Ingenieur R&D Cifre, Deep Reinforcement learning for dose optimisation in radiation therapy

Ingenieur R&D Cifre, Deep Reinforcement learning for dose optimisation in radiation therapy

ORGANISATION/COMPANY TheraPanacea - Institut Gustave Roussy – CentraleSupelec

RESEARCH FIELD Optimization and deep/reinforcement learning applied to medical problems


THESIS DIRECTORS

- Professor Charlotte Robert, University of Paris-Sud, IGR

- Professor Nikos Paragios, TheraPanacea


THESIS CONTRIBUTORS:

- Professor Eric Deutsch, University of Paris-Sud, IGR,

- Professor Maria Vakalopoulou, Ecole CentraleSupelec, STARTING DATE November 1st 2019


Who is TheraPanacea?

We are is a fast growing medical start-up company (Paris Region AI Challenge 1st Prize in 2018) that develops artificial intelligence solutions to unlock the full potential of cancer treatment by radiation therapy. For more information about the company please visit www.therapanacea.eu.


We are looking for a PhD student...

In this thesis, we would like to explore the applicability of deep learning methods and MonteCarlo simulations for radiotherapy planning. Treatment planning software solutions solve high dimensional optimization problems to determine the best parameters (radiation angles, collimation parameters) that are used during treatment sessions carried out using linear accelerators. The successful applicant will explore an end-to-end approach for dose optimization coupling fast precise dose simulation with optimal dose delivery. The first one is to create an accelerated Monte Carlo simulations by using deep learning solutions (especially focusing on recursive neural network / long-short term memory networks) to significantly reduce the noise present in such simulations. The second topic is to study the possibility to create an optimization algorithm that uses the previously developed AI enhanced simulation to optimize the treatment plan parameters. This includes exploring the applicability of deep reinforcement learning to handle the problem of selecting the plan with optimal parameters to ensure the efficacy of the plan.

The successful applicant will integrate a team of ten researchers between TheraPanacea, Institute Gustave Roussy & CentraleSupelc and will work in an international team supervised by leading experts in the field of medical imaging and medical physics. The results of the research will be published in high impact journals.


Required skills

- Master’s degree in computer science or applied mathematics

- Ability to work independently and as a member of a research team

- Experience in optimization, deep learning and python is expected

- English at a conversational level (international team)


Required documents

- Cover letter and curriculum vitae

- Academic transcripts, duplicate of the Master’s diploma if available - Recommendation letter of one referee


To apply, please submit your application at the following address: hr.contact@therapanacea.eu