Description du sujet de thèse

This thesis is part of a multidisciplinary scientific project bringing together physicists, physicians, and biologists. The project, entitled "OPerating Atofluorescence Light In Surgery (OPALIS)", is currently under development within the "Multimodal Instrumentation and Tissue Imaging (IMIT)" team of the health physics department at IJCLab, in collaboration with the engineering department and the neurosurgery service of Lariboisière Hospital in Paris, and the CREATIS laboratory.
Oncological surgery, the most common curative treatment for solid tumors, requires precise identification of tumor boundaries for complete resection. In neurosurgery, this precision is hindered by the infiltrative nature of brain tumors, such as gliomas. Accurate identification of these tumors is crucial to minimize recurrences and preserve vital brain functions. Currently, no real-time imaging tool is available for this identification.

This project aims to develop a multimodal fiber endomicroscope for real-time imaging during surgery. The project will be divided into two tasks:
1. Development of the nonlinear fiber endomicroscope prototype enabling real-time imaging with subcellular resolution. This tool will enable a substitution of post-operative histological imaging with in situ imaging: This step will involve the design, integration, and validation of essential components to ensure real-time intraoperative imaging with high resolution. This task will constitute a significant part of the thesis project.
2. Intelligent classification: The use of artificial intelligence methods will allow automatic analysis of real-time images. These methods will be developed and optimized to ensure accurate classification of tissues, thereby facilitating the surgeon's decision-making process. This work will be carried out with the prior construction of a tissue database for training artificial intelligence algorithms.

This project proposes an innovative approach to improve the accuracy of oncological surgery in neurosurgery. The use of a multimodal fiber endomicroscope combined with artificial intelligence techniques promises real-time diagnostic assistance, thus paving the way for more precise and less invasive surgical interventions.

Contexte de travail

The Laboratory of Physics of the Two Infinities Irène Joliot-Curie is a laboratory of physics of the two infinities under the supervision of the CNRS, the University of Paris-Saclay, and the University of Paris, created in 2020 from the merger of the five UMRs located on the Orsay university campus: the Center for Nuclear Sciences and Materials Sciences (CSNSM), the Laboratory for Imaging and Modeling in Neurobiology and Cancerology (IMNC), the Institute of Nuclear Physics in Orsay (IPNO), the Linear Accelerator Laboratory (LAL), and the Theoretical Physics Laboratory (LPT).
The research themes of the laboratory are nuclear physics, high-energy physics, astroparticles and cosmology, theoretical physics, particle accelerators and detectors, as well as technical research and development and associated applications for energy, health, and the environment.
The structure has very important technical capabilities (about 280 engineers and technicians) in all major areas required to design, develop, and implement experimental devices necessary for its scientific activity: mechanical, electronic, computer science, instrumentation, acceleration techniques, and biology techniques. These technical strengths represent a major asset for the design, development, and use of the necessary instruments (accelerators and detectors). The presence of research infrastructures and technological platforms gathered on the laboratory site is also a major asset. Finally, about 90 ITAs from administrative and support services work alongside scientists and engineers.
The thesis project consists of developing a nonlinear fiber endomicroscope with classification performed by artificial intelligence (machine learning and deep learning). It is part of a collaboration with the CREATIS laboratory in LYON, a laboratory specializing in image processing for health. The objectives are to develop the instrument by making it intelligent, using a database to train artificial intelligence, which will then be integrated into the tool to improve its functionalities.
IJCLab bases its recruitment policy on the promotion of equality, diversity, and inclusion. Essential values, they allow the professional development of the agents, true actors of collective success, but also the development of the laboratory itself.

The candidate must hold a degree in engineering and/or a master's degree in Physics/Optics. The position requires strong knowledge in instrumentation and data analysis, good oral and written communication skills (French and English required) to present at conferences and write articles in scientific journals. We are looking for a young researcher who will be involved in his project, curious, with a certain autonomy, and a strong motivation to develop skills in nonlinear optical instrumentation and artificial intelligence classification. In addition, the candidate must be able to work in a team on multidisciplinary projects. Applications must include a detailed CV; at least two references (people who may be contacted); a one-page cover letter; a one-page summary of the master's thesis; the grades of Master 1 or 2 or engineering school).

Le poste se situe dans un secteur relevant de la protection du potentiel scientifique et technique (PPST), et nécessite donc, conformément à la réglementation, que votre arrivée soit autorisée par l'autorité compétente du MESR.

Contraintes et risques

The thesis will take place in the IMIT (Multimodal Instrumentation and Tissue Imaging) team of the health pole of the IJCLab laboratory. The thesis will be attached to the doctoral school 564 Physics in Île-de-France. Trips to Lyon will be necessary for the part of the thesis related to machine learning.