Mécanique des tissus mous du visage humain en temps réel basée sur des systèmes masse-ressort et l'apprentissage profond // Real-time Soft Tissue Mechanics of Human Face using Advanced Mass-Spring System Modeling Framework and Deep Learning.
|
ABG-138130
ADUM-73868 |
Thesis topic | |
| 2026-04-10 | Public funding alone (i.e. government, region, European, international organization research grant) |
Centrale Lille Institut
Villeneuve d'Ascq - Les Hauts de France - France
Mécanique des tissus mous du visage humain en temps réel basée sur des systèmes masse-ressort et l'apprentissage profond // Real-time Soft Tissue Mechanics of Human Face using Advanced Mass-Spring System Modeling Framework and Deep Learning.
- Electronics
Mécanique des tissus mous, Simulation en temps réel, Systèmes masse-ressort, Apprentissage profond, Visage Humain
Real-time Soft Tissue Mechanics, Mass-Spring System Modeling, Deep Learning, Predictive Digital Twin, Human Face
Real-time Soft Tissue Mechanics, Mass-Spring System Modeling, Deep Learning, Predictive Digital Twin, Human Face
Topic description
La compréhension de la fonction mécanique des muscles faciaux lors des expressions et mimiques faciales est essentielle pour établir un diagnostic quantifié et définir une stratégie de rééducation fonctionnelle personnalisée chez les patients ayant subi une paralysie faciale ou une transplantation du visage. Des modèles d'éléments finis ont été développés pour étudier l'activation, la contraction et la coordination des muscles faciaux au cours des mouvements de la mimique faciale. Toutefois, la modélisation et la simulation dynamique en temps réel des tissus mous constituent des défis scientifiques majeurs. Le comportement des tissus mous est complexe : non linéaire, hétérogène, anisotrope et soumis à de grandes déformations. La méthode des éléments finis, très coûteuse en temps de calcul, est largement utilisée pour modéliser et simuler le comportement des tissus mous. Cependant, cette méthode reste limitée pour les applications interactives, qui nécessitent un retour rapide du comportement des tissus lors de sollicitations mécaniques.
Ce projet de thèse vise à développer de nouvelles approches de modélisation et de simulation dynamique en temps réel des tissus mous, en s'appuyant sur les systèmes masse-ressort et l'apprentissage profond. Les applications cliniques concernent l'analyse quantifiée et la rééducation fonctionnelle des mimiques faciales.
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Understanding the mechanical function of facial muscles during facial expressions and mimetic movements is essential for establishing a quantitative diagnosis and defining a personalized functional rehabilitation strategy in patients who have undergone facial paralysis or face transplantation. Finite element models have been developed to investigate the activation, contraction, and coordination of facial muscles during facial expressions. However, the real-time dynamic modeling and simulation of soft tissues represent major scientific challenges. Soft tissue behavior is complex: it is nonlinear, heterogeneous, anisotropic, and subject to large deformations. The finite element method, which is computationally expensive, is widely used to model and simulate soft tissue behavior. However, this method remains limited for interactive applications that require fast feedback on tissue response under mechanical loading.
This PhD project aims to develop novel approaches for the real-time dynamic modeling and simulation of soft tissues, based on mass-spring system modeling and deep learning approaches. Targeted clinical applications focus on the quantitative analysis and functional rehabilitation of facial expressions.
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Début de la thèse : 01/10/2026
Ce projet de thèse vise à développer de nouvelles approches de modélisation et de simulation dynamique en temps réel des tissus mous, en s'appuyant sur les systèmes masse-ressort et l'apprentissage profond. Les applications cliniques concernent l'analyse quantifiée et la rééducation fonctionnelle des mimiques faciales.
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Understanding the mechanical function of facial muscles during facial expressions and mimetic movements is essential for establishing a quantitative diagnosis and defining a personalized functional rehabilitation strategy in patients who have undergone facial paralysis or face transplantation. Finite element models have been developed to investigate the activation, contraction, and coordination of facial muscles during facial expressions. However, the real-time dynamic modeling and simulation of soft tissues represent major scientific challenges. Soft tissue behavior is complex: it is nonlinear, heterogeneous, anisotropic, and subject to large deformations. The finite element method, which is computationally expensive, is widely used to model and simulate soft tissue behavior. However, this method remains limited for interactive applications that require fast feedback on tissue response under mechanical loading.
This PhD project aims to develop novel approaches for the real-time dynamic modeling and simulation of soft tissues, based on mass-spring system modeling and deep learning approaches. Targeted clinical applications focus on the quantitative analysis and functional rehabilitation of facial expressions.
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Début de la thèse : 01/10/2026
Funding category
Public funding alone (i.e. government, region, European, international organization research grant)
Funding further details
Concours pour un contrat doctoral
Presentation of host institution and host laboratory
Centrale Lille Institut
Institution awarding doctoral degree
Centrale Lille Institut
Graduate school
632 ENGSYS Sciences de l'ingénierie et des systèmes
Candidate's profile
Master en Bioingénierie, Génie Biomédical, Biomécanique, Mécanique Numérique
Connaissances requises :
• Modélisation et simulation des systèmes mécaniques complexes
• Imagerie médicale
• Apprentissage profond
• Programmation Python, C++
• Analyse et esprit critique, autonomie et esprit d'initiative
• Communication scientifique efficace et capacité à travailler en équipe dans des environnements interdisciplinaires.
Master's degree in Bioengineering, Biomedical Engineering, Biomechanics, or Computational Mechanics The candidate needs have the following experiences and required knowledge: • Modeling and simulation of complex mechanical systems • Medical imaging • Deep learning • Proficiency in programming in Python and C++ • Strong analytical and critical thinking skills, independence and initiative • Effective scientific communication and collaborative teamwork in interdisciplinary environments.
Master's degree in Bioengineering, Biomedical Engineering, Biomechanics, or Computational Mechanics The candidate needs have the following experiences and required knowledge: • Modeling and simulation of complex mechanical systems • Medical imaging • Deep learning • Proficiency in programming in Python and C++ • Strong analytical and critical thinking skills, independence and initiative • Effective scientific communication and collaborative teamwork in interdisciplinary environments.
2026-05-31
Apply
Close
Vous avez déjà un compte ?
Nouvel utilisateur ?
Get ABG’s monthly newsletters including news, job offers, grants & fellowships and a selection of relevant events…
Discover our members
Laboratoire National de Métrologie et d'Essais - LNE
Medicen Paris Region
ANRT
Institut Sup'biotech de Paris
ADEME
Nokia Bell Labs France
Ifremer
Tecknowmetrix
Nantes Université
SUEZ
Aérocentre, Pôle d'excellence régional
ONERA - The French Aerospace Lab
Groupe AFNOR - Association française de normalisation
Généthon
TotalEnergies
Servier
ASNR - Autorité de sûreté nucléaire et de radioprotection - Siège

