Abstract
Coronary artery segmentation is important in quantitative coronary angiography. In this work, a novel method is proposed for coronary artery segmentation. It integrates coronary artery features of density, local shape and global structure into the learning framework. The density feature is the vessel’s relative density estimated by means of Gaussian mixture models and is able to suppress individual variances. The local tube shape of the vessel is measured with the advantages of the 3-dimensional multi-scale Hessian filter and is able to enhance the small vessels. The global structure feature is predicted from a support vector regression in terms of vessel’s spatial position and emphasizes the geometric morphometric attribute of the coronary artery tree running across the surface of the heart. The features are fed into a support vector classifier for vessel segmentation. The proposed methodology was tested on ten 3D cardiac computed tomography angiography datasets. It obtained a sensitivity of 81%, a specificity of 99%, and Dice coefficient of 84%. The performance is good.
Preview
Unable to display preview. Download preview PDF.
References
Kitslaar, P., Frenay, M., Oost, E., Dijkstra, J., Stoel, B., Reiber, J.: Connected component and morphology based extraction of arterial centerlines of the heart (CocomoBeach). In: MICCAI Workshop S4 (2008)
Wang, C., Smedby, O.: An automatic seeding method for coronary artery segmentation and skeletonization in CTA. In: MICCAI Workshop S4 (2008)
Li, Z., Zhang, Y., Liu, G., Shao, H., Li, W.: A robust coronary artery identification and centerline extraction method in angiographies. Biomed. Signal Proce. 16, 1–8 (2015)
Zhou, C., Chan, H., Chughtai, C., Patel, S., Hadijiiski, L., Wei, J., Kazerooni, E.: Automated coronary artery tree extraction in coronary CT angiography using a multi-scale enhancement and dynamic balloon tracking (MSCAR-DBT) method. Comput. Med. Imag. Grap. 36, 1–10 (2012)
Yang, G., Kitslaar, P., Frenay, M., Broersen, A., Boogers, M., Bax, J., Reiber, J., Dijkstra, J.: Automatic centerline extraction of coronary arteries in coronary computed tomographic angiography. Int. J. Card. Imaging 28(4), 921–933 (2012)
Zambal, S., Hladuvka, J., Kanitsar, A., Buhler, K.: Shape and appearance models for automatic coronary artery tracking. In: MICCAI Workshop S4 (2008)
Schaap, M., Walum, T., Neefjes, L., Metz, C., Capuano, E., Bruijne, M., Niessen, W.: Robust shape regression for supervised vessel segmentation and its application to coronary segmentation in CTA. IEEE Trans. Med. Imaging 30(11), 1974–1986 (2011)
Wong, W., So, R., Chung, A.: Principal curves for lumen center extraction and flow channel width estimation in 3-D arterial networks: theory, algorithm, and validation. IEEE Trans. Image Process. 21(4), 1847–1862 (2012)
Schneider, M., Hirsch, S., Weber, B., Szekely, G., Menze, B.: Joint 3-D vessel segmentation and centerline extraction using oblique Hough forests with steerable filters. Med Image Anal 19, 220–249 (2015)
Friman, O., Hindennach, M., Kuhnel, C., Peitgen, H.: Multiple hypothesis template tracking of small 3D vessel structures. Med. Image Anal. 14, 160–171 (2010)
Kitamura Y., Li Y., and Ito W.: Automatic coronary extraction by supervised detection and shape matching. In: Proc. of ISBI, pp. 234-237 (2012)
Zheng, Y., Tek, H., Funka-Lea, G.: Robust and accurate coronary artery centerline extraction in CTA by combining model-driven and data-driven approaches. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part III. LNCS, vol. 8151, pp. 74–81. Springer, Heidelberg (2013)
Bishop, C.: Pattern Recognition and Machine Learning, pp. 78–124. Springer Science Business Media, Heidelberg (2006)
Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum-likelihood from incomplete data via the EM algorithm. J. Royal Statist. Soc. Ser. B. 39(1), 1–38 (1977)
Sato, Y., Nakajima, S., Shiraga, N., Atsumi, H., Yoshida, S., Koller, T., Gerig, G., Kikinis, R.: Three-dimensional multi-scale line filter for segmentation and visualization of curvilinear structures in medical images. Med. Image Anal. 2(2), 143–168 (1998)
Dodge, J., Brown, B., Bolson, E., Dodge, H.: Lumen diameter of normal human coronary arteries. Influence of age, sex, anatomic variation, and left ventricular hypertrophy or dilation. Circulation 86, 232–246 (1992)
Smola, A., Scholkopf, B.: A tutorial on support vector regression. Stat. Comp. 14, 199–222 (2004)
Joachims T.: Estimating the generalization performance of an SVM efficiently. In: Proc. ICML, pp. 431-438 (2000)
Mao, S., Ahmadi, N., Shah, B., Beckmann, D., Chen, A., Ngo, L., Flores, F., Gao, Y., Budoff, M.: Normal thoracic aorta diameter on cardiac computed tomography in healthy asymptomatic adult; impact of age and gender. Acad Radiol 15(7), 827–834 (2008)
Hazel, R., Pollack, S., Reichek, N.: Investigation of the relationship between age and the angle of aortic insertion on the left ventricle using 3D MRI. J. Cardiov. Magn. Resonance 14, 77–78 (2012)
Schaap, M., Metz, C., Walsum, T., Giessen, A., et al.: Standardized evaluation methodology and reference database for evaluating coronary artery centerline extraction algorithms. Med. Image Anal. 13, 701–714 (2009)
Lee, T., Kashyap, R., Chu, C.: Building skeleton models via 3-D medical surface/axis thinning algorithms. Graph. Model and Im. Proc. 56(6), 462–478 (1994)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Chi, Y. et al. (2015). A Composite of Features for Learning-Based Coronary Artery Segmentation on Cardiac CT Angiography. In: Zhou, L., Wang, L., Wang, Q., Shi, Y. (eds) Machine Learning in Medical Imaging. MLMI 2015. Lecture Notes in Computer Science(), vol 9352. Springer, Cham. https://doi.org/10.1007/978-3-319-24888-2_33
Download citation
DOI: https://doi.org/10.1007/978-3-319-24888-2_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24887-5
Online ISBN: 978-3-319-24888-2
eBook Packages: Computer ScienceComputer Science (R0)