Abstract
Non-invasive surface matching registration is preferred over paired point registration using bone anchor fiducial markers in neurosurgery due to its ability to avoid iatrogenic injuries and eliminate the need for medical image acquisition during navigation. However, the use of the iterative closest point algorithm for surface matching registration requires a manual coarse registration process, leading to a complicated and inconvenient procedure. To automate the coarse registration, this study proposes a method that combines algorithms for automatic surface matching and determination of optimal scale parameters. The method employs feature-based automatic coarse registration using point clouds with unique features at single scale and persistent features at multiple scales. By combining feature detection, description, and matching algorithms, the optimal scale parameters for each algorithm combination are identified. Through a comprehensive evaluation, 19 out of 24 algorithm combinations were found to achieve correct registration at the optimal scale based on considerations of robustness, accuracy, and time efficiency. The most effective combination was the SIFT + FPFH + SAC-IA + ICP algorithm with a scale parameter of \(\alpha\) = 0.09%, resulting in a Hausdorff distance of 3.205 mm and a registration time of 5.082 s. This algorithmic combination enables the automatic spatial registration of neuronavigation, providing a convenient and reliable method for establishing accurate pose mapping between the image space and the patient space.
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
Similar content being viewed by others
References
Thomas, N.W.D., Sinclair, J.: Image-guided neurosurgery: history and current clinical applications. J. Med. Imaging Radiat. Sci. 46(3), 331–342 (2015)
Besl, P.J., McKay, N.D.: A method for registration of 3-D shapes. IEEE Trans. Pattern Anal. Mach. Intell. 14(2), 239–256 (1992)
Elseberg, J., Magnenat, S., Siegwart, R., et al.: Comparison of nearest-neighbor-search strategies and implementations for efficient shape registration. J. Softw. Eng. Rob. 3, 2–12 (2012)
Liu, Y., Song, Z., Wang, M.: A new robust markerless method for automatic image-to-patient registration in image-guided neurosurgery system. Comput. Assist. Surg. 22(sup1), 319–325 (2017)
Buch, A.G., Kraft, D., Kamarainen, J.K., et al.: Pose estimation using local structure-specific shape and appearance context. In: 2013 IEEE International Conference on Robotics and Automation, pp. 2080–2087(2013)
Guo, Y., Bennamoun, M., Sohel, F., et al.: A comprehensive performance evaluation of 3D local feature descriptors. Int. J. Comput. Vis 116(1), 66–89 (2016)
Zhong, Y.: Intrinsic shape signatures: a shape descriptor for 3D object recognition. In 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops, pp. 689–696(2009)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60(2), 91–110 (2004)
Tian, B., Jiang, P., Zhang, X., Zhang, Y., Wang, F.: A novel feature point detection algorithm of unstructured 3D point cloud. In: Huang, D.-S., Han, K., Hussain, A. (eds.) ICIC 2016. LNCS (LNAI), vol. 9773, pp. 736–744. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-42297-8_68
Rusu, R.B., Blodow, N., Marton, Z.C., et al.: Aligning point cloud views using persistent feature histograms. In: 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 3384–3391 (2008)
Rusu, R.B., Blodow, N., Beetz, M.: Fast Point Feature Histograms (FPFH) for 3D registration. In: 2009 IEEE International Conference on Robotics and Automation. Kobe: IEEE, pp. 3212–3217(2009)
Holz, D., Ichim, A.E., Tombari, F., et al.: Registration with the point cloud library: a modular framework for aligning in 3-D. IEEE Robot. Autom. Mag. 22(4), 110–124 (2015)
Rusu, R.B., Márton, Z.C., Blodow, N., et al.: Persistent point feature histograms for 3D point clouds. In: Proceedings of the 10th International Conference on Intelligent Autonomous Systems, Baden, Germany, vol. 16( 2008)
Zaharescu, A., Boyer, E., Horaud, R.: Keypoints and local descriptors of scalar functions on 2D manifolds. Int. J. Comput. Vision 100(1), 78–98 (2012)
Sun, G., Wang, X.: Three-dimensional point cloud reconstruction and morphology measurement method for greenhouse plants based on the kinect sensor self-calibration. Agronomy 9(10), 596 (2019)
Rusu, R.B., Cousins, S.: 3D is here: point cloud library (PCL). In: 2011 IEEE International Conference on Robotics and Automation, pp. 1–4 (2011)
Acknowledgement
This work was supported by the National Natural Science Foundation of China (U22A20204 and 52205018), the Fundamental Research Funds for the Central Universities, China (NP2022304).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Cao, J., Chen, B., Liu, K. (2023). Comparative Study of Feature-Based Surface Matching Automatic Coarse Registration Algorithms for Neuronavigation. In: Yang, H., et al. Intelligent Robotics and Applications. ICIRA 2023. Lecture Notes in Computer Science(), vol 14272. Springer, Singapore. https://doi.org/10.1007/978-981-99-6480-2_42
Download citation
DOI: https://doi.org/10.1007/978-981-99-6480-2_42
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-6479-6
Online ISBN: 978-981-99-6480-2
eBook Packages: Computer ScienceComputer Science (R0)