Abstract
The construction of a powerful statistical shape model (SSM) requires a rich training dataset that includes the large variety of complex anatomical topologies. The lack of real data causes most SSMs unable to generalize possible unseen instances. Artificial enrichment of training data is one of the methods proposed to address this issue. In this paper, we introduce a novel technique called constrained cage-based deformation (CCBD), which has the ability to produce unlimited artificial data that promises to enrich variability within the training dataset. The proposed method is a two-step algorithm: in the first step, it moves a few handles together, and in the second step transfers the displacements of these handles to the base mesh vertices to generate a real new instance. The evaluation of statistical characteristics of the CCBD confirms that our proposed technique outperforms notable data-generating methods quantitatively, in terms of the generalization ability, and with respect to specificity.
Similar content being viewed by others
References
Heimann T, Meinzer H-P (2009) Statistical shape models for 3D medical image segmentation: a review. Med Image Anal 13(4):543–563
Lüthi M (2010) A machine learning approach to statistical shape models with applications to medical image analysis. University_of_Basel, Basel
Gholipour A et al (2007) Brain functional localization: a survey of image registration techniques. IEEE Trans Med Imaging 26(4):427–451
Zitova B, Flusser J (2003) Image registration methods: a survey. Image Vis Comput 21(11):977–1000
Gain J, Bechmann D (2008) A survey of spatial deformation from a user-centered perspective. ACM Trans Graph (TOG) 27(4):107
Castro-Mateos I et al (2015) Statistical interspace models (SIMs): application to robust 3D spine segmentation. IEEE Trans Med Imaging 34(8):1663–1675
Yokota F et al (2009) Automated segmentation of the femur and pelvis from 3D CT data of diseased hip using hierarchical statistical shape model of joint structure. In international conference on medical image computing and computer-assisted intervention. Springer
Lamecker H, Lange T, Seebass M (2004) Segmentation of the liver using a 3D statistical shape model. Konrad-Zuse-Zentrum fur Informationstechnik, Berlin
Zhang X et al (2010) Automatic liver segmentation using a statistical shape model with optimal surface detection. IEEE Trans Biomed Eng 57(10):2622–2626
Martin S, Troccaz J, Daanen V (2010) Automated segmentation of the prostate in 3D MR images using a probabilistic atlas and a spatially constrained deformable model. Med Phys 37(4):1579–1590
Chandra SS et al (2014) Focused shape models for hip joint segmentation in 3D magnetic resonance images. Med Image Anal 18(3):567–578
Albà X et al (2014) Reusability of statistical shape models for the segmentation of severely abnormal hearts. In: international workshop on statistical atlases and computational models of the heart. Springer, New York
Lötjönen J et al (2005) Artificial enlargement of a training set for statistical shape models: application to cardiac images. In international workshop on functional imaging and modeling of the heart. Springer
Van Assen HC et al (2005) SPASM: segmentation of sparse and arbitrarily oriented cardiac MRI data using a 3D-ASM. In international workshop on functional imaging and modeling of the heart. Springer
Mitchell SC et al (2002) 3-D active appearance models: segmentation of cardiac MR and ultrasound images. IEEE Trans Med Imaging 21(9):1167–1178
Davatzikos C, Tao X, Shen D (2003) Hierarchical active shape models, using the wavelet transform. IEEE Trans Med Imaging 22(3):414–423
Chung F et al (2011) Comparison of statistical models performance in case of segmentation using a small amount of training datasets. Visual Comput 27(2):141–151
Ordas S, et al (2004) Grid-enabled automatic construction of a two-chamber cardiac PDM from a large database of dynamic 3D shapes. In IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2004. IEEE
de Bruijne M et al (2003). Adapting active shape models for 3D segmentation of tubular structures in medical images. In biennial international conference on information processing in medical imaging. Springer
Hu N et al (2014) A method for generating large datasets of organ geometries for radiotherapy treatment planning studies. Radiol Oncol 48(4):408–415
Pereañez M (2017) Enlargement, subdivision and individualization of statistical shape models: application to 3D medical image segmentation
Pereañez M et al (2014) A framework for the merging of pre-existing and correspondenceless 3D statistical shape models. Med Image Anal 18(7):1044–1058
Ehrhardt J, Wilms M, Handels H (2016) Patch-based low-rank matrix completion for learning of shape and motion models from few training samples. In European conference on computer vision. Springer
Cootes TF, Taylor CJ (1995) Combining point distribution models with shape models based on finite element analysis. Image Vis Comput 13(5):403–409
Koikkalainen J et al (2008) Methods of artificial enlargement of the training set for statistical shape models. IEEE Trans Med Imaging 27(11):1643–1654
Jacobson A et al (2011) Bounded biharmonic weights for real-time deformation. ACM Trans Graph 30(4):1–8
Ju T, Schaefer S, Warren J (2005) Mean value coordinates for closed triangular meshes. In ACM transactions on graphics (TOG). ACM
Lipman Y et al (2007) GPU-assisted positive mean value coordinates for mesh deformations. In symposium on geometry processing
Joshi P et al (2007) Harmonic coordinates for character articulation. In: ACM transactions on graphics (TOG). ACM
Wang Y, Staib LH (2000) Physical model-based non-rigid registration incorporating statistical shape information. Med Image Anal 4(1):7–20
Cootes TF, Taylor CJ (1996) data driven refinement of active shape model search. In: BMVC
Zhang S, Zhan Y, Metaxas DN (2012) Deformable segmentation via sparse representation and dictionary learning. Med Image Anal 16(7):1385–1396
Fang Q, Boas DA (2009) Tetrahedral mesh generation from volumetric binary and grayscale images. In: IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2009. ISBI’09. IEEE
Hussain M, Okada Y, Niijima K (2004) Efficient and feature-preserving triangular mesh decimation. In WSCG
Meyer M et al (2002) Generalized barycentric coordinates on irregular polygons. J Graph Tools 7(1):13–22
Jacobson A et al (2011) Bounded biharmonic weights for real-time deformation. ACM Trans Graph 30(4):78:1–78:8
Floater MS (2003) Mean value coordinates. Comput Aided Geom Des 20(1):19–27
Lipman Y, Levin D, Cohen-Or D (2008) Green coordinates. ACM Trans Graphics (TOG) 27(3):78
Lipman Y et al (2004) Differential coordinates for interactive mesh editing. In: Proceedings shape modeling applications. IEEE
Meyer M et al (2003) Discrete differential-geometry operators for triangulated manifolds. Visualization and mathematics. Springer, New York, pp 35–57
Feldmar J et al (1997) Extension of the ICP algorithm to nonrigid intensity-based registration of 3D volumes. Comput Vis Image Underst 66(2):193–206
Jolliffe IT (2002) Principal component analysis and factor analysis. Princ Compon Anal 69:150–166
Davies RH (2002) Learning shape: optimal models for analysing natural variability. University of Manchester, Manchester
Pham DL, Xu C, Prince JL (2000) Current methods in medical image segmentation. Annu Rev Biomed Eng 2(1):315–337
Lenkiewicz P et al (2010) Techniques for medical image segmentation: review of the most popular approaches. Biomedical diagnostics and clinical technologies: applying high-performance cluster and grid computing. University of Beira Interior, Covilha, pp 1–33
Acknowledgements
The authors gratefully acknowledge the support and generosity of Fanavaran Jarahyar Sharif Co. for providing Femur dataset that without which the present study could not have been completed. We are also immensely grateful to Seyed Mohammad Reza Noori for comments that significantly improved the manuscript.
Funding
This work was supported by the medical school, Tehran University of Medical Science in Grant Number 28345 and also by the Iran National Science Foundation in Grant Number 92011635.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Alimohamadi Gilakjan, S., Hasani Bidgoli, J., Aghaizadeh Zorofi, R. et al. Artificially enriching the training dataset of statistical shape models via constrained cage-based deformation. Australas Phys Eng Sci Med 42, 573–584 (2019). https://doi.org/10.1007/s13246-019-00759-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13246-019-00759-0