Abstract
Many applications require the automatic identification of bone structures in CT scans. The segmentation of the bone at the joints, however, is a difficult task to automate since the separation of the bones can be reduced by a degradation of the articular cartilage. In addition, the bone boundary can become very thin at certain locations due to osteoporosis, making it difficult to discriminate between the bone and neighbouring soft tissue. In this work, therefore, a probabilistic method is proposed to segment the bone structures by the registration of multiple atlases. Several atlas combination strategies are evaluated with respect to the segmentation and discrimination of the proximal femur and pelvic bone, and the L2 and L3 vertebrae, on datasets of 30 subjects using a leave-one-out approach. The mean overlap is computed and a false overlap measure is proposed to assess the correct discrimination of the bone structures. In addition, the mean average surface distances and Hausdorff distances are computed on the surface meshes extracted from the label maps. The results indicate that a generalized local-weighted voting approach is preferred, which results in a mean overlap \(\ge 0.97\) for all bone structures, while being able to accurately discriminate between neighbouring bone structures.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
MRC-Ageing: LREC 06/Q0108/180 study previously published in Poole et al., J Bone Miner Res, 2010.
- 2.
ACCT-1: LREC 04/Q0108/257 study previously published in McEniery et al., Hypertension, 2009.
References
Zoroofi, R., Sato, Y., Sasama, T., Nishii, T., Sugano, N., Yonenobu, K., Yoshikawa, H., Ochi, T., Tamura, S.: IEEE Trans. Inf. Technol. Biomed. 7(4), 329 (2003)
Krcah, M., Szekely, G., Blanc, R.: IEEE ISBI 2087–2090 (2011)
Hanaoka, S., Fritscher, K., Welk, M., Nemoto, M., Masutani, Y., Hayashi, N., K. Ohtomo, K., Schubert, R.: MICCAI, 554–561 (2011)
Ma, J., Lu, L., Zhan, Y., Zhou, X., Salganicoff, M., Krishnan, A.: MICCAI, 19–27 (2010)
Fritscher, K., Grünerbl, A., Schubert, R.: Int. J. CARS 1(6), 341 (2007)
Seim, H., Kainmueller, D., Heller, M., Lamecker, H., Zachow, S., Hege, H.C.: EG VCBM, 93–100 (2008)
Hanaoka, S., Fritscher, K., Schuler, B., Masutani, Y., Hayashi, N., Ohtomo, K., Schubert, R.: SPIE Med. Imaging, 796, 242–14 (2011)
Heckemann, R.A., Hajnal, J.V., Aljabar, P., Rueckert, D., Hammers, A.: Neuroimage 33(1), 115 (2006)
Artaechevarria, X., Muñoz-Barrutia, A., de Solórzano, C.O.: IEEE Trans. Med. Imaging. 28(8), 1266 (2009)
Rueckert, D., Aljabar, P., Heckemann, R., Hajnal, J., Hammers, A.: MICCAI, 702–709 (2006)
Warfield, S.K., Zou, K.H., Wells, W.M.: IEEE Trans. Med. Imaging 23(7), 903 (2004)
Lim, P.H., Bagci, U., Bai, L.: IEEE Trans. Biomed. Eng. 60(1), 115 (2013)
Yokota, F., Okada, T., Takao, M., Sugano, N., Tada, Y., Sato Y.: MICCAI, 811–818 (2009)
Glocker, B., Feulner, J., Criminisi, A., Haynor, D.R., Konukoglu, E.: MICCAI, 590–598 (2012)
Acknowledgments
Tristan Whitmarsh receives research funding from Eli Lilly.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Whitmarsh, T., Treece, G.M., Poole, K.E.S. (2014). Automatic Segmentation and Discrimination of Connected Joint Bones from CT by Multi-atlas Registration. In: Yao, J., Klinder, T., Li, S. (eds) Computational Methods and Clinical Applications for Spine Imaging. Lecture Notes in Computational Vision and Biomechanics, vol 17. Springer, Cham. https://doi.org/10.1007/978-3-319-07269-2_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-07269-2_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-07268-5
Online ISBN: 978-3-319-07269-2
eBook Packages: EngineeringEngineering (R0)