Skip to Main content Skip to Navigation
Conference papers

Acquisition multi-modale en temps réel pour le suivi du mouvement respiratoire

Abstract : Treatment of cancerous tumours in the lungs by ha- drontherapy requires precise knowledge of the position of the tumour throughout the treatment. A biomechani- cal model of the respiratory system allows the tracking of the tumour. This model requires the de nition of boundary conditions, set by the skin of the chest. In this sense, the objective of this article concerns the establishment of the complete processing chain for a continuous monitoring of the skin of the thorax (from neck to abdomen) through the use of a multi-modal non-invasive real-time system. A geometric model of reference of the thorax is rst created from preoperative medical data (CT, MRI). Then, during several respiratory cycles, this geome- tric model (surface mesh) is deformed to match the images of the thorax acquired by two cameras (above and lateral side). We achieve an accuracy around one millimeter, corresponding to the precision of the 3D images as well as the one of the used cameras, with a treatment rate of 6 frames per second.
Document type :
Conference papers
Complete list of metadata

Cited literature [17 references]  Display  Hide  Download
Contributor : Peter Sturm Connect in order to contact the contributor
Submitted on : Wednesday, June 1, 2011 - 5:33:58 PM
Last modification on : Thursday, July 29, 2021 - 10:04:01 AM
Long-term archiving on: : Friday, November 9, 2012 - 2:11:19 PM


Files produced by the author(s)


  • HAL Id : inria-00597739, version 1


Xavier Faure, Fabrice Jaillet, Florence Zara, Jean-Michel Moreau. Acquisition multi-modale en temps réel pour le suivi du mouvement respiratoire. ORASIS - Congrès des jeunes chercheurs en vision par ordinateur, INRIA Grenoble Rhône-Alpes, Jun 2011, Praz-sur-Arly, France. ⟨inria-00597739⟩



Les métriques sont temporairement indisponibles