Coronary vein tracking from MSCT using a minimum cost path approach

Authors:
M.-P. Garcia;C. Toumoulin;P. Haigron;J. Velut;M. Garreau;D. Boulmier
Affiliations:
INSERM, Rennes, France and Université de Rennes I, LTSI, Rennes, France;INSERM, Rennes, France and Université de Rennes I, LTSI, Rennes, France;INSERM, Rennes, France and Université de Rennes I, LTSI, Rennes, France;INSERM, Rennes, France and Université de Rennes I, LTSI, Rennes, France;INSERM, Rennes, France and Université de Rennes I, LTSI, Rennes, France;INSERM, Rennes, France and Université de Rennes I, LTSI, Rennes, France and CHU Rennes, Rennes, France
Venue:
ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
Year:
2010

Citing 3
Cited 0

Muliscale Vessel Enhancement Filtering

MICCAI '98 Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention
Evaluation of a 3D segmentation software for the coronary characterization in multi-slice computed tomography

FIMH'03 Proceedings of the 2nd international conference on Functional imaging and modeling of the heart
Characterizing vascular connectivity from micro CT images

MICCAI'05 Proceedings of the 8th international conference on Medical image computing and computer-assisted intervention - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we deal with the problem of tracking the coronary venous tree from Multi-Slice Computed Tomography (MSCT) angiography. Contrast inhomogeneities are a major issue. The proposed tracking procedure is based on minimum-cost path computation and makes use of 'Fast-Marching' technique. The algorithm aims at propagating a front inside a vascular structure and extracting a centered path. To achieve this goal, a specific cost function which combines the vessel local orientation to a vesselness measure is designed. Experiments on synthetic data and real data have been performed. Coronary veins with contrast difficulties are extracted with a low computing time.