En poursuivant votre navigation sur ce site, vous acceptez le dépôt de cookies dans votre navigateur. (En savoir plus)
Portail > Offres > Offre UMR7346-ANNPOR-151 - Méthodes d'apprentissage pour le contrôle de dose en hadronthérapie en Prompt-Gamma Time Imaging (H/F)

Learning methods for dosimetry in hadrontherapy with Prompt-Gamma Time Imaging (M/F)

This offer is available in the following languages:
- Français-- Anglais-- Espagnol

Date Limite Candidature : jeudi 24 avril 2025 00:00:00 heure de Paris

Assurez-vous que votre profil candidat soit correctement renseigné avant de postuler

Informations générales

Intitulé de l'offre : Learning methods for dosimetry in hadrontherapy with Prompt-Gamma Time Imaging (M/F) (H/F)
Référence : UMR7346-ANNPOR-151
Nombre de Postes : 1
Lieu de travail : MARSEILLE 09
Date de publication : jeudi 27 février 2025
Type de contrat : Chercheur en contrat CDD
Durée du contrat : 24 mois
Date d'embauche prévue : 1 mai 2025
Quotité de travail : Complet
Rémunération : between 3081 et 4291 euros gross monthly depending on experience
Niveau d'études souhaité : Doctorat
Expérience souhaitée : 1 à 4 années
Section(s) CN : 01 - Interactions, particules, noyaux du laboratoire au cosmos

Missions

The research work forms part of the Prompt-Gamma Time Imaging (PGTI) project, funded by the ERC, which aims to provide an instrumental and methodological proof of concept for real-time monitoring, using real data, of the emission distribution of Gamma Prompts (GPs) in the context of hadrontherapy. A detection system placed around the patient - consisting of a beam monitor and gamma detectors - with a temporal resolution of 100 ps provides time-of-flight measurements of the particles involved in the treatment. The first objective of the proposed mission is to use this data to be able to detect as early as possible any significant divergence between the actual treatment and the treatment plan (simulated upstream), and to stop the treatment if necessary. The final objective is to be able to estimate the dose deposition profile from the time-of-flight measurements with sufficient accuracy to adjust the treatment in real time in relation to the treatment plan.

Activités

The researcher recruited will join the imXgam team at the Centre de Physique des Particules de Marseille, which is responsible for developing the data processing methodology for the PGTI project.

He/she will develop a research activity at the interface between information sciences and medical physics in order to explore applications of artificial intelligence for time-of-flight data in hadrontherapy. He/she will pursue the following main objectives: i) perfect our approach to 3D reconstruction of GP vertices based on an optimisation problem that incorporates the physics of hadrontherapy (e.g. in particular by analysing simulated and real data available in order to incorporate suitable regularisations). The results obtained at this stage will be used in particular to optimise the design of the instrument for maximum spatial resolution; ii) evaluate the contribution of machine learning and deep learning methods to jointly estimate the 3D distribution of GP vertices and the anatomical changes (i.e. in electron density) between the time of the treatment plan and the time of the actual treatment. This essential quantity is often estimated beforehand with significant uncertainties that need to be compensated for. Various strategies will be studied and the most relevant (transfer learning, use of Generative Adversarial Networks) will be evaluated on real data with feedback from doctors and radiophysicists.


The researcher will be part of the PGTI project funded by an ERC Starting Grant led by Sara Marcatili (LPSC) as part of a tripartite collaboration between the Laboratoire de Physique Subatomique & Cosmologie (LPSC) in Grenoble, the Centre de Physique des Particules de Marseille (CPPM) and the Centre Antoine Lacassagne (CAL) in Nice.
He/she will benefit from the rich and stimulating multidisciplinary working environment of the imXgam team, the CPPM and the Luminy Campus, including access to the know-how and computing resources of the IN2P3 Computing Centre.

Compétences

At least two skills among data processing, learning methods, medical physics, Monte Carlo simulation.
Development in Python.
Ability to report in French or English (presentations, reports, writing articles), to welcome, listen and communicate diplomatically.
Good interpersonal skills, rigour and organisation, autonomy.
Managerial skills

Contexte de travail

Located in the heart of the Parc National des Calanques, on the Luminy campus, the CPPM is a joint research laboratory of the CNRS and Aix-Marseille University, with around 180 researchers, engineers and PhD students. The laboratory studies subjects ranging from particle physics to astroparticle physics and cosmology, with a strong technological focus on electronics, mechanics, instrumentation and computing, enabling the design and construction of cutting-edge detection systems, often called upon to operate under extreme conditions: in the depths of the sea, in space or underground. Most of our research is carried out as part of leading international scientific collaborations, and our contributions are recognized worldwide. CPPM is committed to ethical research and promotes diversity and inclusion in the workplace, and provides administrative and logistical support to newcomers, particularly PhD students. (more details here: https://www.cppm.in2p3.fr/web/fr/index.html)