نوع مقاله : مقاله کامل پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد مهندسی پزشکی، گروه مهندسی پزشکی، دانشکده فنی و مهندسی، دانشگاه شاهد، تهران، ایران

2 استادیار، گروه مهندسی پزشکی، دانشکده فنی و مهندسی، دانشگاه شاهد، تهران، ایران

3 استاد، دانشکده علوم انفورماتیک و مهندسی، دانشگاه ریتسومیکان، شیگا، ژاپن

10.22041/ijbme.2014.13287

چکیده

مدل­های شکل آماری، از اطلاعات آماری جهت تفسیر و بررسی شکل استفاده می­کنند. اطلاعات آماری شامل میانگین و واریانس نقاط متناظر شکل­های مجموعه آموزش است. یافتن نقاط متناظر دربین نقاط اعضای مجموعه­ی آموزش، یکی­از چالش­های مهم در ساخت مدل شکل آماری است. درین مقاله، از روش CPDجهت یافتن تناظر بین نقاط استفاده شد. درین روش، با ترکیب تناظر فازی، الگوریتم سرد شدن معین و انطباق غیرصلب دو شکل، تناظر بین نقاط به دست آمد. پس­از یافتن نقاط متناظر، مدل شکل آماری با یک تبدیل صلب ایجاد شد. ارزیابی روش پیشنهادی با استفاده­از میزان فشردگی، قابلیّت تعمیم و اختصاصی بودن  انجام شد. مدل ساخته شده به کمک روش پیشنهادی با مدل­های ساخته شده به روش­های TPS-RPM، ICP ،MDL   مقایسه شد. نتایج نشان می­دهد که مدل پیشنهادی در معیار اختصاصی بودن با مقدار 06/0±21/0 مانند روش MDL عمل می­کند. در مورد معیارهای فشردگی و قابلیت تعمیم، نتایج به دست آمده با روش MDL مشابهت دارد. زمان متوسط اجرای الگوریتم در روش پیشنهادی 68 ثانیه است، در صورتی­که برای الگوریتم TPS-RPM390 ثانیه و برای الگوریتم MDL 3600 ثانیه است که برتری روش پیشنهادی را از نظر سرعت نشان می­دهد. هم­چنین در روش پیشنهادی، نسبت به روش­های ICP وTPS-RPM عملکرد بهتری به دست آمد.
 

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Improvement of Statistical Shape Models for Non-rigid Tissues Using Coherent Point Drift Algorithm

نویسندگان [English]

  • Mehdi Delavari 1
  • Amir Hosein Foruzan 2
  • Ben Vi Chen 3

1 MS Student, Biomedical Engineering Department, Engineering Faculty, Shahed University, Tehran, Iran

2 Assistant Professor, Biomedical Engineering Department, Engineering Faculty, Shahed University, Tehran, Iran

3 Professor, College of Information Science and Engineering, Ritsumeikan University, Shiga, Japan

چکیده [English]

Statistical Shape Models are used to interpret shapes. They include mean and variance of corresponding points of training shapes. One of the most important challenges in building statistical shape models is to establish correct correspondences among landmarks in a training set.  In this paper, the non-rigid CPD (Coherent Point Drift) method is used to find correct correspondences among points. This method uses both Deterministic Annealing and a non-rigid scheme to register two shapes simultaneously. Then, the statistical shape model is built using a rigid transformation. The proposed method is evaluated using Compactness, Generalization ability and Specificity measures. The built model is compared to models created using the ICP (Iterative Closest Point), TPS-RPM (Thin Plate Spline – Robust Point Matching) and MDL (Minimum Descreption Length) methods by these metrics. The results show that the proposed method performs like the MDL regarding Specificity measure (0.21±0.06). The Compactness and Generalization ability measures of the proposed method are very similar to those for the MDL method. The run-time of our proposed method is about 68 seconds which is faster than non-rigid TPS-RPM and MDL approaches (390 and 3600 seconds respectively). Our results are superior to the ICP and TPS-RPM algorithms.

کلیدواژه‌ها [English]

  • Coherent Point Drift
  • Corresponding points
  • Liver shape model
  • Medical image registration
  • Statistical shape models
[1]     T. Heimann, M. Hans-Peter, “Statistical shape models for 3D medical image segmentation: A review” Medical image analysis 13 (4): 543-56, 2009.
[2]     T. F. Cootes, C. J. Taylor, D. H. Cooper, J. Graham, “Active shape models-their training and application” Computer vision and image understanding 61 (1): 38-59, 1995.
[3]     S. I. Buchaillard, S. H. Ong, Y. Payan, K. Foong, “3D statistical models for tooth surface reconstruction” Original Research Article Computers in Biology and Medicine 37 (10): 1461-1471, 2007.
[4]     A. Pepe, L. Zhao, J. Koikkalainen, J. Hietala, U. Ruotsalainen, J. Tohka, “Automatic statistical shape analysis of cerebral asymmetry in 3D T1-weighted magnetic resonance images at vertex-level: Application to neuroleptic-naïve schizophrenia” Magnetic Resonance Imaging 31 (5): 676-687, 2013.
[5]     M. Koch, S. Bauer, J. Hornegger, N. Strobel, “Towards Deformable Shape Modeling of the Left Atrium Using Non-Rigid Coherent Point Drift Registration” Bildverarbeitung für die Medizin 332-337, 2013.
[6]     S. F. Roohi, R. A. Zoroofi, “4D statistical shape modeling of the left ventricle in cardiac MR images; Int. J. Comput. Assist” Radiol Surg 8 (3): 335-351, 2013.
[7]     A. Suinesiaputra, A. F. Frangi, T. Kaandorp, H. J. Lamb, “Automated Detection of Regional Wall Motion Abnormalities Based on a Statistical Model Applied to Multislice Short-Axis Cardiac MR Images; IEEE Trans” On Medical Imaging 28 (4): 595-607, 2009.
[8]     T. Okada, M. Linguraru, Y. Yoshida, M. Hori, R. M. Summers, Y. W. Chen, N. Tomiyama, Y. Sato, “Abdominal multi-organ segmentation of CT images based on hierarchical spatial modeling of organ interrelations” Abdominal imaging, computational and clinical applications 7029: 173–180, 2012
[9]     H. Hufnagel, X. Pennec, J. Ehrhardt, N. Ayache, H. Handels, “Computation of a probabilistic statistical shape model in a maximum-a-posteriori framework Methods” Inf Med 48 (4): 314-319, 2009.
[10] H. Yipeng, “A comparison of the accuracy of statistical models of prostate motion trained using data from biomechanical simulations” Progress in Biophysics and Molecular Biology 103: 262-272, 2010.
[11] N. Baka, B. L. Kaptein, M. Bruijne, T. Walsum, J. E. Giphart, W. J. Niessen, B. P. F. Lelieveldt, “2D–3D shape reconstruction of the distal femur from stereo X-ray imaging using statistical shape models” Medical Image Analysis 15 (6): 840-850, 2011.
[12] M. Becker, M. Kirschner, S. Fuhrmann, S. Wesarg, “Automatic construction of statistical shape models for vertebrae” Med. Image Comput. Assist Interv 14 (2): 500-507, 2011.
[13] H. Davies Rhodri, “Learning shape: optimal models for analysing shape variability” PhD diss, PhD thesis, University of Manchester, 2002.
[14] H. Chui, A. Rangarajan, “A new point matching algorithm for non-rigid registration” Computer Vision and Image Understanding 89 (2-3): 114–141, 2003.
[15] A. Sotiras, C. Davatzikos, N. Paragios, “Deformable Medical Image Registration: A Survey” IEEE Transaction on Medical Imaging 32 (7): 1153-1190, 2013.
[16] F. Maes, D. Vandermeulen, A. Suetens, “Medical Image Registration Using Mutual Information” Proceedings of the IEEE 91 (10): 1699-1722, 2003.
[17] L. S. Hibbard, R. A. Hawkins, “Objective image alignment for three dimensional reconstruction of digital autoradiograms” Journal of neuroscience methods 26: 55-74, 1988.
[18] D. H. Ballard, “Generalizing the Hough transform to detect arbitrary shapes” Pattern recognition 13: 111-122, 1981.
[19] H. Baird, “Model-based image matching using location” MIT Press, Cambridge, 1984.
[20] D. P. Huttenlocher, G. A. Klanderman, W.J. Rucklidge, “Comparing images using the Hausdorff distance” IEEE Trans Patt Anal Mach Intell 15 (9): 850–863, 1993.
[21] D. Cross, E. R. Hancock, “Graph matching with a dual-step EM algorithm” IEEE Transactions on Pattern Analysis and Machine Intelligence 20: 1236-1253, 1998.
[22] M. Koch, S. Bauer, J. Hornegger, N. Strobel, “Towards Deformable Shape Modeling of the Left Atrium Using Non-Rigid Coherent Point Drift Registration” Bildverarbeitung für die Medizin 332-337, 2013.
[23] G. Niculescu, D. Forand, J. Nosher, “Non-rigid registration of the liver in consecutive CT studies for assessment of tumor response to radiofrequency ablation 29th Annual International Conference of the IEEE in Engineering in Medicine and Biology Society 856-859, 2007.
[24] J. Hermans, D. Smeets, D. Vandermeulen, P. Suetens, “Robust point set registration using EM-ICP with information-theoretically optimal outlier handling” IEEE Conference on Computer Vision and Pattern Recognition 2465–2472, 2011.
[25] S. Du, N.Zheng, G. Meng, Z. Yuan, “Affine Registration of Point Sets Using ICP and ICA” IEEE Signal Processing Letters 15: 689-692, 2008.
[26] F. L. Bookstein, “Principal warps: Thin-plate splines and the decomposition of deformations” IEEE Trans Pattern Anal Mach Intell 11 (6): 567–585, 1989.
[27] T. K. Moon, “The expectation-maximization algorithm” IEEE Signal Processing Magazine 13 (6): 47-60, 1996.
[28] T. Hofmann, J. M. Buhmann, “Pairwise data clustering by deterministic annealing” IEEE Trans Patt Anal Mach Intell 19 (1): 1–14, 1997.
[29] C. Mourning, et al. “GPU Acceleration of Robust Point Matching” Advances in Visual Computing Lecture Notes in Computer Science 6455: 417-426, 2010.
[30] A. Myronenko, X. Song, “Point Set Registration: Coherent Point Drift” TPAMI 32 (12): 2262–2275, 2010.
[31] A. L. Yuille, N. M. Grzywacz, “The motion coherence theory” Int J Computer Vision 3: 344-353, 1988.
[32] R. Davies, et al. “Building optimal 2D statistical shape models” Image ans. vision computing 21: 1171-1182, 2003.
[33] R. Davies, C. J. Twining, T. F. Cootes, J. C. Waterton, C. J. Taylor, “A minimum description length approach to statistical shape modeling” IEEE Transactions on Medical Imaging 21 (5): 525-537, 2002.
[34] A. H. Foruzan, et al. “Segmentation of Liver in Low-Contrast Images Using K-Means Clustering and Geodesic Active Contour Algorithms” IEICE TRANSACTIONS on Information and Systems E96-D (4): 798-807, 2013.
[35] W. E. Lorensen, H. E. Cline, “Marching Cubes: A high resolution 3D surface construction algorithm” Computer Graphics 21 (4): 163-169, 1987.
[36] J. C. Gower, “Generalized procrustes analysis” Psychometrika 40 (1): 33-51, 1975.
[37] T. Heimann, et al. “Optimal landmark distributions for statistical shape model construction” Proc. SPIE Medical Imaging: Image Processing 6144: 518-528, 2006.
[38] R. XU, et al. “Improvement of MDL method by adaptive sampling on spherical parameter space” IEICE 111 (389): 173-178, 2012.
[39] H. A. Foruzan, Y. W. Chen, M. Hori, Y. Sato, N. Tomiyama, “Capturing  large  shape  variations  of  liver using  population-based  statistical  shape  models” International Journal of Computer Assisted Radiology and Surgery 9 (6): 967-977, 2014.