1. Object tracking in medical imaging using a 2D active mesh system
- Author
-
J. Lautissier, Alain Lalande, L. Legrand, Paul Walker, François Brunotte, Laboratoire Electronique, Informatique et Image ( Le2i ), Université de Bourgogne ( UB ) -AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Centre National de la Recherche Scientifique ( CNRS ), Walker, Paul, Laboratoire Electronique, Informatique et Image [UMR6306] (Le2i), Université de Bourgogne (UB)-École Nationale Supérieure d'Arts et Métiers (ENSAM), Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-Arts et Métiers Sciences et Technologies, and HESAM Université (HESAM)-HESAM Université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Centre National de la Recherche Scientifique (CNRS)
- Subjects
Digital image correlation ,[ INFO.INFO-IM ] Computer Science [cs]/Medical Imaging ,business.industry ,Computer science ,Optical flow ,[INFO.INFO-IM] Computer Science [cs]/Medical Imaging ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,02 engineering and technology ,Tracking (particle physics) ,Object detection ,030218 nuclear medicine & medical imaging ,03 medical and health sciences ,0302 clinical medicine ,Mesh generation ,Video tracking ,0202 electrical engineering, electronic engineering, information engineering ,Medical imaging ,[INFO.INFO-IM]Computer Science [cs]/Medical Imaging ,020201 artificial intelligence & image processing ,Computer vision ,Noise (video) ,Artificial intelligence ,business ,ComputingMethodologies_COMPUTERGRAPHICS - Abstract
International audience; Abstract: This article proposes a technique for tracking moving organs in medical imaging. It can be split into two stages. We first initialize a 2D-triangular mesh on the first image of the sequence. We distinguish different objects of interest by grouping together the triangles that make them up. Afterwards, we deform this mesh on the successive images in order to track each identified object. The tracking stage uses optical flow by adding a node relaxation step to avoid mesh deteriorations. The mesh deformations analysis provides access to motion information along the sequence. This technique is applied to a cine-MRI sequences of the heart and allows the analysis of ventricular motions. The obtained results are quite precise, all the more as the implemented techniques are rather robust to noise and to contrast variations.
- Published
- 2003