[Imageworld] Post-Doctoral Position: Ecole Centrale/INRIA/APHP
PitieSalPetriere/Paris (Medical Imaging/Virtual bronchoscope)
nikos.paragios at ecp.fr
Wed May 20 17:31:07 CEST 2009
Ecole Centrale de Paris/INRIA-Saclay Ile-de-France/APHP Pitie SalPetriere
http://www.ecp.fr & http://www.inria.fr/saclay/home/view?set_language=en
The Galen group (http://vision.mas.ecp.fr) [approx 25 members], a joint
research team between Ecole Centrale de Paris (one of the leading
engineering schools in France) and INRIA (leading research institute in
the field of computer science and engineering) is looking for a highly
motivated candidate to develop an image-based virtual bronchoscope
towards computer assisted chest surgery. This is a high;y collaborative
effort with the department of radiology of Pitie SalPetriere (Prof. P.
Grenier) and the department of respiratory medicine (Prof. T.
Similowsky, Dr. V. Trosini-Desert).
This effort aims to provide to surgeons of chest medicine a unique
computer-aided tool towards real-time intra-operative navigation. The
idea behind such a project is to be able to perform real-time
multi-modal alignment between preoperative annotated data (CT) and
interventional data bronchoscope images. Such a process will lead to an
automatic navigation tool on the 3D bronchial topography model obtained
through preoperative procedures. Therefore it will allow to the
physicians better diagnosis as well as better treatment of diseases.
This is a novel concept of computer-aided guided bronchoscopy through
biomedical image fusion that has never been investigated before.
Biomedical image fusion is an on-going research axis in the field of
medical image analysis with aim to establish correspondences between
different clinical modalities. The idea is to determine a transformation
that once applied to one of the signal minimizes or maximizes some
dissimilarity measure between them. However, such a concept was never
considered in the context of visual bronchoscopy since existing
registration methods suffer from numerous limitations: (i) in the most
general case, comparing heterogeneous signals with certain statistical
dependencies using low-rank statistical metrics is not sufficient, (ii)
in many examples because of the physics that are behind the acquisition,
signals can be very different and therefore finding statistical
measurements to determine their relation is not possible. The problem
considered in the proposal is far more challenging than conventional
registration problems. This is due the following reasons: (i)
pre-operative data is three dimensional while the bronchoscopic images
correspond to 2D depth views, therefore we are looking into a 2D-to-3D
registration problem, (ii) these modalities have nothing in common and
conventional registration criteria will fail to provide any meaningful
correspondences, (iii) the process has to be almost real-time as
navigation take places on the flexible bronchoscope. The approach that
will be considered in this proposal will benefit for recent advances in
the field of machine learning as well as the ones in discrete
The successful candidate is expected to closely collaborate with the two
leading hospital in Paris, the Pitie Sal-Petriere and the Henri Mondor.
He is also expected to contribute to numerous on going projects in the
field of medical image analysis and computer assisted diagnosis.
Prior work in the field of structure of motion, stereo reconstruction,
motion analysis registration will be a plus while candidates.
Successful candidates should hold a PhD degree in the field of medical
imaging/computer vision or related field, have excellent mathematical
skills, solid programming abilities and established research record.
- Duration: 12 months (renewable)
- Availability: immediate
- Net salary income: 2,250- 2,500 Euros/month (according to
qualifications) + benefits
- Location: The Galen group is located at Ecole Centrale, at the south
suburbs of Paris and is easily accessible with public transportation
(~20/25min with the regional train from the heart of Paris).
Applications: please mail your resume to Prof. Nikos Paragios
(nikos.paragios at inria.fr) including a list of two potentials references.
Nikos Paragios, Professor http://vision.mas.ecp.fr
Ecole Centrale de Paris Department of Applied Mathematics
Grande Voie des Vignes 92295 Chatenay-Malabry, France
Phone +33 (0) 1-4113-1785 Fax +33 (0) 1-4113-1735
mailto:nikos.paragios at ecp.fr
INRIA Saclay - Île-de-France Equipe GALEN, Head
Parc Orsay Université 4 rue Jacques Monod,91893 Orsay,France
mailto:nikos.paragios at inria.fr
More information about the Imageworld