Share Email Print

Proceedings Paper

Machine learning based vesselness measurement for coronary artery segmentation in cardiac CT volumes
Author(s): Yefeng Zheng; Maciej Loziczonek; Bogdan Georgescu; S. Kevin Zhou; Fernando Vega-Higuera; Dorin Comaniciu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Automatic coronary centerline extraction and lumen segmentation facilitate the diagnosis of coronary artery disease (CAD), which is a leading cause of death in developed countries. Various coronary centerline extraction methods have been proposed and most of them are based on shortest path computation given one or two end points on the artery. The major variation of the shortest path based approaches is in the different vesselness measurements used for the path cost. An empirically designed measurement (e.g., the widely used Hessian vesselness) is by no means optimal in the use of image context information. In this paper, a machine learning based vesselness is proposed by exploiting the rich domain specific knowledge embedded in an expert-annotated dataset. For each voxel, we extract a set of geometric and image features. The probabilistic boosting tree (PBT) is then used to train a classifier, which assigns a high score to voxels inside the artery and a low score to those outside. The detection score can be treated as a vesselness measurement in the computation of the shortest path. Since the detection score measures the probability of a voxel to be inside the vessel lumen, it can also be used for the coronary lumen segmentation. To speed up the computation, we perform classification only for voxels around the heart surface, which is achieved by automatically segmenting the whole heart from the 3D volume in a preprocessing step. An efficient voxel-wise classification strategy is used to further improve the speed. Experiments demonstrate that the proposed learning based vesselness outperforms the conventional Hessian vesselness in both speed and accuracy. On average, it only takes approximately 2.3 seconds to process a large volume with a typical size of 512x512x200 voxels.

Paper Details

Date Published: 11 March 2011
PDF: 12 pages
Proc. SPIE 7962, Medical Imaging 2011: Image Processing, 79621K (11 March 2011); doi: 10.1117/12.877233
Show Author Affiliations
Yefeng Zheng, Siemens Corp. Research (United States)
Maciej Loziczonek, Siemens Corp. Research (United States)
Bogdan Georgescu, Siemens Corp. Research (United States)
S. Kevin Zhou, Siemens Corp. Research (United States)
Fernando Vega-Higuera, Siemens Medical Solutions GmbH (Germany)
Dorin Comaniciu, Siemens Corp. Research (United States)

Published in SPIE Proceedings Vol. 7962:
Medical Imaging 2011: Image Processing
Benoit M. Dawant; David R. Haynor, Editor(s)

© SPIE. Terms of Use
Back to Top