Contexte et atouts du poste

The MIMESIS team is at the forefront of innovation, working in the fields of scientific computing, machine learning, medical imaging, and control. We are an interdisciplinary team, that collaborates closely with clinicians to develop new technologies that can help improve healthcare, in particular through computer-assisted interventions. Our core research activities take place in the biomechanical modeling of soft tissue and developing novel numerical methods for real-time computation. Our research results enable the creation of digital twins of organs for personalized planning, augmented reality during surgery, and control in medical robotics.

The MIMESIS team recently joined the MEDITWIN consortium, whose main objective is to enable doctors to simulate the outcome of various treatment scenarios for a patient. MEDITWIN will enable the clinical validation, and possible industrialization, of these innovations so that these technologies can be deployed in a standardized way, and benefit as many people as possible. The best standards of care will be incorporated into virtualized experiences made accessible worldwide, setting a new benchmark for quality in healthcare and providing a decisive learning ground for progress in medical science. The benefits of digital twins will be assessed for medical teams, patients, and the healthcare system, notably in terms of improving the efficiency of care, quality of multidisciplinary decision-making, and effectiveness and safety of medical practices and interventions. More information about the project and Ph.D. topic can be found here .

Mission confiée

Thermal ablation liver therapy is a minimally invasive procedure for the treatment of certain types of tumors in inoperable liver cancer patients. The aim of this therapy is to destroy tumor cells via the local application of excessively high/low temperatures, which are delivered by percutaneously inserted needle probes. Various approaches for thermal ablation exist, all differing in terms of both their practical use and the results they achieve. Microwave ablation, radiofrequency ablation and cryoablation are the three most commonly used ablation approaches. However, to date, it is impossible to determine a priori either the optimal approach or the optimal delivery configuration.

This PhD project aims to estimate patient-specific parameters of various diffusion models using preoperative (and eventually intraoperative) data. This data will essentially be image-based, such as MRI, CT, or ultrasound. Additional information such as patient age, cancer status, or biomarkers will also be investigated. The overall objective is to determine the minimal data set that permits a predictive simulation of the ablation process. This work will be done jointly with another PhD candidate developing models and numerical methods for the digital twin of liver thermal ablation. This will ultimately allow to predict the outcome of ablation therapy in diverse configurations, which could significantly enhance the planning and execution of the procedures, potentially improving treatment outcomes and reducing complications. This digital twin could also provide valuable insights into the behavior effects of ablation procedures in liver tumors, contributing to the broader understanding of liver cancer treatment.

This ambitious project will require close collaboration with other researchers, engineers and clinicians.

Principales activités

The main steps of the research project are:

1. Data collection and image processing: Participate in the data collection protocol and process patient data. Determine what data is needed and what image modality can provide this information.
2. Parametrization: Develop of AI-based medical image characterization methods for parametrizing the ablation therapy computational models, taking into account patient-specific tissue and disease characteristics.
3. Ablation procedures outcome prediction: Use the parametrized ablation therapy digital twin to simulate the two main ablation therapy procedures in various delivery configurations. Use the simulation outputs to predict key clinical outcomes, including the extent of tumor destruction, potential complications, and prognosis.
4. Validation: validate the digital twin and outcome predictions using retrospective clinical data and prospective clinical trials.

Compétences

Technical skills and level required:

• Sound knowledge of numerical analysis and optimization methods
• Sound knowledge of Machine Learning / Deep Learning with Artificial Neural Networks
• Sound knowledge of image processing techniques

Software development skills: Python programming, TensorFlow, Pytorch.

Relational skills: team worker (verbal communication, active listening, motivation, and commitment).

Avantages

• Subsidized meals
• Partial reimbursement of public transport costs
• Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
• Possibility of teleworking (after 6 months of employment) and flexible organization of working hours
• Professional equipment available (videoconferencing, loan of computer equipment, etc.)
• Social, cultural and sports events and activities
• Access to vocational training
• Social security coverage

Rémunération

2200 € gross/month