Aller au menu Aller au contenu Aller à la recherche
  • Français
  • English

Internship: improving the aorta segmentation from magnetic resonance imaging (MRI)

aA - +Imprimer la page

Internship: improving the aorta segmentation from magnetic resonance imaging (MRI)

Supervisors: Arnaud Boucher, PhD, Olivier Bouchot, MD, PhD, Alain Lalande, PhD, Benoit Presles, PhD

Starting date: 1st February 2021

Project description

Among cardiovascular diseases, a swelling of the aorta called aortic aneurysm represents a significant risk of mortality caused by tears of the aortic wall or aneurysm rupture. The surgical decision to replace the aorta with a Dacron tube is mainly based on the size of the aneurysm (>50-55mm). However, it is known that aneurysm rupture of the ascending aorta occurs in more than 66% of cases for aneurysms with a size smaller than 55mm. Therefore, it seems decisive to acquire a better understanding of this phenomena.

The work carried out by our team on 4D (3D+t) segmentation on MRI is promising today but could be improved by segmenting beforehand a 3D angiography since this type of image has a better resolution. It will allow us to obtain the exact shape of the aorta and use this information as a prior for the 4D MRI segmentation.

The aim of this internship is therefore to develop a 3D segmentation method of the aorta on angiography and generate a description of this shape to use it for the 4D segmentation. The student will have access to a database of more than 40 patients with both 3D angiography and 4D MRI exams done just before surgery. Deep learning based methods could be interesting to investigate.

The student will be located in the “Imagerie et Vision Artificielle" (ImViA) in Dijon (France), and will work in close relation with the medical team of the University Hospital François Mitterrand in Dijon (France).

Person specification

Candidates must be engineering or master students in a relevant subject area such as computer science, biomedical engineering or applied mathematics.


Applications (including a CV and covering letter outlining your motivation for the position) should be sent to Arnaud Boucher (arnaud.boucher at, Alain Lalande (alain.lalande at, and Benoit Presles (benoit.presles at

Closing date: 31th December 2020


Log In

Create an account