Abstract
In this chapter, we present the constrained MSL to exploit correlations learned from the training set to increase the efficiency of the computational framework. The prior distribution of the object position is learned based on the statistics of the distance from the object center to volume border, and the test hypotheses of the orientation and scale are generated using an example-based sampling strategy from the training set. Furthermore, we employ the quaternion formulation for 3D orientation representation and distance measurement to overcome the limitations of Euler angles in the original MSL. Extensive comparison experiments are performed on three 3D anatomical structure detection problems in medical images, namely, liver detection in Computed Tomography (CT) volumes, and left ventricle detection in both CT and ultrasound volumes. They show that constrained MSL can improve the detection speed up to 14 times relative to the original MSL, while achieving comparable or better detection accuracy. It takes less than half a second to detect a typical 3D anatomical structure in a volume.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
In Chap. 2, a special city-block distance is actually used to split the orientation hypotheses into the positive and negative sets. The city-block distance is less accurate than the Euclidean distance and can be taken as an approximation of the latter.
References
Curtis, W.D., Janin, A.L., Zikan, K.: A note on averaging rotations. In: Proc. IEEE Virtual Reality Annual International Symposium, pp. 377–385 (1993)
Georgescu, B., Zhou, X.S., Comaniciu, D., Gupta, A.: Database-guided segmentation of anatomical structures with complex appearance. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 429–436 (2005)
van Ginneken, B., Heimann, T., Styner, M.: 3D segmentation in the clinic: A grand challenge. In: MICCAI Workshop on 3D Segmentation in the Clinic: A Grand Challenge (2007)
Karney, C.F.F.: Quaternions in molecular modeling. Journal of Molecular Graphics and Modeling 25(5), 595–604 (2007)
Kelm, B.M., Wels, M., Zhou, S.K., Seifert, S., Suehling, M., Zheng, Y., Comaniciu, D.: Spine detection in CT and MR using iterated marginal space learning. Medical Image Analysis 17(8), 1283–1292 (2013)
Kelm, B.M., Zhou, S.K., Suehling, M., Zheng, Y., Wels, M., Comaniciu, D.: Detection of 3D spinal geometry using iterated marginal space learning. In: Proc. MICCAI Workshop Medical Computer Vision — Recognition Techniques and Applications in Medical Imaging, pp. 96–105 (2010)
Kuffner, J.J.: Effective sampling and distance metrics for 3D rigid body path planning. In: Proc. IEEE Int’l Conf. Robotics and Automation, pp. 3993–3998 (2004)
Ling, H., Zhou, S.K., Zheng, Y., Georgescu, B., Suehling, M., Comaniciu, D.: Hierarchical, learning-based automatic liver segmentation. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1–8 (2008)
Okada, T., Shimada, R., Sato, Y., Hori, M., Yokota, K., Nakamoto, M., Chen, Y.W., Nakamura, H., Tamura, S.: Automated segmentation of the liver from 3D CT images using probabilistic atlas and multi-level statistical shape model. In: Proc. Int’l Conf. Medical Image Computing and Computer Assisted Intervention, vol. 1, p. 86–93 (2007)
Rancourt, D., Rivest, L.P., Asselin, J.: Using orientation statistics to investigate variations in human kinematics. Applied Statistics 49(1), 81–94 (2000)
Shoemake, K.: Animating rotation with quaternion curves. In: Proc. SIGGRAPH, pp. 245–254 (1985)
Zheng, Y., Barbu, A., Georgescu, B., Scheuering, M., Comaniciu, D.: Fast automatic heart chamber segmentation from 3D CT data using marginal space learning and steerable features. In: Proc. Int’l Conf. Computer Vision, pp. 1–8 (2007)
Zheng, Y., Barbu, A., Georgescu, B., Scheuering, M., Comaniciu, D.: Four-chamber heart modeling and automatic segmentation for 3D cardiac CT volumes using marginal space learning and steerable features. IEEE Trans. Medical Imaging 27(11), 1668–1681 (2008)
Zheng, Y., Georgescu, B., Comaniciu, D.: Marginal space learning for efficient detection of 2D/3D anatomical structures in medical images. In: Proc. Information Processing in Medical Imaging, pp. 411–422 (2009)
Zheng, Y., Georgescu, B., Ling, H., Zhou, S.K., Scheuering, M., Comaniciu, D.: Constrained marginal space learning for efficient 3D anatomical structure detection in medical images. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 194–201 (2009)
Zheng, Y., Zhou, X.S., Georgescu, B., Zhou, S.K., Comaniciu, D.: Example based non-rigid shape detection. In: Proc. European Conf. Computer Vision, pp. 423–436 (2006)
Zhou, X., Kitagawa, T., Hara, T., Fujita, H., Zhang, X., Yokoyama, R., Kondo, H., Kanematsu, M., Hoshi, H.: Constructing a probabilistic model for automated liver region segmentation using non-contrast X-ray torso CT images. In: Proc. Int’l Conf. Medical Image Computing and Computer Assisted Intervention, vol. 2, pp. 856–863 (2006)
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media New York
About this chapter
Cite this chapter
Zheng, Y., Comaniciu, D. (2014). Constrained Marginal Space Learning. In: Marginal Space Learning for Medical Image Analysis. Springer, New York, NY. https://doi.org/10.1007/978-1-4939-0600-0_4
Download citation
DOI: https://doi.org/10.1007/978-1-4939-0600-0_4
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4939-0599-7
Online ISBN: 978-1-4939-0600-0
eBook Packages: Computer ScienceComputer Science (R0)