张量模式三维主动外观模型及其在肺CT图像分割中的应用<sup>*</sup>

doi:10.16451/j.cnki.issn1003-6059.201508011

Abstract
Figure/Table
References
Related Citation (2)

Download: PDF (1461 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract In the existing 3D active appearance model (AAM), a 3D appearance matrix must be transformed into a 1D vector. Thus, the segmentation accuracy is affected by the transformation and the segmentation efficiency is affected by the generated oversize vector. For the above problems, a 3D tensor based AAM is proposed aiming at direct operating on 3D appearances of lungs by higher order singular value decomposition, rather than transforming it from 3D to 1D. Firstly, the tensor-based model is built and the parameters are deduced. Then, a block-based Kronecker is designed to determine the optimal scheme for low rank representation of appearance tensors. This optimization avoids repeated computation. Finally, the whole segmentation system is constructed and used in the segmentation of lung images. Experimental results of clinical CT images are compared to other 3D landmark-based methods. The proposed model performs a better result in both precision and efficiency.

Key words： Computer-Aided Diagnosis Tensor Technology Active Appearance Model Higher Order Singular Value Decomposition

Received: 24 July 2014

ZTFLH:	TP 18
	TP 391

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	WANG Qing-Zhu
	SUN Na
	WANG Bin

Cite this article:

WANG Qing-Zhu,SUN Na,WANG Bin. Three-Dimensional Active Appearance Model Based on Tensor Mode andIts Application in Lung Field Segmentation from CT Images[J]. , 2015, 28(8): 750-759.

URL:

http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.201508011 OR http://manu46.magtech.com.cn/Jweb_prai/EN/Y2015/V28/I8/750

[1] Lee S L A, Kouzani A Z, Hu E J. Automated Detection of Lung Nodules in Computed Tomography Images: A Review. Machine Vision and Applications, 2012, 23(1): 151-163
[2] Kass M, Witkin A, Terzopoulos D. Snakes-Active Contour Models. International Journal of Computer Vision, 1987, 1(4): 321-331
[3] Cootes T F, Taylor C J, Cooper D H, et al. Active Shape Models: Their Training and Application. Computer Vision and Image Understanding, 1995, 61(1): 38-59
[4] Cootes T F, Edwards G J, Taylor C J. Active Appearance Models. IEEE Trans on Pattern Analysis and Machine Intelligence, 2001, 23(6): 681-685
[5] Cootes T F, Edwards G J, Taylor C J, et al. Comparing Active Shape Models with Active Appearance Models // Proc of the British Machine Vision Conference. Nottingham, UK, 1999, I: 173-182
[6] Li B, Acton S T. Active Contour External Force Using Vector Field Convolution for Image Segmentation. IEEE Trans on Image Proce-ssing, 2007, 16(8): 2096-2106
[7] Li B, Acton S T. Automatic Active Model Initialization via Poisson Inverse Gradient. IEEE Trans on Image Processing, 2008, 17(8):1406-1420
[8] Qin L M, Zhu C, Zhao Y, et al. Generalized Gradient Vector Flow for Snakes: New Observations, Analysis, and Improvement. IEEE Trans on Circuits and Systems for Video Technology, 2013, 23(5): 883-897
[9] Sukno F M, Ordas S, Butakoff C, et al. Active Shape Models with Invariant Optimal Features: Application to Facial Analysis. IEEE Trans on Pattern Analysis and Machine Intelligence, 2007, 29(7): 1105-1117
[10] Xu T, Mandal M, Long R, et al. An Edge-Region Force Guided Active Shape Approach for Automatic Lung Field Detection in Chest Radiographs. Computerized Medical Imaging and Graphics, 2012, 36(6): 452-463
[11] Liu J M, Udupa J K. Oriented Active Shape Models. IEEE Trans on Medical Imaging, 2009, 28(4): 571-584
[12] Ibragimov B, Likar B, Permus F, et al. A Game-Theoretic Framework for Landmark-Based Image Segmentation. IEEE Trans on Image Processing, 2012, 31(9): 1761-1776
[13] Sun S H, Bauer C, Beichel R. Automated 3-D Segmentation of Lungs with Lung Cancer in CT Data Using a Novel Robust Active Shape Model Approach. IEEE Trans on Medical Imaging, 2012, 31(2): 449-460
[14] Tobon-Gomez C, Sukno F M, Butakoff C, et al. Automatic Trai-ning and Reliability Estimation for 3D ASM Applied to Cardiac MRI Segmentation. Physics in Medicine and Biology, 2012, 57(13): 4155-4174
[15] Wang Q Z, Kang W W, Wang B. Design of Two-Dimensional Mahalanobis Distance Based on ASM and Application in Lung Segmentation. Journal of Computational Information Systems, 2014, 10(16): 7027-7034
[16] Tobon-Gomez C, Butakoff C, Aguade S, et al. Automatic Construction of 3D-ASM Intensity Models by Simulating Image Acquisition: Application to Myocardial Gated SPECT Studies. IEEE Trans on Medical Imaging, 2008, 27(11): 1655-1667
[17] Lekadir K, Merrifield R, Yang G Z. Outlier Detection and Hand-ling for Robust 3D Active Shape Models Search. IEEE Trans on Medical Imaging, 2007, 26(2): 212-222
[18] Chen X J, Udupa J K, Bagci U, et al. Medical Image Segmentation by Combining Graph Cuts and Oriented Active Appearance Models. IEEE Trans on Imaging Processing, 2012, 21(4): 2035-2046
[19] Hu S Y, Colins D L. Joint Level-Set Shape Modeling and Appea-rance Modeling for Bra Structure Segmentation. NeuroImage, 2007, 36(3): 672-683
[20] Larsen R, Stegmann M B, Darkner S, et al. Texture Enhanced Appearance Models. Computer Vision and Image Understanding, 2007, 106 (1): 20-30
[21] Baka N, Milles J, Hendriks E A, et al. Segmentation of Myocar-dial Perfusion MR Sequences with Multi-band Active Appearance Models Driven by Spatial and Temporal Features. Proceedings of SPIE, 2008, 6914(3): 691415.1-691415.10
[22] Toth R, Madabhushi A. Multifeature Landmark-Free Active Appearance Models: Application to Prostate MRI Segmentation. IEEE Trans on Medical Imaging, 2012, 31(8): 1638-1650
[23] Toth R, Ribault J, Gentile J, et al. Simultaneous Segmentation of Prostatic Zones Using Active Appearance Models with Multiple Coupled Levelsets. Computer Vision and Image Understanding, 2013, 117(9): 1051-1060
[24] Yang J, Zhang D, Frangi A F, et al. Two-Dimensional PCA: A New Approach to Appearance-Based Face Representation and Re-cognition. IEEE Trans on Pattern Analysis and Machine Intelligence, 2004, 26(1): 131-137
[25] Chen Y L, Hsu C T. Multilinear Graph Embedding: Representation and Regularization for Images. IEEE Trans on Image Proce-ssing, 2013, 23(2): 741-754
[26] Rajwade A, Rangarajan A, Banerjee A. Image Denoising Using the Higher Order Singular Value Decomposition. IEEE Trans on Pattern Analysis and Machine Intelligence, 2012, 35(4): 849-862
[27] Hou C P, Nie F P, Zhang C S, et al. Multiple Rank Multi-linear
SVM for Matrix Date Classification. Pattern Recognition, 2014, 47(1): 454-469
[28] Wang Q Z, Kang W W, Wu C M, et al. Computer-Aided Detection of Lung Nodules by SVM Based on 3D Matrix Patterns. Clinical Imaging, 2013, 37(1): 62-69
[29] de Lathauwer L, de Moor B, Vandewalle J. A Multilinear Singular Value Decomposition. SIAM Journal on Matrix Analysis and Application, 2000, 21(4): 1253-1278
[30] Vannieuwenhoven N, Vandebril R, Meerbergen K. A New Truncation Strategy for the Higher-Order Singular Value Decomposition. SIAM Journal on Scientific Computing, 2012, 34(2): A1027-A1052
[31] Kroon D J. Active Shape Model (ASM) and Active Appearance Model (AAM)[EB/OL]. [2014-02-25]. http://www.mathworks.cn/matlabcentral/fileexchange/26706-active-shape-model-asm-and-active-appearance-m
[32] Tomoshige S, Oost E, Shimizu A, et al. A Conditional Statistical Shape Model with Integrated Error Estimation of the Conditions: Application to Liver Segmentation in Non-contrast CT Images. Medical Image Analysis, 2014, 18(1): 130-143