Abstract
Purpose
Statistical shape models have shown improved reliability and consistency in cardiac image segmentation. They incorporate a sufficient amount of a priori knowledge from the training datasets and solve some major problems such as noise and image artifacts or partial volume effect. In this paper, we construct a 4D statistical model of the left ventricle using human cardiac short-axis MR images.
Methods
Kernel PCA is utilized to explore the nonlinear variation of a population. The distribution of the landmarks is divided into the inter- and intra-subject subspaces. We compare the result of Kernel PCA with linear PCA and ICA for each of these subspaces. The initial atlas in natural coordinate system is built for the end-diastolic frame. The landmarks extracted from it are propagated to all frames of all datasets. We apply the 4D KPCA-based ASM for segmentation of all phases of a cardiac cycle and compare it with the conventional ASM.
Results
The proposed statistical model is evaluated by calculating the compactness capacity, specificity and generalization ability measures. We investigate the behavior of the nonlinear model for different values of the kernel parameter. The results show that the model built by KPCA is less compact than PCA but more compact than ICA. Although for a constant number of modes the reconstruction error is a little higher for the KPCA-based statistical model, it produces a statistical model with substantially better specificity than PCA- and ICA-based models.
Conclusion
Quantitative analysis of the results demonstrates that our method improves the segmentation accuracy.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
American Heart Association (2010) 2010 Heart and Stroke Statistical Update. [Online]. Available: http://www.americanheart.org
Frangi AF, Niessen WJ, Viergever MA (2001) Three-dimensional modeling for functional analysis of cardiac images: a review. IEEE Trans Medical Imaging 20(1): 2–25
Jolly MP, Xue H, Grady L, Gühring J (2009) Combining registration and minimum surfaces for the segmentation of the left ventricle in cardiac cine MR images. In: Proceedings MICCAI, LNCS 5762, pp 910–918
Cousty J, Najman L, Couprie M, Clément-Guinaudeau S, Goissen T, Garot J (2010) Segmentation of 4D cardiac MRI: automated method based on spatio-temporal watershed cuts. J Image Vis Comput 28(8): 1229–1243
Schaerer C, Casta C, Pousin J, Clarysse P (2010) A dynamic elastic model for segmentation and tracking of the heart in MR image sequences. Medical Image Anal 14(6): 738–749
Grande LC, Ferrero GVS, Higuera PC, Calvar JASR, Orodea AR, Fernández MM, López CA (2011) Unsupervised 4D myocardium segmentation with a Markov random field based deformable model. Medical Image Anal 15(3): 283–301
Zhuang X, Rhode KS, Razavi RS, Hawkes DJ, Ourselin S (2010) A registration-based propagation framework for automatic whole heart segmentation of cardiac MRI. IEEE Trans Medical Imaging 29(9): 1612–1625
Petitjean C, Dacher JN (2011) A review of segmentation methods in short axis cardiac MR images. Medical Image Anal 15(2): 169–184
Heimann T, Meinzer HP (2009) Statistical shape models for 3D medical image segmentation: a review. Medical Image Anal 13(4): 543–563
Rueckert D, Frangi AF, Schnabel JA (2003) Automatic construction of 3D statistical deformation models of the brain using non-rigid registration. IEEE Trans Medical Imaging 22(8): 1014–1025
Lorenzo-Valdes M, Sanchez-Ortiz GI, Elkington A, Mohiaddin R, Rueckert D (2004) Segmentation of 4D cardiac MR images using a probabilistic atlas and the EM algorithm. Medical Image Anal 8(3): 255–265
Pilgram R, Schubert R, Fritscher KD, Zwick RH, Schocke MF, Trieb T, Pachinger O (2006) Shape discrimination of healthy and diseased cardiac ventricles using medial representation. Int J CARS 1(1): 33–38
Cootes TF, Taylor CJ, Cooper DH, Graham J (1995) Active shape models: their training and application. Comput Vis Image Understand 61(1): 38–59
Frangi AF, Rueckert D, Schnabel JA, Niessen WJ (2002) Automatic construction of multiple-object three-dimensional statistical shape models: application to cardiac modeling. IEEE Trans Medical Imaging 21(9): 1151–1164
Lotjonen J, Kivisto S, Koikkalainen J, Smutek D, Lauerma K (2004) Statistical shape model of atria, ventricles and epicardium from short- and long-axis MR images. Medical Image Anal 8(3): 371–386
Ordas S, Oubel E, Leta R, Carreras F, Frangi AF (2007) A statistical shape model of the heart and its application to model-based segmentation. In: Proceedings of SPIE medical imaging, vol 6511
Perperidis D, Mohiaddin R, Rueckert D (2005) Construction of a 4D statistical atlas of the cardiac anatomy and its use in classification. In: Proceedings of MICCAI, LNCS 3750, pp 402–405
Stegmann MB, Pedersen D (2005) Bi-temporal 3D active appearance models with applications to unsupervised ejection fraction estimation. In: Proceedings of SPIE medical imaging, vol 5747, pp 336–350
Zhang H, Wahle A, Johnson RK, Scholz TD, Sonka M (2010) 4D cardiac MR image analysis: left and right ventricular morphology and function. IEEE Trans Medical Imaging 29(2): 350–364
Zhu Y, Papademetris X, Sinusas AJ, Duncan JS (2010) Segmentation of the left ventricle from cardiac MR images using a subject-specific dynamical model. IEEE Trans Medical Imaging 29(3): 669–687
O’Brien SP, Ghita O, Whelan PF (2011) A novel model-based 3D+time left ventricular segmentation technique. IEEE Trans Medical Imaging 30(2): 461–474
Suinesiaputra A, Frangi AF, Kaandorp TAM, Lamb HJ, Bax JJ, Reiber JHC, Lelieveldt BPF (2009) Automated detection of regional wall motion abnormalities based on a statistical model applied to multislice short-axis cardiac MR images. IEEE Trans Medical Imaging 28(4): 595–607
Twining CJ, Taylor CJ (2001) Kernel principal component analysis and the construction of non-linear active shape models. In: Proceedings of British machine vision conference, vol 1, pp 23–32
Uzumcu M, Frangi AF, Reiber JHC, Lelieveldt BPF (2003) Independent component analysis in statistical shape models. In: Proceedings of SPIE medical imaging, vol 5032, pp 375–383
Koikkalainen J, Lotjonen J (2004) Image segmentation with the combination of PCA- and ICA-based modes of shape variation. In: Proceedings of IEEE international symposium on biomedical imaging: from Nano to Macro, vol 1, pp 149–152
Hilger KB, Larsen R, Wrobel MC (2003) Growth modeling of human mandibles using non-euclidean metrics. Medical Image Anal 7(4): 425–433
Larsen R, Hilger KB (2003) Statistical shape analysis using non-Euclidean metrics. Medical Image Anal 7(4): 417–423
Dambreville S, Rathi Y, Tannenbaum A (2008) A framework for image segmentation using shape models and kernel space shape priors. IEEE Trans Pattern Anal Mach Intell 30(8): 1385–1399
Rathi Y, Dambreville S, Tannenbaum A (2006) Comparative analysis of kernel methods for statistical shape learning. In: Proceedings of 2nd international workshop computer vision approaches to medical image analysis, vol 2
Cremers D, Kohlberger T, Schnorr C (2003) Shape statistics in kernel space for variational image segmentation. Pattern Recogn 36: 1929–1943
Andreopoulos A, Tsotsos JK (2008) Efficient and generalizable statistical models of shape and appearance for analysis of cardiac MRI. Medical Image Anal 12(3): 335–357
Herman GT, Zheng J, Bucholtz CA (1992) Shape-based interpolation. IEEE Comput Graph Appl, 69–79
Raya S, Udupa J (1990) Shape-based interpolation of multidimensional objects. IEEE Trans Medical Imaging 9(1): 33–42
Newman T, Yi H (2006) A survey of the marching cubes algorithm. Comput Graph 30(5): 854–879
Knapp M (2002) Mesh decimation using VTK, Technical report, Vienna University of Technology
Goodall C (1991) Procrustes methods in the statistical analysis of shape. J R Stat Soc 53(2): 285–339
Cootes TF (2004) Statistical models of appearance for computer vision, Technical Report, University of Manchester
Davies R, Twining C, Taylor C (2008) Statistical models of shape: optimization and evaluation. 1st edn. Springer, London
Twining CJ, Taylor CJ (2003) The use of kernel principal component analysis to model data distribution. Pattern Recogn 36: 217–227
Mika S, Scholkopf B, Smola A, Muller K, Scholz M, Ratsch G (1998) Kernel PCA and denoising in feature spaces. Adv Neural Inf Process Syst 11
Kwok , Tsang I (2004) The pre-image problem in kernel methods. IEEE Trans Neural Netw 15(6): 1517–1525
Rathi Y, Dambreville S, Tannenbaum A (2006) Statistical shape analysis using kernel PCA. In: Proceedings of SPIE medical imaging, vol 6064, pp 425–432
Department of Computer Science and Engineering, Centre for Vision Research, York University. [Online]. Available: http://www.cse.yorku.ca/~ridataset/
Schnabel A, Rueckert D, Quist M, Blackall JM, Castellano Smith AD, Hartkens T, Penney GP, Hall WA, Liu H, Truwit CL, Gerritsen FA, Hill DLG, Hawkes DJ (2001) A generic framework for non-rigid registration based on non-uniform multi-level free-form deformations. In: Proceedings of MICCAI, LNCS 2208, pp 573–581
Avila Lisa S, Barre S, Blue R, Cole D, Geveci B, Hoffman WA, King B, Law CC, Martin KM, Schroeder WJ, Squillacote AH, The VTK User’s Guide (2011) Kitware, 11th edn., New York
Franc V, Hlavac V (2004) Statistical pattern recognition toolbox for MATLAB, Technical Report, Czech Technical University Prague, June 2004
Leiner B, Jimena O, Boris ER, Fernando A, Enrique V (2012) Segmentation of 4D cardiac computed tomography images using active shape models. In: Proceedings of SPIE medical imaging, vol 8436
Kroon D-J. Active shape model (ASM) and active appearance model (AAM). Available: http://www.mathworks.com/matlabcentral/fileexchange/
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Faghih Roohi, S., Aghaeizadeh Zoroofi, R. 4D statistical shape modeling of the left ventricle in cardiac MR images. Int J CARS 8, 335–351 (2013). https://doi.org/10.1007/s11548-012-0787-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-012-0787-1