Comparison and Assessment of Different Image Registration Algorithms Based on ITK

Abstract:

A lot of image registration algorithms are proposed in recent year, among these algorithms, which one is better or faster than the other can be only validated by experiments. In this paper, ITK (Insight Segmentation and Registration Toolkit) is used for verifying different algorithms as a framework. ITK framework requires the following components: a fixed image, a moving image, a transform, a metric, an interpolator and an optimizer. Dozens of classical algorithms are tested under the same conditions and their experimental results are demonstrated with different metrics, interpolators or optimizers. By comparison of registration time and accuracy, those practical and useful algorithms are selected for developing software in image analysis. These kinds of experiments are very valuable for software engineering, they can shorten the cycle of software development and greatly reduce the development costs.

• Periodical: Applied Mechanics and Materials (Volume 442)
• Pages: 515-519
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.442.515
• Online since: October 2013
• Authors: Zhen Huan Zhou*
• Keywords: Algorithms Comparison, Image Registration, ITK, Registration Framework

References

[1] Terry S. Yoo1, Engineering and Algorithm Design for an Image Processing API: A Technical Report on ITK - the Insight Toolkit, Studies in Health Technology and Informatics, vol. 85., Amsterdam: IOS Press, 2002, pp.586-592.

[2] Vincent Chu, Ghassan Hamarneh, MATLAB-ITK Interface for Medical Image Filtering, Segmentation, and Registration, Proc. of SPIE Vol. 6144, 61443T (2006).

DOI: 10.1117/12.652628

[3] Josien P. W. Pluim, J. B. Antoine, Mutual information based registration of medical images: a survey, IEEE Transcations on medical imaging, Vol. 22, no. 8, 2003, p.986–1004.

DOI: 10.1109/tmi.2003.815867

[4] J. B. Antoine Maintz and Max A. Viergever, A survey of medical image registration, Medical Image Analysis, 1998, Vol. 2, no. 1, pp.1-36.

DOI: 10.1016/s1361-8415(01)80026-8

[5] K. Murphy , B. van Ginneken, Semi-automatic construction of reference standards for evaluation of image registration, Medical Image Analysis, 2011, Vol. 15, p.71–84.

DOI: 10.1016/j.media.2010.07.005

[6] Urschler, M., Kluckner, A framework for comparison and evaluation of nonlinear intra-subject image registration algorithms, MICCAI Open Science Workshop, (2007).

DOI: 10.54294/9lhq05

[7] T. Vik, S. Kabus, Validation and comparison of registration methods for free breathing 4D lung CT, Proceedings of the SPIE, 2008, Vol. 6917.

DOI: 10.1117/12.767787

[8] R. Wiemker, B. deHoop, Performance study of a globally elastic locally rigid matching algorithm for follow-up chest CT, Proceedings of the SPIE, 2008, Vol. 6917.

DOI: 10.1117/12.765166

[9] R. Shams, P. Sadeghi, A Survey of Medical Image Registration on Multicore and the GPU, IEEE Signal Processing Magazine, 2010, Vol. 27, no. 2, pp.50-60.

DOI: 10.1109/msp.2009.935387

[10] H. Zhang, F. Yang, Multimodality Medical Image Registration Using Hybrid Optimization Algorithm, 2008 International Conference on BMEI, Vol. 2, pp.183-187.