Postdoc H/F - Reconstruction de tomodensitométries dentaires utilisant l’apprentissage automatique

Fourteen-month postdoctoral position in the collaborative Cone-Beam AI project between Acteon, a company designing X-ray medical devices for dentistry, the CREATIS medical-imaging research centre and the Institut de Mathématiques de Bordeaux. The project aims to improve the quality of the cone-beam computed tomography (CBCT) scans used for dental diagnosis while reducing the radiation dose received by patients, by developing better tomographic reconstruction algorithms that use machine-learning methods suited to inverse problems.

Topics include quantitative CBCT reconstruction from truncated data, inside and as far as possible outside the scanner’s field of view; estimating patient or scanner motion without prior reconstruction using data-consistency conditions; correcting X-ray projections for scattered radiation with deep-learning estimates; and correcting metal artefacts in the projections. The postdoc is supervised by Simon Rit and joins the CREATIS tomoradio team, working mainly at the Centre Léon Bérard cancer centre in Lyon.

Start as soon as possible; gross monthly salary from €3,071 depending on experience.

PhD in applied mathematics, computer science or medical physics; Python and C++ (ITK, RTK); English required, French optional.