All
 
|
 
 


Refinement of the Coherent Point Drift Registration Results by the Example of Cephalometry Problems
 
PIIS013234740000681-4-1
DOI10.31857/S013234740000681-4
Publication type Article
Status Published
Authors
Dmitry Lachinov 
Affiliation: Lobachevsky State University of Nizhni Novgorod
Address: Russian Federation, Nizhni Novgorod
Vadim Turlapov
Affiliation: Institute of Information Technology, Mathematics and Mechanics, Lobachevsky State University of Nizhni Novgorod
Address: Russian Federation, Nizhni Novgorod
Alexandra Getmanskaya
Affiliation: Institute of Information Technology, Mathematics and Mechanics, Lobachevsky State University of Nizhni Novgorod
Address: Russian Federation, Nizhni Novgorod
Journal nameProgrammirovanie
EditionIssue 4
Pages55-66
Abstract

Personalizing the three-dimensional atlas model (template) of an organ under analysis based on the data of patient’s three-dimensional examination is an important task for modern digital medicine. The template should be represented by a set of points Y and marked with the key points for the model (landmarks). The template is personalized by the non-rigid registration of the set Y with the set of points X that represents patient’s tomogram. Presently, the coherent point drift (CPD) is the most popular method for solving the problem of non-rigid alignment. In this paper, we propose and explore an approach that substantially improves the CPD result in the problem of automatic registration of cephalometric points (CPs). The proposed algorithm remains robust in the presence of significant skull deformations. Traditionally, 3D cephalometry uses the geometric descriptor of a CP, which refines the position of the point on the bone surface. However, the result of applying the descriptor depends significantly on the accuracy of its anatomical basis reconstruction. The proposed approach solves this problem by clarifying the basis of geometric descriptors, the supporting elements of which are orbital planes and the Frankfurt (orbital-ear) horizontal. For this purpose, additionally marked points of the orbitals (YO) are included into the template Y. Once Y and X are aligned by the CPD method, the plane positions of the orbitals are refined by solving a linear regression problem on the subsets of YO for the left and right orbitals. Cases of refinement with and without use of Tikhonov regularization (ridge-regression) are analyzed. The effect of the increase in the cardinality of the set X relative to Y on the registration accuracy is investigated. It is found that the condition |X| < |Y| has a negative effect on the accuracy, which increases when the cardinality of X relative to Y decreases. The refinement of CPs by the geometric descriptor is carried out on tomogram data in the region around CPs that is found by the CPD method. The dimensions of this region along three coordinates are determined by the anatomical domain of a particular CP descriptor. The quality of the algorithm is measured by the Euclidean distance between hand-marked and automatically found points. The template Y for the algorithm is built on a trauma-deformed skull. The algorithm is quantitatively verified by registering the CPs of orbitals and cheekbones from the data of four tomograms for the deformed skull. A key feature and source of high accuracy of the approach is the use of linear regression with Tikhonov regularization to refine it. As a result, 81.25% of the points found fall within a radius of 2 mm from the hand-marked points and 100% of the points fall within a radius of 4 mm.

Keywords
Received01.10.2018
Publication date07.10.2018
Number of characters2616
Cite   Download pdf To download PDF you should sign in
Размещенный ниже текст является ознакомительной версией и может не соответствовать печатной

views: 1295

Readers community rating: votes 0 

1. Myronenko A., Song X., Carreira-Perpinan M.A. Non-rigid point set registration: Coherent Point Drift / NIPS 2007 Proceedings, pp. 1009–1016.
2. Myronenko A., Song X. Point set registration: Coherent point drift, IEEE transactions on pattern analysis and machine intelligence, 2010, vol. 32, no. 12, pp. 2262–2275.
3. Jacobson A., Jacobson R.L. Radiographic Cephalometry: From Basics to Videoimaging, Quintessence Pub., 1995, pp. 53–63.
4. Yue W., Yin D., Li C., Wang G., Xu T. Automated 2-D cephalometric analysis on X-ray images by a model-based approach, IEEE Trans Biomed Eng 2006, vol. 53, no. 8, pp. 1615–1623.
5. Chu C. et al. Fully automatic cephalometric x-ray landmark detection using random forest regression and sparse shape composition, Proc. ISBI 2014: Automatic Cephalometric X-Ray Landmark Detection Challenge, 2014. 8 p.
6. Wang C.-W. Evaluation and Comparison of Anatomical Landmark Detection Methods for Cephalometric X-Ray Images: A Grand Challenge, IEEE Transactions on Medical Imaging, 2015, 11 p.
7. Swennen G.R.J., Schutyser F., Hausamen J.-E. Three-Dimensional Cephalometry / A Color Atlas and Manual. Springer-Verlag, Berlin, Heidelberg, 2006, pp. 116–185.
8. Shahidi S, Bahrampour E, Soltanimehr E, Zamani A, Oshagh M, Moattari M, Mehdizadeh A. The accuracy of a designed software for automated localization of craniofacial landmarks on CBCT images, BMC Med. Imaging, 2014, vol. 14, no. 1, pp. 1471–2342.
9. Gupta A., Kharbanda O.P., Sardana V., Balachandran R., Sardana H.K. A knowledgebased algorithm for automatic detection of cephalometric landmarks on CBCT images, International journal of computer assisted radiology and surgery, 2015 1 November, vol. 10, no. 11, pp. 1737–1752.
10. Koch M. et al. (2013) Towards Deformable Shape Modeling of the Left Atrium Using Non-Rigid Coherent Point Drift Registration. Meinzer HP (eds) Bildverarbeitung fur die Medizin 2013. Informatik aktuell. Springer, Berlin, Heidelberg, 2013, pp. 332–337.
11. Delavari M., Foruzan A.H., Chen Y.-W. Improvement of statistical shapemodels for soft tissues using modified-coherent point drift, IFAC-PapersOnLine, 2015, vol. 48, pp. 36–41.
12. Peng L., Li G., Xiao M., Xie L. Robust CPD Algorithm for Non-Rigid Point Set Registration Based on Structure Information, Public Library of Science (PLOS) One, Feb 2016, vol. 11, no. 2, pp. 1–17.
13. Mansoory M.S., Allahverdy A., Jafari A.H. Mitral Valve Prolapse Classification from an Echocardiography Sequence using Coherent Point Drift Method based on Fractal Dimension, Journal of Biomedical Physics and Engineering, 2016.
14. Ravikumar N., Gooya A., Frangi A.F. and Taylor Z.A. Generalised coherent point drift for group-wise registration of multi-dimensional point sets, International Conference on Medical Image Computing and Computer-Assisted Intervention. Medical Image Computing and Computer Assisted Intervention — MICCAI 2017 , September 11–13, 2017, Quebec City, QC, Canada. Lecture Notes in Computer Science (10433). Springer, pp. 309–316.
15. Gadomski P.J. Measuring Glacier Surface Velocities With LiDAR: A Comparison of Three-Dimensional Change Detection Methods / Master’s thesis, University of Houston, Geosensing Systems Engineering and Sciences. (December 2016). https://www.researchgate.net/publication/  /315773214_Measuring_Glacier_Surface_ _Velocities_With_LiDAR_A_Comparison_of_ _Three-Dimensional_Change_ Detection_ _Methods
16. Senyukova O.V., Zubov A.Yu. Polnaya anatomicheskaya razmetka izobrazhenij magnitnorezonansnoj tomografii golovnogo mozga s pomosch'yu sopostavleniya s neskol'kimi atlasami // Programmirovanie, 2016, № 6, c. 35–41.
17. Khvostikov A.V., Krylov A.S., Kamalov Yu.R. Teksturnyj analiz ul'trazvukovykh izobrazhenij dlya diagnostirovaniya fibroza pecheni // Programmirovanie, 2015, № 5, c. 39–46.
18. Tikhonov A.N. O nekorrektnykh zadachakh linejnoj algebry i ustojchivom metode ikh resheniya // Doklady Akademii nauk SSSR, 1965, t. 163, № 3, c. 97–102.
19. Lindeberg T. Scale Selection Properties of Generalized Scale-Space Interest Point Detectors, J. Math. Imaging Vis., 2013, vol. 46, no. 2, pp. 177–210.
20. Kharinov M.V. Klasterizatsiya pikselej dlya segmentatsii tsvetovogo izobrazheniya // Programmirovanie, 2015, № 5, c. 20–30.
21. Garilov N.I., Turlapov V.E. Novyj podkhod k razrabotke algoritmov ob'emnogo renderinga na osnove izmereniya kachestva vizualizatsii // Programmirovanie. 2014, № 4, c. 23–36.
22. Mamaev N.V., Lukin A.S., Yurin D.V. HeNLMLA: Lokal'no-adaptivnyj algoritm nelokal'nogo srednego na osnove razlozheniya po funktsiyam Ehrmita // Programmirovanie, 2014, № 4, c. 46–54.

Система Orphus

Loading...
Up