facial mimic movements in real time. In perspectives, serious game technology will be integrated into this system towards a full computer-aided decision support system for facial rehabilitation. (C) 2020 Elsevier B.V. All rights reserved.

Facial muscle coordination is a fundamental mechanism for facial mimics and expressions. The understanding of this complex mechanism leads to better diagnosis and treatment of facial disorders like facial palsy or disfigurement. The objective of this work was to use magnetic resonance imaging (MRI) technique to characterize the activation behavior of facial muscles and then simulate their coordination mechanism using a subject specific finite element model. MRI data of lower head of a healthy subject were acquired in neutral and in the pronunciation of the sound [o] positions. Then, a finite element model was derived directly from acquired MRI images in neutral position. Transversely-isotropic, hyperelastic, quasi-incompressible behavior law was implemented for modeling facial muscles. The simulation to produce the pronunciation of the sound [o] was performed by the cumulative coordination between three pairs of facial mimic muscles (Zygomaticus Major (ZM), Levator Labii Superioris (LLS), Levator Anguli Oris (LAO)). Mean displacement amplitude showed a good agreement with a relative deviation of 15% between numerical outcome and MRI-based measurement when all three muscles are involved. This study elucidates, for the first time, the facial muscle coordination using in vivo data leading to improve the model understanding and simulation outcomes.

International audience; In this paper, we tackle the problem of extracting frequent opinions from uncertain databases. We introduce the foundation of an opinion mining approach with the definition of pattern and support measure. The support measure is derived from the commitment definition. A new algorithm called OpMiner that extracts the set of frequent opinions modelled as a mass functions is detailed. Finally, we apply our approach on a real-world biomedical database that stores opinions of experts to evaluate the reliability level of biomedical data. Performance analysis showed a better quality patterns for our proposed model in comparison with literature-based methods.

Finite element simulation of facial mimics provides objective indicators about soft tissue functions for improving diagnosis, treatment and follow-up of facial disorders. There is a lack of in vivo experimental data for model development and validation. In this study, the contribution of the paired Zygomaticus Major (ZM) muscle contraction on the facial mimics was investigated using in vivo experimental data derived from MRI. Maximal relative differences of 7.7% and 37% were noted between MRI-based measurements and numerical outcomes for ZM and skin deformation behaviors respectively. This study opens a new direction to simulate facial mimics with in vivo data.

International audience; The musculoskeletal system is a complex arrangement of muscles, tendons and bones. This system is affected by many factors, and presents unique features for each individual. There is constant risk that the normal behavior of this system might be altered due to transport accidents or aging effects. Usually, physical therapy sessions are practiced at the clinics to recover the patient’s functionalities. Recently, tele-rehabilitation has been investigated to improve the clinical outcomes. In this paper, we introduced a novel tele-rehabilitation solution based on serious gaming technologies. Different components of the system were designed and described. Two serious game scenarios were created. A multi-sensor fusion approach was developed to improve the kinematic accuracy of the rehabilitation movement. A preliminary evaluation showed great potential for our system to be applied in a home-based rehabilitation setting.

International audience; Serious games have been established as a complementary tool for conventional rehabilitation. This trend proved to be beneficial for both experts and patients since the first are able to assign and monitor virtual reality games for their patients to be executed at home, and the latter are greatly motivated by the challenges of these games rather than the repeatable and boring rehabilitation movements. In a previous work, we proposed a serious game for lower limb rehabilitation of the musculoskeletal system using the Microsoft KinectTM camera and a virtual environment. However, this system suffers from inaccurate kinematic measurement due to various external sources. Therefore, this paper explores various kinematic measurement technics to improve the accuracy of our system. Six real time orientation measurement algorithms were assessed and compared, using multiple types of sensors. The results obtained showed a better performance for our system. In fact, this study reinforced a clearer view on a low cost, real time portable system to be implemented at home.

International audience; Trois positions (l'étirement des commissures « Sourire », la protrusion labiale sur le son « POU » et « O ») décrivant des mouvements spécifiques de la face lors de la mimique faciale ont été acquises via l'IRM permettant la modélisation personnalisée du comportement mécanique du grand zygomatique, zygomaticus major GZ (un des muscles peauciers). Une loi de comportement (LDC) isotrope transverse, hyperélastique, incompressible permettant de décrire les comportements passifs et actifs du muscle a été utilisée. Les résultats de simulations ont été comparés qualitativement puis quantitativement aux images IRM traitées. Les déplacements moyens obtenus via l'IRM du GZ sont de 4±2mm, 4,5±1,4mm et 6±3mm pour les positions « Sourire », « POU » et « O » respectivement. Les déplacements moyens obtenus via les simulations numériques du GZ sont de 1,9±0,8mm, 2±1mm et 2,8±1,1mm pour les positions « Sourire », « POU » et « O » respectivement. Sur le plan quantitatif, les déplacements obtenus numériquement sont sous estimés d'environ d'un facteur 2, sur le plan qualitatif le meilleur résultat est obtenu avec la position « Sourire ». On notera seule la contribution d'un muscle a été étudiée et que la contraction de ce muscle est en grande partie responsable de l'expression du « Sourire ». Cette étude préliminaire a permis la mise en place d'une méthodologie de modélisation personnalisée permettant une confrontation entre les données expérimentales et simulées. La prochaine étape consistera à réaliser le modèle complet avec les autres muscles, et les tissus environnants les muscles, à prendre en considération les conditions aux limites du modèle, puis à effectuer l'identification des propriétés mécaniques du GZ in vivo.

Mechanical properties of cortical human bone have been investigated for more than over three decades. The objectives of the present study were 1) to investigate the influence of multiscale structural characteristics of the bone tissue on its mechanical behavior and 2) to perform a micro-macro numerical modelling based on the experimental data. It should be noted that variations of the osteon lamellae elastic properties are higher (40%) at the microstructural level than those found at the macroscopic level (about 15%) for measurements performed in the same anatomical direction. Physico-chemical analyses found that organic components were found to be higher for femurs exhibiting lower mechanical properties. There is a consistency between changes observed at the different levels. These results contribute to a basic understanding of the multiscale mechanical behavior of human cortical bone.

The aim of this research is to study facials mimics movements and to correlate externat soft tissue (i.e., cutaneous) movement during facial mimics with internal (i.e., facial mimic muscle) movement. The entire facial mimicry couldn't be studied, that's why relevant movements had been selected. Those movements were characterised by a clinically qualitative analysis in 23 young healthy volunteers. The analysis was performed with video recordings including scaling derived from the FACS (Facial Action Coding System). After the validation of external characterisation by this method, internal characterisation of the mimic facial muscle was carried out in 10 volunteers. A modelization of selected facial mimic muscle as Zygomaticus Major was achieved. With this work, morphological parameters could be extracted, 3D morphometric data were analysed to provide a better understanding of cinematic behaviour of muscle in different positions.This research is included in the Simovi Project, which aims to determine to what extent a facial mimic can be evaluated objectively, to select the qualitative and quantitative indicators for evaluation of mimic facial disorders, and to transfer our technological developments in clinical field. This research is a first step and provides data for simulation or developments of measurement tools in evaluation and follow-up of mimic facial disorders., Ce travail de thèse, inclus dans un projet structurant plus vaste, projet SIMOVI (SImulation des MOuvements du VIsage), s’attache à étudier spécifiquement la mimique faciale en corrélant les déplacements visibles du revêtement cutané et les mouvements musculaires internes à travers le développement de plusieurs méthodologies. L’ensemble de la mimique faciale ne pouvant être étudié, étant donné la multitude d’expressions, les mouvements pertinents à étudier dans nos travaux ont été identifiés. Ces mouvements ont été caractérisés chez 23 sujets jeunes dans une analyse descriptive qualitative et clinique, basée sur une méthodologie s’appuyant sur l’analyse d’enregistrements vidéoscopiques, et le développement d’un codage issu du FACS (Facial Action Coding System). Une cohorte de référence a ainsi été constituée. Après avoir validé notre méthodologie pour la caractérisation externe de la mimique, l’analyse des muscles peauciers par l’IRM a été réalisée sur 10 hémifaces parmi les sujets sains issus de la cohorte. Cette caractérisation a fait appel, à partir d’une anatomie in vivo, à une modélisation de certains muscles peauciers (zygomaticus major en particulier) afin d’extraire des paramètres morphologiques, de réaliser une analyse plus fine de la morphologie musculaire en 3 dimensions, et d’apporter une meilleure compréhension du comportement cinématique du muscle dans différentes positions. Par son intégration dans un questionnement plus vaste :- comment caractériser objectivement la mimique faciale ? - quels sont les indicateurs qualitatifs et quantitatifs de la mimique que nous pouvons recueillir, et comment réaliser ce recueil ? - comment utiliser les développements technologiques dans les applications cliniques ? Ce travail constitue une étape préliminaire à d’autres travaux. Il pourra fournir des données de référence à des fins de modélisation, de simulation de la mimique faciale, ou de développements d’outil de mesures pour le suivi et l’évaluation des déficits de la mimique faciale.

The aim of the project is to investigate the modeling of the reliability/incertitude/imprecision of biomedical and biomechanics data (medical images, kinematics/kinetics/EMG data, etc.) and its propagation in the predictive diagnosls models of the disorders of musculoskeletal systems. These diagnosis models will be based on multimodal and multidimensional patient data (3D medical imaging, mechanical data,dinical data,etc.). The literature-based data have been collected to estabish an uncertainty space, which represents fused data from multiple sources, of morphological, mechanical, and movement analysis properties of the musculoskeletal system from multiple sources (i.e. research papers from Science Direct and Pubmed). After that,a new clustering method (US-ECM) is proposed for integrating fused data from multiple sources ln form of a multidimensional uncertainty space (US). Reliability of biomechanical data was evaluated by a fusion approach expert opinion. Reliability criteria of a data source (ie scientific paper published) focus on the technique used the acquisition protocol and measurement and the number of data. A system of questionnaires was developed to co!lect expert opinion. Then, the theory of beliet functions has been applied to merge these opinion to establish a confidence level each data source.; Les pathologies du système musculosquelettique concernant les déformations / anomalies osseuses et musculaires (e.g. paralysie cérébrale) ont un fort impact sur la qualité de vie des personnes concernées. Les objectifs de la thèse sont d’approfondir les études précédentes en intégrant la modélisation de l’incertitude des données biomécaniques et biomédicales dans les modèles de diagnostic prédictif des pathologies du système musculosquelettique. L’intervalle a été choisi pour représenter l’incertitude des données biomécaniques. Ce formalisme est simple et peu coûteux sur le plan du calcul. Les données (physiologiques, morphologiques, mécaniques et analyse du mouvement) ont été recueillies à partir de la littérature en utilisant les moteurs de recherche des articles scientifiques fiables pour établir un espace d’incertitude. La nouvelle méthode de classement (nommée US-ECM) proposée est une méthode de classement semi-supervisé qui utilise la partition crédale pour représenter les connaissances partielles sur les clusters. L’utilisation de la fonction de croyance pour représenter ces éléments de connaissance permet de les combiner d’une manière souple et robuste. De plus, l’extension de cette méthode avec un espace d’incertitude multidimensionnelle a montré la meilleure performance par rapport à la version originale. L’analyse des avis d’expert permettra d’inclure ou d’exclure les sources de données selon leurs niveaux de fiabilité. Ensuite, le modèle de regroupement (US-ECM) développé sera appliqué sur une nouvelle base de données pour évaluer l’impact de la fiabilité des données sur la performance de diagnostic.

Bone is a dynamical, anisotropic, hierarchical, inhomogeneous and time-dependent biological material. At the micro and nano scales, their mechanical and structural characterizations are still being a challenging topic. Nanoindentation and Atomic Force Microscopy are used to assess the mechanical and morphological characteristics of cortical bones. Time-dependent, elastic and plastic mechanical properties were computed using the nanoindentation method proposed by (Mazeran et al., 2012). Experiments were performed on different species of bones for different conditions. Wistar rat femoral cortical bone was used to assess the evolution of the mechanical properties in a life span model (from growth to senescence). The variation of the mechanical properties with age was evidenced and their correlation with physico-chemical properties was established. Then, prediction equations were proposed to describe these behaviours. From these equations, it is possible to estimate an apparent maturation age for each mechanical property. Our findings suggest maturation age is earlier and growth rate are higher for elastic properties than for time-dependent mechanical properties. Time-dependent mechanical behaviour of Human femoral cortical bones were assessed considering its heterogeneity. Haversian systems with different apparent mineral content were identified by means of their apparent grey levels obtained from ESEM images. Results prove the mechanical heterogeneity of the Haversian systems and highlight the influence of the time-dependent mechanical properties in the anisotropic behaviour of bone. Bovine femoral cortical bone was used to quantify the mechanical and morphological effects of the demineralization process. Bone seems to have a quasi-isotropic mechanical behaviour after mineral loss. AFM images of the remaining organic components show that collagen fibrils are oriented in a possible privileged direction. According to our knowledge, few investigations have been performed simultaneously on mechanical, morphological and physico-chemical properties of bone. All these results provide a better understanding of the interactions of the collagen-mineral matrix, bone remodelling and their influence especially in the time-dependent mechanical response. Data reported in this work could be useful to develop and to improve multi-scale bone models and multi-scale constitutive laws for cortical bone., Dans ce travail, la nanoindentation et la Microscopie à Force Atomique ont été utilisées pour déterminer les caractéristiques mécaniques et morphologiques de l'os cortical aux échelles micro et nanoscopique. Les propriétés mécaniques qui dépendent du temps, élastique et plastique ont été quantifiées par nanoindentation en utilisant une méthode spécifique. Les essais ont été réalisés sur trois différentes espèces d'os cortical. Dans un premier temps, l'os du rat fut utilisé pour quantifier l"évolution des propriétés mécaniques de la croissance à la sénescence. La variation des propriétés mécaniques avec l'âge fut démontrée et sa corrélation avec les propriétés physico-chimiques établie. Les équations de prédiction ont été proposées afin de décrire le comportement mécanique puis pour quantifier un âge de maturation apparent pour chaque propriété. Dans un deuxième temps, le comportement mécanique qui dépend du temps a été examiné sur l'os humain. Les systèmes Haversiens avec différents contenus du minéral furent identifiés à partir d'images ESEM. Les résultats démontrent l'hétérogénéité mécanique des systèmes Haversiens et l'influence des propriétés mécaniques qui dépendent du temps sur l'anisotropie de l'os. Enfin, l'os bovin fut utilisé pour quantifier les effets mécaniques et morphologiques du processus de déminéralisation. Le résidu organique de l'os déminéralisé présente un comportement mécanique quasi-isotrope. Les images AFM montrent que les fibres de collagène sont orientées dans une direction privilégiée. Les données obtenues pourront servir à développer des matériaux biomimétiques et à établir des lois de comportement multi-échelles de l'os cortical.

This work concerned the first carpo-metacarpal joint. The first part of this work was the study of the morphogenesis of the palmar arch using three-dimensional geometrie modeling. Five embryos were used for this study. The results of this study support the hypothesis that opposition and asymmetry of the thumb appears early in embryological development. In the second part, with specifie MRI protocol on 5 normal subjects, the objective was to quantify the 3D motion of the trapezo-metacarpal joint using helical axes theory. In the last part, using the same protocol on pathological subjects (CT scan images), the objective was to evaluate the effect of different type of treatment of the first carpo­ metacarpal arthritis.The results of the work are of interest for the quantitative evaluation of pathological trapezo-metacarpal joint and in the development of prosthesis., Ce travail de thèse concerne l'articulation trapézométacarpienne. La première partie du travail a concerné l'étude de la morphogénèse de l'arche palmaire par modélisation géométrique 3D. Cinq embryons ont été utilisés. Les résultats de cette étude montre le caractère asymétrique et l'opposition précoce du pouce chez l'embryon humain. La deuxième partie a consisté à partir d'un protocole IRM spécifique sur 5 sujets sains à déterminer la cinématique 3D de l'articulation trapézo-métacarpienne en utilisant les axes hélicoïdaux. La troisième partie, suivant le même protocole sur sujets pathologiques à partir d'image scanner a permis d'évaluer l'effet des différents types de traitement en cas de rhizarthrose. Les résultats trouvent leur application dans l'évaluation quantitative des pathologies de l'articulation trapézo-métacarpienne ainsi que dans le développement des prothèses.

Understanding of the mechanical behavior of the human body is a challenge to take appropriate medical decisions (e.g. the patient's diagnosis or treatment). To solve this problem, rst, a dynamic model of the musculoskeletal system of the lower limbs has been developed. A sensitivity analysis of the anthropometrical and geometrical parameters of the bones and muscles was performed with literature data. The computational results showed strong variations of kinematics and kinetics parameters function of the selected input data. All these ndings suggest the development of patient specic musculoskeletal models using medical imaging technique for individualized geometrical parameters of the subjects. As clinical application, two personalized models were developed (a healthy subject with normal gait and a subject with gait disorders (Polio pathology)). This study showed the importance of personalized modeling to evaluate and design the Polio lower limb orthoses. The limitations and perspectives of the biomechanical models were presented in real clinical context. Second, a new class of model was proposed as meta-model (Computer-Aided Decision System) combining knowledge-based engineering methods to diagnose and guide the clinical treatment of the disorders of the musculoskeletal system of the lower limbs. The ontology, the data mining, the belief theory and the articial intelligence were applied to develop our meta-model. The crossing of these methods allowed us to develop a generic, exible and extensible system. Three clinical applications (rotational anomalies, clubfeet deformities, and cerebral palsy) were studied in the rst version of our system. The results showed that our system is able to provide aids to clinicians in their medical decisions (e.g. a diagnosis or a treatment). Finally, the methodological confrontation of these two modeling approaches was carried out to highlight the strengths and also the weaknesses of each modeling approach.; La compréhension du fonctionnement du corps humain est un challenge de recherche an de prendre une décision médicale (le diagnostic, le traitement) adéquate dans le cas des pathologies liées au syst ème musculosquelettique. Pour faire face à cette problématique, dans un premier temps, un modèle biomécanique a été développé décrivant la dynamique du mouvement avec prise en considération des caractéristiques géométriques (os et muscles) et mécaniques du système musculo-squelettique. Une étude de sensibilité de ces paramètres géométriques à partir des données de la littérature a montré l'importance de la personnalisation des ces paramètres. En application, un cas d'étude clinique d'un sujet présentant une pathologie (Heine-Medin (polio)) a été étudié. Deux modèles personnalisés (un sujet sain et un sujet pathologique) ont été réalisés. Les résultats obtenus ont montré l'intérêt d'une modélisation personnalisée pour évaluer et concevoir des orthèses personnalisés. Dans un deuxième temps, nous avons proposé une nouvelle classe de modèle - un méta modèle (Système d'Aide à la Décision) - intégrant des résultats du domaine de l'ingénierie des connaissances pour prédire, diagnostiquer, classer et proposer un traitement des pathologies du système musculo-squelettique des membres inférieurs (anomalies rotationnelles (AR), enfants PC (Paralysie Cérébrale), pied bot). La modélisation de ce méta modèle se base sur les modèles mathématiques prédictifs pour prendre une décision médicale (une prédiction, un diagnostic, ou une classi cation). Le but nal est de dégager un résultat cliniquement applicable. Ce système est générique, exible, et extensible et permet donc l'étude et l'analyse de pathologies diverses du système musculosquelettique des membres inférieurs. Enn, une comparaison de ces deux approches de modélisation a été eectuée an d'évaluer leur complémentarité pour une utilisation clinique.

Understanding of the mechanical behavior of the human body is a challenge to take appropriate medical decisions (e.g. the patient's diagnosis or treatment). To solve this problem, rst, a dynamic model of the musculoskeletal system of the lower limbs has been developed. A sensitivity analysis of the anthropometrical and geometrical parameters of the bones and muscles was performed with literature data. The computational results showed strong variations of kinematics and kinetics parameters function of the selected input data. All these ndings suggest the development of patient specic musculoskeletal models using medical imaging technique for individualized geometrical parameters of the subjects. As clinical application, two personalized models were developed (a healthy subject with normal gait and a subject with gait disorders (Polio pathology)). This study showed the importance of personalized modeling to evaluate and design the Polio lower limb orthoses. The limitations and perspectives of the biomechanical models were presented in real clinical context. Second, a new class of model was proposed as meta-model (Computer-Aided Decision System) combining knowledge-based engineering methods to diagnose and guide the clinical treatment of the disorders of the musculoskeletal system of the lower limbs. The ontology, the data mining, the belief theory and the articial intelligence were applied to develop our meta-model. The crossing of these methods allowed us to develop a generic, exible and extensible system. Three clinical applications (rotational anomalies, clubfeet deformities, and cerebral palsy) were studied in the rst version of our system. The results showed that our system is able to provide aids to clinicians in their medical decisions (e.g. a diagnosis or a treatment). Finally, the methodological confrontation of these two modeling approaches was carried out to highlight the strengths and also the weaknesses of each modeling approach., La compréhension du fonctionnement du corps humain est un challenge de recherche an de prendre une décision médicale (le diagnostic, le traitement) adéquate dans le cas des pathologies liées au syst ème musculosquelettique. Pour faire face à cette problématique, dans un premier temps, un modèle biomécanique a été développé décrivant la dynamique du mouvement avec prise en considération des caractéristiques géométriques (os et muscles) et mécaniques du système musculo-squelettique. Une étude de sensibilité de ces paramètres géométriques à partir des données de la littérature a montré l'importance de la personnalisation des ces paramètres. En application, un cas d'étude clinique d'un sujet présentant une pathologie (Heine-Medin (polio)) a été étudié. Deux modèles personnalisés (un sujet sain et un sujet pathologique) ont été réalisés. Les résultats obtenus ont montré l'intérêt d'une modélisation personnalisée pour évaluer et concevoir des orthèses personnalisés. Dans un deuxième temps, nous avons proposé une nouvelle classe de modèle - un méta modèle (Système d'Aide à la Décision) - intégrant des résultats du domaine de l'ingénierie des connaissances pour prédire, diagnostiquer, classer et proposer un traitement des pathologies du système musculo-squelettique des membres inférieurs (anomalies rotationnelles (AR), enfants PC (Paralysie Cérébrale), pied bot). La modélisation de ce méta modèle se base sur les modèles mathématiques prédictifs pour prendre une décision médicale (une prédiction, un diagnostic, ou une classi cation). Le but nal est de dégager un résultat cliniquement applicable. Ce système est générique, exible, et extensible et permet donc l'étude et l'analyse de pathologies diverses du système musculosquelettique des membres inférieurs. Enn, une comparaison de ces deux approches de modélisation a été eectuée an d'évaluer leur complémentarité pour une utilisation clinique.