Abstract
We propose an algorithm for rigid registration of pre- and intra-operative patient anatomy, represented as pointclouds, during minimally invasive surgery. This capability is essential for development of augmented reality systems for guiding such interventions. Key challenges in this context are differences in the point density in the pre- and intra-operative pointclouds, and potentially low spatial overlap between the two. Solutions, correspondingly, must be robust to both of these phenomena. We formulated a pointclouds registration approach which considers the pointclouds after rigid transformation to be observations of a global non-parametric probabilistic model named Dirichlet Process Gaussian Mixture Model. The registration problem is solved by minimizing the Kullback–Leibler divergence in a variational Bayesian inference framework. By this means, all unknown parameters are recursively inferred, including, importantly, the optimal number of mixture model components, which ensures the model complexity efficiently matches that of the observed data. By presenting the pointclouds as KDTrees, both the data and model are expanded in a coarse-to-fine style. The scanning weight of each point is estimated by its neighborhood, imparting the algorithm with robustness to point density variations. Experiments on several datasets with different levels of noise, outliers and pointcloud overlap show that our method has a comparable accuracy, but higher efficiency than existing Gaussian Mixture Model methods, whose performance is sensitive to the number of model components.
Similar content being viewed by others
References
Besl P, McKay ND (1992) A method for registration of 3-D shapes. IEEE Trans Pattern Analy Mach Intel 14(2):239–256. https://doi.org/10.1109/34.121791
Rusu RB, Blodow N, Beetz M (2009) Fast point feature histograms (FPFH) for 3D registration. In: IEEE Int Conf Robot Autom. IEEE, pp 3212–3217, https://doi.org/10.1109/ROBOT.2009.5152473, http://ieeexplore.ieee.org/document/5152473/
Yang J, Li H, Campbell D et al. (2016) Go-ICP: a globally optimal solution to 3D ICP point-set registration. IEEE Trans Pattern Analy Mach Intel 38(11):2241–2254. https://doi.org/10.1109/TPAMI.2015.2513405
Raguram R, Frahm JM, Pollefeys M (2008) A comparative analysis of RANSAC techniques leading to adaptive real-time random sample consensus. In: European Conference on Computer Vision, Springer, pp 500–513
Ma J, Zhao J, Tian J et al. (2014) Robust point matching via vector field consensus. IEEE Trans Image Process 23(4):1706–1721. https://doi.org/10.1109/TIP.2014.2307478
Ma J, Zhao J, Jiang J et al. (2019) Locality preserving matching. Int J Comput Vision 127(5):512–531. https://doi.org/10.1007/s11263-018-1117-z
Zhou QyY, Park J, Koltun V (2016) Fast Global Registration. In: Proceedings of the European Conference on Computer Vision, p 766–782, https://doi.org/10.1007/978-3-319-46475-6_47
Maiseli B, Gu Y, Gao H (2017) Recent developments and trends in point set registration methods. J Vis Commun Image Represent 46:95–106. https://doi.org/10.1016/j.jvcir.2017.03.012
Myronenko A, Song Xubo (2010) Point set registration: coherent point drift. IEEE Trans Pattern Analy Mach Intel 32(12):2262–2275. https://doi.org/10.1109/TPAMI.2010.46
Gao W, Tedrake R (2019) FilterReg: robust and efficient probabilistic point-set registration using Gaussian filter and twist parameterization. Proc IEEE Conf Comput Vis Pattern Recognit 1:11095–11104
Adams A, Baek J, Davis MA (1981) Fast high-dimensional filtering using the permutohedral lattice. Comput Graphics Forum. https://doi.org/10.1111/j.1467-8659.2009.01645.x
Jiayi M, Ji Z, Yuille AL (2016) Non-rgid point set registration by preserving global and local structures. IEEE Trans Image Process 25(1):53–64. https://doi.org/10.1109/TIP.2015.2467217
Hirose O (2020) A Bayesian formulation of coherent point drift. IEEE Trans Pattern Analy Mach Intel. https://doi.org/10.1109/TPAMI.2020.2971687
Eckart B, Kelly A (2013) REM-Seg: a robust em algorithm for parallel segmentation and registration of point clouds. In: IEEE International Conference on Intelligent Robots and Systems, p 4355–4362, https://doi.org/10.1109/IROS.2013.6696981
Eckart B, Kim K, Troccoli A, et al. (2015) MLMD: maximum likelihood mixture decoupling for fast and accurate point cloud registration. In: Proceedings of international conference on 3D vision, 3DV 2015, p 241–249, https://doi.org/10.1109/3DV.2015.34
Eckart B, Kim K, Kautz J (2018) HGMR: hierarchical Gaussian mixtures for adaptive 3D registration. In: Proceedings of the European conference on computer vision, vol 11219 LNCS. p 730–746, https://doi.org/10.1007/978-3-030-01267-0_43, http://link.springer.com/10.1007/978-3-030-01267-0_43
Evangelidis GD, Kounades-Bastian D, Horaud R, et al. (2014) A generative model for the joint registration of multiple point sets. In: Cham (ed) European conference on computer vision, vol 8695 LNCS. Springer, p 109–122, https://doi.org/10.1007/978-3-319-10584-0_8
Meng XL, Rubin DB (1993) Maximum likelihood estimation via the ECM algorithm: a general framework. Biometrika 80(2):267–278
Danelljan M, Meneghetti G, Khan FS, et al. (2016) A probabilistic framework for color-based point set registration. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition 2016 Dec, p 1818–1826. https://doi.org/10.1109/CVPR.2016.201
Lawin FJ, Danelljan M, Khan FS, et al. (2018) Density adaptive point set registration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, p 3829–3837
Ravikumar N, Gooya A, Çimen S, et al. (2016) A multi-resolution T-mixture model approach to robust group-wise alignment of shapes. In: International conference on medical image computing and computer-assisted intervention, lecture notes in computer science, vol 9902. Springer International Publishing, p 142–149, https://doi.org/10.1007/978-3-319-46726-9_17
Ravikumar N, Gooya A, Çimen S et al. (2018) Group-wise similarity registration of point sets using student’s t-mixture model for statistical shape models. Med Image Anal 44:156–176. https://doi.org/10.1016/j.media.2017.11.012
Ravikumar N, Gooya A, Frangi AF et al. (2017) Generalised coherent point drift for group-wise registration of multi-dimensional point sets. In: Descoteaux M, Maier-Hein L, Franz A et al. (eds) International conference on medical image computing and computer-assisted intervention, vol 10433. Lecture notes in computer science. Springer International Publishing, Cham, pp 309–316
Ravikumar N, Gooya A, Beltrachini L et al. (2019) Generalised coherent point drift for group-wise multi-dimensional analysis of diffusion brain MRI data. Med Image Anal 53:47–63. https://doi.org/10.1016/j.media.2019.01.001
Zhang M, Yang C, Wei L et al. (2017) Non-rigid point set registration via coherent spatial mapping and local structures preserving. Proceedings–15th international symposium on parallel and distributed computing. ISPDC 2016:382–385. https://doi.org/10.1109/ISPDC.2016.64
Ma J, Wu J, Zhao J et al. (2019) Nonrigid point set registration with robust transformation learning under manifold regularization. IEEE Trans Neural Netw Learn Syst 30(12):3584–3597. https://doi.org/10.1109/TNNLS.2018.2872528
Yang Y, Ong SH, Foong KWC (2015) A robust global and local mixture distance based non-rigid point set registration. Pattern Recogn 48(1):156–173. https://doi.org/10.1016/j.patcog.2014.06.017
Chen J, Ma J, Yang C et al. (2015) Non-rigid point set registration via coherent spatial mapping. Signal Process 106:62–72. https://doi.org/10.1016/j.sigpro.2014.07.004
Peterlík I, Courtecuisse H, Rohling R et al. (2018) Fast elastic registration of soft tissues under large deformations. Med Image Anal 45:24–40. https://doi.org/10.1016/j.media.2017.12.006
Kondarasaiah MH, Ananda S (2006) Pattern recognition and machine learning, vol 27
Campbell D, Petersson L (2015) An adaptive data representation for robust point-set registration and merging. Proceedings of the IEEE International Conference on Computer Vision 2015 Inter:4292–4300. https://doi.org/10.1109/ICCV.2015.488, arXiv:1511.04240
Greengard L, Strain J (1991) The fast Gauss transform. SIAM J Sci Stat Comput 12(1):79–94
Yang C, Duraiswami R, Gumerov NA, et al. (2003) Improved fast gauss transform and efficient kernel density estimation. IEEE
Williams CKI, Seeger M (2001) Using the Nyström method to speed up kernel machines. In: Advances in neural information processing systems, p 682–688
Bentley JL (1975) Multidimensional binary search trees used for associative searching. Commun ACM 18(9):509–517
Hemant I, Lancelot FJ (2001) stickBreaking. J Am Stat Assoc 96:453
Kurihara K, Welling M, Vlassis N (2007) Accelerated variational Dirichlet process mixtures. Adv Neural Info Process Syst. https://doi.org/10.7551/mitpress/7503.003.0100
Theiler PW, Wegner JD, Schindler K (2015) Globally consistent registration of terrestrial laser scans via graph optimization. ISPRS J Photogramm Remote Sens 109:126–138. https://doi.org/10.1016/j.isprsjprs.2015.08.007
Funding
This work was supported by grants from National Key R &D Program of China (2022YFE0197900), the National Natural Science Foundation of China (81971709; M-0019; 82011530141), the Foundation of Science and Technology Commission of Shanghai Municipality (20490740700),Shanghai Jiao Tong University Foundation on Medical and Technological Joint Science Research (YG2021ZD21; YG2021QN72; YG2022QN056), the Hospital Funded Clinical Research by Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine (21XJMR02), 2020 Key Research Project of Xiamen Municipal Government (3502Z20201030), and the Royal Academy of Engineering Leverhulme Trust Research Fellowships programme (LTRF2021-17115).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
All of these authors have no conflict of interest.
Informed consent
Informed consent was obtained from all individual participants included in the study.
Appendix A: some derivations and positive semidefinite rotation matrix objective function
Appendix A: some derivations and positive semidefinite rotation matrix objective function
-
1.
Derivation of \(q^{\star }(v_k)\)
Equation 10 in Sect. "Variational inference of Dirichlet Process Gaussian Mixture Model" is deduced as follows:
-
2.
Derivation of \(\rho _{ij,k}\) involved in the update of \(q^{\star }({\varvec{Z}})\).
-
3.
The derivation of the objective function to solve the rigid transformation between input pointclouds and the global coordinate system.
-
4.
Positive semidefinite rotation matrix objective function. By replacing the rotation matrix \({\textbf{R}}_i\) with its vector representation \({\textbf{r}}_i=\textrm{Vec}({\textbf{R}}_i)\), \({\textbf{r}}_i \in {\mathcal {R}}^{9\times 1}\), the objective function Eq. 20 for solving the rotation matrix can be recast in the general form:
The orthogonality constraints \({\textbf{R}}_i{\textbf{R}}_i^{\textrm{T}}={\textbf{I}}\) similarly become:
Here \(\delta _{kl}=1\) when \(k=l\), otherwise \(\delta _{kl}=0\). \(\Delta _{kl}\) are six symmetric \(9\times 9\) matrices, that can be easily obtained from \({\textbf{R}}_i{\textbf{R}}_i^{\textrm{T}}={\textbf{I}}\).
To eliminate the first order term \(2{\textbf{b}}^{\textrm{T}}{\textbf{r}}_i\) in \({\textbf{r}}_i\), we let \(\mathbf {r'}_i=\{r_i[1],r_i[2],....,r_i[9],1\}\), so that Eq. A4 can be rewritten as
in which
The constraints are then reformulated as:
with
Finally, the optimized problem of solving the rotation matrix \({\textbf{R}}_i\) can be formulated in the standard positive semidefinite optimization problem form as:
Once \({\rho }_i\) is solved, \({\textbf{r}}_i\) is obtained as \({\textbf{r}}_i={\rho }_i[1:9,10]\).
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Jia, T., Taylor, Z.A. & Chen, X. Density-adaptive registration of pointclouds based on Dirichlet Process Gaussian Mixture Models. Phys Eng Sci Med 46, 719–734 (2023). https://doi.org/10.1007/s13246-023-01245-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13246-023-01245-4