Abstract
There is much interest in developing algorithms based on 3D convolutional neural networks (CNNs) for performing regression and classification with brain imaging data and more generally, with biomedical imaging data. A standard assumption in learning is that the training samples are independently drawn from the underlying distribution. In computer vision, where we have millions of training examples, this assumption is violated but the empirical performance may remain satisfactory. But in many biomedical studies with just a few hundred training examples, one often has multiple samples per participant and/or data may be curated by pooling datasets from a few different institutions. Here, the violation of the independent samples assumption turns out to be more significant, especially in small-to-medium sized datasets. Motivated by this need, we show how 3D CNNs can be modified to deal with dependent samples. We show that even with standard 3D CNNs, there is value in augmenting the network to exploit information regarding dependent samples. We present empirical results for predicting cognitive trajectories (slope and intercept) from morphometric change images derived from multiple time points. With terms which encode dependency between samples in the model, we get consistent improvements over a strong baseline which ignores such knowledge.
Supported by UW CPCP AI117924, R01 EB022883 and R01 AG062336. Partial support also provided by R01 AG040396, R01 AG021155, UW ADRC (AG033514), UW ICTR (1UL1RR025011) and NSF CAREER award RI 1252725. We also thank Nagesh Adluru for his help during data processing.
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
References
Bône, A., Colliot, O., Durrleman, S.: Learning distributions of shape trajectories from longitudinal datasets: a hierarchical model on a manifold of diffeomorphisms. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018
Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 424–432. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46723-8_49
Elhamifar, E., Vidal, R.: Sparse manifold clustering and embedding. In: Advances in Neural Information Processing Systems, pp. 55–63 (2011)
Fahrmeir, L., Tutz, G.: Multivariate Statistical Modelling Based on Generalized Linear Models. Springer, Heidelberg (2013)
Fong, R.C., Vedaldi, A.: Interpretable explanations of black boxes by meaningful perturbation
Hajjem, A., Bellavance, F., Larocque, D.: Mixed-effects random forest for clustered data. J. Stat. Comput. Simul. 84(6), 1313–1328 (2014)
Ithapu, V.K., Singh, V., Okonkwo, O., Johnson, S.C.: Randomized denoising autoencoders for smaller and efficient imaging based AD clinical trials. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014. LNCS, vol. 8674, pp. 470–478. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10470-6_59
Kehagia, A.A., Barker, R.A., Robbins, T.W.: Neuropsychological and clinical heterogeneity of cognitive impairment and dementia in patients with Parkinson’s disease. Lancet Neurol. 9(12), 1200–1213 (2010)
Kim, H.J., Adluru, N., et al.: Riemannian nonlinear mixed effects models: analyzing longitudinal deformations in neuroimaging
Lorenzi, M., Ayache, N., et al.: LCC-Demons: a robust and accurate symmetric diffeomorphic registration algorithm. NeuroImage 81, 470–483 (2013)
Lorenzi, M., Pennec, X.: Efficient parallel transport of deformations in time series of images: from schild’s to pole ladder. JMIG 50(1–2), 5–17 (2014)
Quiñonero-Candela, J., Rasmussen, C.E.: A unifying view of sparse approximate Gaussian process regression. JMLR 6(Dec), 1939–1959 (2005)
Robinson, G.K.: That BLUP is a good thing: the estimation of random effects. Stat. Sci. 6, 15–32 (1991)
Schmidt, M., et al.: Rey Auditory Verbal Learning Test: A Handbook. Western Psychological Services, Los Angeles (1996)
Sela, R.J., Simonoff, J.S.: RE-EM trees: a data mining approach for longitudinal and clustered data. Mach. Learn. 86(2), 169–207 (2012)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Smyser, C.D., et al.: Longitudinal analysis of neural network development in preterm infants. Cereb. Cortex 20, 2852–2862 (2010)
Wu, H., Zhang, J.T.: Nonparametric Regression Methods for Longitudinal Data Analysis: Mixed-Effects Modeling Approaches, vol. 515. Wiley, Hoboken (2006)
Yang, C., et al.: Visual explanations from deep 3D CNNs for Alzheimer’s disease classification. arXiv:1803.02544 (2018)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Xiong, Y., Kim, H.J., Tangirala, B., Mehta, R., Johnson, S.C., Singh, V. (2019). On Training Deep 3D CNN Models with Dependent Samples in Neuroimaging. In: Chung, A., Gee, J., Yushkevich, P., Bao, S. (eds) Information Processing in Medical Imaging. IPMI 2019. Lecture Notes in Computer Science(), vol 11492. Springer, Cham. https://doi.org/10.1007/978-3-030-20351-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-20351-1_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20350-4
Online ISBN: 978-3-030-20351-1
eBook Packages: Computer ScienceComputer Science (R0)