Abstract
Statistical shape modeling (SSM) has recently taken advantage of advances in deep learning to alleviate the need for a time-consuming and expert-driven workflow of anatomy segmentation, shape registration, and the optimization of population-level shape representations. DeepSSM is an end-to-end deep learning approach that extracts statistical shape representation directly from unsegmented images with little manual overhead. It performs comparably with state-of-the-art shape modeling methods for estimating morphologies that are viable for subsequent downstream tasks. Nonetheless, DeepSSM produces an overconfident estimate of shape that cannot be blindly assumed to be accurate. Hence, conveying what DeepSSM does not know, via quantifying granular estimates of uncertainty, is critical for its direct clinical application as an on-demand diagnostic tool to determine how trustworthy the model output is. Here, we propose Uncertain-DeepSSM as a unified model that quantifies both, data-dependent aleatoric uncertainty by adapting the network to predict intrinsic input variance, and model-dependent epistemic uncertainty via a Monte Carlo dropout sampling to approximate a variational distribution over the network parameters. Experiments show an accuracy improvement over DeepSSM while maintaining the same benefits of being end-to-end with little pre-processing.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baccetti, T., Franchi, L., McNamara, J.: Thin-plate spline analysis of treatment effects of rapid maxillary expansion and face mask therapy in early class III malocclusions. Eur. J. Orthod. 21(3), 275–281 (1999)
Bhalodia, R., Dvoracek, L.A., Ayyash, A.M., Kavan, L., Whitaker, R., Goldstein, J.A.: Quantifying the severity of metopic craniosynostosis: a pilot study application of machine learning in craniofacial surgery. J. Craniofac. Surg. 31, 697–701 (2020)
Bhalodia, R., Elhabian, S.Y., Kavan, L., Whitaker, R.T.: Deepssm: a deep learning framework for statistical shape modeling from raw images. CoRR abs/1810.00111 (2018). http://arxiv.org/abs/1810.00111
Bhalodia, R., et al.: Deep learning for end-to-end atrial fibrillation recurrence estimation. In: Computing in Cardiology, CinC 2018, Maastricht, The Netherlands, 23–26 September 2018 (2018)
Bookstein, F.L.: Principal warps: thin-plate splines and the decomposition of deformations. IEEE Trans. Pattern Anal. Mach. Intell. 11(6), 567–585 (1989)
Bryan, R., Nair, P.B., Taylor, M.: Use of a statistical model of the whole femur in a large scale, multi-model study of femoral neck fracture risk. J. Biomech. 42(13), 2171–2176 (2009)
Cates, J., et al.: Computational shape models characterize shape change of the left atrium in atrial fibrillation. Clin. Med. Insights Cardiol. 8, CMC-S15710 (2014)
Cates, J., Elhabian, S., Whitaker, R.: Shapeworks: particle-based shape correspondence and visualization software. In: Statistical Shape and Deformation Analysis, pp. 257–298. Elsevier (2017)
Cates, J., Fletcher, P.T., Styner, M., Shenton, M., Whitaker, R.: Shape modeling and analysis with entropy-based particle systems. In: Karssemeijer, N., Lelieveldt, B. (eds.) IPMI 2007. LNCS, vol. 4584, pp. 333–345. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-73273-0_28
Chang, J., Fisher, J.W.: Efficient MCMC sampling with implicit shape representations. In: CVPR 2011, pp. 2081–2088. IEEE (2011)
Davies, R.H., Twining, C.J., Cootes, T.F., Waterton, J.C., Taylor, C.J.: A minimum description length approach to statistical shape modeling. IEEE Trans. Med. Imaging 21(5), 525–537 (2002). https://doi.org/10.1109/TMI.2002.1009388
Denker, J.S., LeCun, Y.: Transforming neural-net output levels to probability distributions. In: Advances in Neural Information Processing Systems, pp. 853–859 (1991)
Durrleman, S., et al.: Morphometry of anatomical shape complexes with dense deformations and sparse parameters. NeuroImage 101, 35–49 (2014)
Gal, Y.: Uncertainty in deep learning. Univ. Camb. 1, 3 (2016)
Gal, Y., Ghahramani, Z.: Bayesian convolutional neural networks with bernoulli approximate variational inference. arXiv preprint arXiv:1506.02158 (2015)
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning, pp. 1050–1059 (2016)
Galloway, F., et al.: A large scale finite element study of a cementless osseointegrated tibial tray. J. Biomech. 46(11), 1900–1906 (2013)
Gardner, G., Morris, A., Higuchi, K., MacLeod, R., Cates, J.: A point-correspondence approach to describing the distribution of image features on anatomical surfaces, with application to atrial fibrillation. In: 2013 IEEE 10th International Symposium on Biomedical Imaging, pp. 226–229, April 2013. https://doi.org/10.1109/ISBI.2013.6556453
Gerig, G., Styner, M., Jones, D., Weinberger, D., Lieberman, J.: Shape analysis of brain ventricles using spharm. In: Proceedings IEEE Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA 2001), pp. 171–178 (2001). https://doi.org/10.1109/MMBIA.2001.991731
Gielis, J.: A generic transformation that unifies a wide range of natural and abstract shapes (2013)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research, vol. 9, pp. 249–256. PMLR, 13–15 May 2010
Harris, M.D., Datar, M., Whitaker, R.T., Jurrus, E.R., Peters, C.L., Anderson, A.E.: Statistical shape modeling of cam femoroacetabular impingement. J. Orthop. Res. 31(10), 1620–1626 (2013). https://doi.org/10.1002/jor.22389
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. CoRR abs/1502.01852 (2015). http://arxiv.org/abs/1502.01852
Ho, S.Y., Cabrera, J.A., Sanchez-Quintana, D.: Left atrial anatomy revisited. Circ. Arrhythmia Electrophysiol. 5(1), 220–228 (2012)
Huang, W., Bridge, C.P., Noble, J.A., Zisserman, A.: Temporal heartnet: towards human-level automatic analysis of fetal cardiac screening video. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10434, pp. 341–349. Springer International Publishing, Cham (2017). https://doi.org/10.1007/978-3-319-66185-8_39
Joshi, S.C., Miller, M.I.: Landmark matching via large deformation diffeomorphisms. IEEE Trans. Image Process. 9(8), 1357–1370 (2000)
Joshi, S., Davis, B., Jomier, M., Gerig, G.: Unbiased diffeomorphic atlas construction for computational anatomy. NeuroImage 23(Supplement1), S151–S160 (2004)
Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? CoRR abs/1703.04977 (2017). http://arxiv.org/abs/1703.04977
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2014)
Kiureghian, A.D., Ditlevsen, O.D.: Aleatory or epistemic? Does it matter? (2009)
Kozic, N., et al.: Optimisation of orthopaedic implant design using statistical shape space analysis based on level sets. Med. Image Anal. 14(3), 265–275 (2010)
Kwon, Y., Won, J.H., Kim, B.J., Paik, M.C.: Uncertainty quantification using Bayesian neural networks in classification: application to ischemic stroke lesion segmentation (2018)
Lamecker, H., Lange, T., Seebass, M.: A statistical shape model for the liver. In: Dohi, T., Kikinis, R. (eds.) MICCAI 2002. LNCS, vol. 2489, pp. 421–427. Springer, Heidelberg (2002). https://doi.org/10.1007/3-540-45787-9_53
Lê, M., Unkelbach, J., Ayache, N., Delingette, H.: Sampling image segmentations for uncertainty quantification. Med. Image Anal. 34, 42–51 (2016)
Le, Q.V., Smola, A.J., Canu, S.: Heteroscedastic Gaussian process regression. In: Proceedings of the 22nd International Conference on Machine Learning, pp. 489–496 (2005)
Li, X., Chen, S., Hu, X., Yang, J.: Understanding the disharmony between dropout and batch normalization by variance shift. CoRR abs/1801.05134 (2018). http://arxiv.org/abs/1801.05134
MacKay, D.J.: A practical Bayesian framework for backpropagation networks. Neural Comput. 4(3), 448–472 (1992)
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 International Publishing, Cham (2017). https://doi.org/10.1007/978-3-319-66182-7_19
Moghaddam, B., Pentland, A.: Probabilistic visual learning for object representation. IEEE Trans. Pattern Anal. Mach. Intell. 19(7), 696–710 (1997)
Nix, D.A., Weigend, A.S.: Estimating the mean and variance of the target probability distribution. In: Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN 1994), vol. 1, pp. 55–60. IEEE (1994)
Oktay, O., et al.: Anatomically constrained neural networks (ACNN): application to cardiac image enhancement and segmentation. CoRR abs/1705.08302 (2017). http://arxiv.org/abs/1705.08302
Reinhold, J.C., et al.: Validating uncertainty in medical image translation. In: 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), pp. 95–98. IEEE (2020)
Sarkalkan, N., Weinans, H., Zadpoor, A.A.: Statistical shape and appearance models of bones. Bone 60, 129–140 (2014)
Selvan, R., Faye, F., Middleton, J., Pai, A.: Uncertainty quantification in medical image segmentation with normalizing flows. arXiv preprint arXiv:2006.02683 (2020)
Styner, M., et al.: Framework for the statistical shape analysis of brain structures using SPHARM-PDM (2006)
Tóthová, K., et al.: Uncertainty quantification in cnn-based surface prediction using shape priors. CoRR abs/1807.11272 (2018). http://arxiv.org/abs/1807.11272
Wang, D., Shi, L., Griffith, J.F., Qin, L., Yew, D.T., Riggs, C.M.: Comprehensive surface-based morphometry reveals the association of fracture risk and bone geometry. J. Orthop. Res. 30(8), 1277–1284 (2012)
Xie, J., Dai, G., Zhu, F., Wong, E.K., Fang, Y.: Deepshape: deep-learned shape descriptor for 3d shape retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 39(7), 1335–1345 (2017)
Zhao, Z., et al.: Hippocampus shape analysis and late-life depression. PLoS One 3(3), e1837 (2008)
Zheng, Y., Liu, D., Georgescu, B., Nguyen, H., Comaniciu, D.: 3D deep learning for efficient and robust landmark detection in volumetric data. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9349, pp. 565–572. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24553-9_69
Acknowledgement
This work was supported by the National Institutes of Health under grant numbers NIBIB-U24EB029011, NIAMS-R01AR076120, NHLBI-R01HL135568, and NIGMS-P41GM103545. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. MRI scans and segmentation were obtained retrospectively from the AFib database at the University of Utah. The authors would like to thank the Division of Cardiovascular Medicine (data were collected under Nassir Marrouche, MD, oversight and currently managed by Brent Wilson, MD, PhD) at the University of Utah for providing the left atrium MRI scans and their corresponding segmentations.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Adams, J., Bhalodia, R., Elhabian, S. (2020). Uncertain-DeepSSM: From Images to Probabilistic Shape Models. In: Reuter, M., Wachinger, C., Lombaert, H., Paniagua, B., Goksel, O., Rekik, I. (eds) Shape in Medical Imaging. ShapeMI 2020. Lecture Notes in Computer Science(), vol 12474. Springer, Cham. https://doi.org/10.1007/978-3-030-61056-2_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-61056-2_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61055-5
Online ISBN: 978-3-030-61056-2
eBook Packages: Computer ScienceComputer Science (R0)