Abstract
Segmentation of intervertebral discs from three-dimensional magnetic resonance images is a challenging problem with numerous medical applications. In this paper we describe a fully automated segmentation method based on a conditional random field operating on supervoxels. A mean Dice score of \(90\pm 3\) % was obtained on data provided for the intervertebral disc localisation and segmentation challenge in conjunction with the 3rd MICCAI Workshop & Challenge on Computational Methods and Clinical Applications for Spine Imaging - MICCAI–CSI2015.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Separate dictionaries are used to encode patches at different levels of the pyramid.
- 2.
Available from the SpineWeb: http://spineweb.digitalimaginggroup.ca.
References
Hutt, H., Everson, R., Meakin, J.: Segmentation of lumbar vertebrae slices from CT images. In: Yao, J., et al. (eds.) CSI 2014. LNCVB, vol. 20, pp. 61–71. Springer, Switzerland (2015)
Hutt, H., Everson, R., Meakin, J.: 3D segmentation of the lumbar spine from MRI using supervoxel-based CRFs. Technical report, University of Exeter, UK (2015)
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)
Olshausen, B., Field, D.: Emergence of simple-cell receptive field properties. Nature 381(6583), 607–609 (1996)
Weinberger, K., Saul, L.: Distance metric learning for large margin nearest neighbor classification. J. Mach. Learn. Res. 10, 207–244 (2009)
Chen, C., Belavy, D., Yu, W., Chu, C., Armbrecht, G., Bansmann, M., Felsenberg, D., Zheng, G.: Localization and segmentation of 3D intervertebral discs in MR images by data driven estimation. IEEE Trans. Med. Imaging 34(8), 1719–1729 (2015)
Acknowledgements
We are grateful to the organisers of the challenge and to the SpineWeb initiative for making the data available.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Hutt, H., Everson, R., Meakin, J. (2016). 3D Intervertebral Disc Segmentation from MRI Using Supervoxel-Based CRFs. In: Vrtovec, T., et al. Computational Methods and Clinical Applications for Spine Imaging. CSI 2015. Lecture Notes in Computer Science(), vol 9402. Springer, Cham. https://doi.org/10.1007/978-3-319-41827-8_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-41827-8_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-41826-1
Online ISBN: 978-3-319-41827-8
eBook Packages: Computer ScienceComputer Science (R0)