Où docteurs et entreprises se rencontrent

Vous avez déjà un compte ?

Nouvel utilisateur ?

Mot de passe oublié

Improving the estimation of dynamic parameters in PET imaging for breast cancer

ABG-84697 Sujet de Thèse
15/04/2019 < 25 K€ brut annuel
Université de Bourgogne
Dijon - Bourgogne-Franche-Comté - France
Improving the estimation of dynamic parameters in PET imaging for breast cancer
  • Informatique
  • Physique
  • Santé, médecine humaine, vétérinaire

Description du sujet

18F-Fluorodeoxyglucose (FDG) Positron Emission Tomography (PET) is a gold standard for the evaluation of tumour metabolism and is now widely used in medical oncology for cancer detection, staging, and more recently therapy monitoring. The concomitant evaluation of tumour perfusion and tumour metabolism is promising for the monitoring of new therapies targeting both tumour perfusion and viability. However, the development of dynamic FDG PET in clinical practice is challenging, due to the poor spatial resolution and signal to noise ratio of dynamic PET images. For example, classical reconstruction algorithms (MLEM) have shown to produce bias in short-duration frames in dynamic PET studies. Such a bias is very problematic for quantitative imaging, particularly when trying to derive an image-derived input function. Currently, both the acquisition procedure and the analysis methodology need to be improved in order to find robust and reproducible PET-based biomarkers that could be useful for the early evaluation of treatment response.

The main objectives of this project are to improve the methods of dynamic FDG PET acquisition and analysis with a new digital PET system. More specifically, it will focus on:

- Simulating pairs of dynamic pristine and PET-like images to mimic the new digital PET system.

- Developing a deep learning algorithm to denoise the dynamic PET-like images.

- Validating the developed denoising technique with the real 4D PET images currently obtained in clinical routine.

- Analysing the image data through textural features (TF) to describe global and local heterogeneities for both perfusion and metabolism.

- Using the TF analysis to predict the evaluation of treatment response with machine learning techniques.

The student will be located in the imagerie et vision artificielle (ImViA) laboratory in Dijon (France), and will work in close relation with the department of nuclear medicine of the Georges-François Leclerc centre (Dijon, France).


Nature du financement

Contrat doctoral

Précisions sur le financement

1700 € gross per month

Présentation établissement et labo d'accueil

Université de Bourgogne

Imagerie et Vision Artificielle (ImViA), EA 7535, Université de Bourgogne, Dijon (France).


Profil du candidat

Candidates must hold at least an upper second class degree or equivalent qualifications in a relevant subject area such as physics, biomedical engineering, computer science, or applied mathematics. A Master's degree in a relevant discipline and additional research experience would be an advantage.

Candidates should be fluent in English and possibly French.

Date limite de candidature

Partager via

Vous avez déjà un compte ?

Nouvel utilisateur ?

Mot de passe oublié
Besoin d'informations ?

Vous souhaitez recevoir une ou plusieurs lettres d’information de l’ABG. Chaque mois des actualités, des offres, des outils, un agenda…

item1 item1