Abstract
Statistical shape models (SSMs) are a standard generative shape modeling technique and they are still successfully employed in modern deep learning-based solutions for data augmentation purposes or as shape priors. However, with few training samples they often fail to represent local shape variations. Recently, a new state-of-the-art method has been proposed to alleviate this problem via a multi-level model localization scheme using distance-based covariance manipulations and Grassmannian-based level fusion during model training. This method significantly improves a SSMs performance, but heavily relies on costly eigendecompositions of large covariance matrices. In this paper, we derive a novel computationally-efficient formulation of the original method using ideas from kernel theory and randomized eigendecomposition. The proposed extension leads to a multi-level localization method for large-scale shape modeling problems that preserves the key characteristics of the original method while also improving its performance. Furthermore, our extensive evaluation on two publicly available data sets reveals the benefits of Grassmannian-based level fusion in contrast to a method derived from the popular Gaussian Process Morphable Models framework.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Naive implementation of the eigendecomposition algorithm is assumed here.
- 2.
- 3.
References
Alvarez, M.A., Rosasco, L., Lawrence, N.D., et al.: Kernels for vector-valued functions: a review. Found. Trends Mach. Learn. 4(3), 195–266 (2012)
Avants, B., Tustison, N.: ANTs/ANTsR brain templates (2014). https://doi.org/10.6084/m9.figshare.915436.v2
Cootes, T., Taylor, C., Cooper, D., Graham, J.: Active shape models-their training and application. CVIU 61(1), 38–59 (1995)
Cootes, T.F., Taylor, C.J.: Data driven refinement of active shape model search. In: British Machine Vision Conference - BMVC, 1996, pp. 1–10 (1996)
Davies, R., Twining, C., Cootes, T., Waterton, J., Taylor, C.: A minimum description length approach to statistical shape modeling. IEEE Trans. Med. Imaging 21(5), 525–537 (2002)
Dölz, J., Gerig, T., Lüthi, M., Harbrecht, H., Vetter, T.: Error-controlled model approximation for gaussian process morphable models. J. Math. Imaging Vision 61(4), 443–457 (2019)
Ehrhardt, J., Schmidt-Richberg, A., Werner, R., Handels, H.: Variational registration - a flexible open-source itk toolbox for nonrigid image registration. Bildverarbeitung für die Medizin 2015, 209–214 (2015)
Feragen, A., Lauze, F., Hauberg, S.: Geodesic exponential kernels: when curvature and linearity conflict. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3032–3042 (2015)
van Ginneken, B., Stegmann, M.B., Loog, M.: Segmentation of anatomical structures in chest radiographs using supervised methods: a comparative study on a public database. Med. Image Anal. 10(1), 19–40 (2006)
Heimann, T., Meinzer, H.P.: Statistical shape models for 3d medical image segmentation: a review. Med. Image Anal. 13(4), 543–563 (2009)
Jud, C., Giger, A., Sandkühler, R., Cattin, P.C.: A localized statistical motion model as a reproducing kernel for non-rigid image registration. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10434, pp. 261–269. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66185-8_30
Karimi, D., Samei, G., Kesch, C., Nir, G., Salcudean, S.E.: Prostate segmentation in MRI using a convolutional neural network architecture and training strategy based on statistical shape models. Int. J. Comput. Assist. Radiol. Surg. 13(8), 1211–1219 (2018)
Kollias, D., Cheng, S., Ververas, E., Kotsia, I., Zafeiriou, S.: Deep neural network augmentation: generating faces for affect analysis. Int. J. Comput. Vision 128(5), 1455–1484 (2020). https://doi.org/10.1007/s11263-020-01304-3
Lin, A., Wu, J., Yang, X.: A data augmentation approach to train fully convolutional networks for left ventricle segmentation. Magn. Reson. Imaging 66, 152–164 (2019)
Lüthi, M., Gerig, T., Jud, C., Vetter, T.: Gaussian process morphable models. IEEE Trans. Pattern Anal. Mach. Intell. 40(8), 1860–1873 (2018)
Milletari, F., Rothberg, A., Jia, J., Sofka, M.: Integrating statistical prior knowledge into convolutional neural networks. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 161–168. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66182-7_19
Ploumpis, S., Wang, H., Pears, N., Smith, W.A., Zafeiriou, S.: Combining 3d morphable models: A large scale face-and-head model. In: CVPR, pp. 10934–10943 (2019)
Shiraishi, J., et al.: Development of a digital image database for chest radiographs with and without a lung nodule: receiver operating characteristic analysis of radiologists’ detection of pulmonary nodules. Am. J. Roentgenol. 174(1), 71–74 (2000)
Tang, Z., Chen, K., Pan, M., Wang, M., Song, Z.: An augmentation strategy for medical image processing based on statistical shape model and 3D thin plate spline for deep learning. IEEE Access 7, 133111–133121 (2019)
Uzunova, H., Wilms, M., Handels, H., Ehrhardt, J.: Training CNNS for image registration from few samples with model-based data augmentation. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) Med Image Comput Comput Assist Interv - MICCAI 2017. LNCS, vol. 10433, pp. 223–231. Springer, Cham (2017)
Wang, S., Zhang, Z., Zhang, T.: Towards more efficient SPSD matrix approximation and CUR matrix decomposition. J. Mach. Learn. Res. 17(210), 1–49 (2016)
Wang, Y., Staib, L.H.: Boundary finding with prior shape and smoothness models. IEEE Trans. Pattern Anal. Mach. Intell. 22(7), 738–743 (2000)
Werner, R., Schmidt-Richberg, A., Handels, H., Ehrhardt, J.: Estimation of lung motion fields in 4D CT data by variational non-linear intensity-based registration: a comparison and evaluation study. Phys. Med. Biol. 59(15), 4247–4260 (2014)
Williams, C.K., Rasmussen, C.E.: Gaussian processes for machine learning, vol. 2. MIT press, Cambridge (2006)
Wilms, M., Handels, H., Ehrhardt, J.: Multi-resolution multi-object statistical shape models based on the locality assumption. Med. Image Anal. 38(5), 17–29 (2017)
Wilms, M., Handels, H., Ehrhardt, J.: Representative patch-based active appearance models generated from small training populations. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 152–160. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66182-7_18
Yu, X., Zhou, F., Chandraker, M.: Deep deformation network for object landmark localization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 52–70. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46454-1_4
Zhang, H., Li, Q., Sun, Z., Liu, Y.: Combining data-driven and model-driven methods for robust facial landmark detection. IEEE Trans. Inf. Forensics Secur. 13(10), 2409–2422 (2018)
Zhao, A., Balakrishnan, G., Durand, F., Guttag, J.V., Dalca, A.V.: Data augmentation using learned transformations for one-shot medical image segmentation. In: CVPR 2019, pp. 8543–8553 (2019)
Acknowledgements
This work was supported by the University of Calgary’s Eyes High postdoctoral scholarship program and the River Fund at Calgary Foundation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Wilms, M., Ehrhardt, J., Forkert, N.D. (2020). A Kernelized Multi-level Localization Method for Flexible Shape Modeling with Few Training Data. In: Martel, A.L., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. MICCAI 2020. Lecture Notes in Computer Science(), vol 12264. Springer, Cham. https://doi.org/10.1007/978-3-030-59719-1_74
Download citation
DOI: https://doi.org/10.1007/978-3-030-59719-1_74
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59718-4
Online ISBN: 978-3-030-59719-1
eBook Packages: Computer ScienceComputer Science (R0)
