Abstract
Multimodal 3D medical images have the characteristics of huge operational data and multi degrees of freedom in geometric transformation. However, there are some difficulties in multimodal medical image registration, such as low registration efficiency and speed. In order to meet the clinical needs, a feature sphere constrained registration algorithm based on conformal geometric algebra is proposed in this paper. Firstly, 3D contour point clouds are extracted from multimodal medical images. Then, the spatial conformal sphere is constructed, and the feature points are calculated based on the spatial projection constraint from the point cloud to the conformal sphere. Finally, rotation operators are constructed by feature points to realize fast 3D medical image registration. Experimental results indicate that the registration algorithm based on geometric feature constraints in this paper is more effective for registration of multimodal 3D medical images, with high accuracy, anti-noise ability, rapid calculation, and strong universality.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Plattard, D., Soret, M., Troccaz, J., et al.: Patient set-up using portal images: 2D/2D image registration using mutual information. Comput. Aided Surg. 5(4), 246–262 (2015)
Miao, S., Wang, Z.J., Rui, L.: A CNN regression approach for real-time 2D/3D registration. IEEE Trans. Med. Imaging. 35(5), 1 (2016)
Brockmeyer, D., Gruber, D.P., Haller, J., et al.: High-accuracy 3D image-based registration of endoscopic video to C-arm cone-beam CT for image-guided skull base surgery. Laryngoscope 122(1), 1925−1932 (2018)
Wu, K., Kalvin, A.D., Williamson, B., et al.: Providing visual information to validate 2-D to 3-D registration. Med. Image Anal. 4(4), 357–374 (2000)
Wu, J.: Rigid 3D registration: a simple method free of SVD and eigen-decomposition. IEEE Instrum. Meas. Magn. 69(10), 8288–8303 (2020)
He, Y., Lee, C.H.: An improved ICP registration algorithm by combining PointNet++ and ICP algorithm. In: 2020 6th International Conference on Control, pp. 741−745. ICCAR, Singapore (2020)
Bricq, S., Kidane, H.L., Zavala-Bojorquez, J., et al.: Automatic deformable PET/MRI registration for preclinical studies based on B-splines and non-linear intensity transformation. Med. Biol. Eng. Comput. 56(9), 1531–1539 (2018)
Cao, W.M., Liu, H., Xu, C.: 3D medical image registration based on conformal geometric algebra. Sci. Sinica Informationis. 43(2), 254–274 (2013)
Hua, L., Yu, K., Ding, L., et al.: A methodology of three-dimensional medical image registration based on conformal geometric invariant. Math. Probl. Eng. 1−8 (2014)
Hua, L., Cheng, T.Y., Gu, J.P., et al.: 3D medical image registration based on Clifford relative invariant and region of interest. J. Graphics 38(1), 90–96 (2017)
Li, H.B.: Conformal geometric algebra for motion and shape description. Comput. Aided Des. Comput. Graphics 18(7), 895–903 (2006)
Sierra, S.J.: Geometric algebras on projective surfaces. J. Algebra 324(7), 1687–1730 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Cheng, T., Gu, J., Hua, L., Zhu, J., Zhao, F., Cao, Y. (2021). Research of Medical Image Registration Based on Characteristic Ball Constraint in Conformal Geometric Algebra. In: Fei, M., Chen, L., Ma, S., Li, X. (eds) Intelligent Life System Modelling, Image Processing and Analysis. LSMS ICSEE 2021 2021. Communications in Computer and Information Science, vol 1467. Springer, Singapore. https://doi.org/10.1007/978-981-16-7207-1_6
Download citation
DOI: https://doi.org/10.1007/978-981-16-7207-1_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7206-4
Online ISBN: 978-981-16-7207-1
eBook Packages: Computer ScienceComputer Science (R0)