Nonparametric matrix regression function estimation over symmetric positive definite matrices. (English) Zbl 1485.62066
Summary: Symmetric positive definite matrix data commonly appear in computer vision and medical imaging, such as diffusion tensor imaging. The aim of this paper is to develop a nonparametric estimation method for a symmetric positive definite matrix regression function given covariates. By obtaining a suitable parametrization based on the Cholesky decomposition, we make it possible to apply univariate smoothing methods to the matrix regression problem. The parametrization also guarantees that the proposed estimator is symmetric positive definite over the entire domain. We adopt the Wishart log-likelihood and a smoothing technique using the basis methodology to define our estimator. The rate of convergence of the proposed estimator is obtained under some regularity conditions. Simulations are performed to investigate the finite sample properties of our proposed method using natural splines. Moreover, we present the results of an analysis of real diffusion tensor imaging data where the estimated fractional anisotropy is provided using \(3\times 3\) symmetric positive definite matrices measured at consecutive positions along a fiber tract in the brain of subjects.
MSC:
| 62H12 | Estimation in multivariate analysis |
| 62G05 | Nonparametric estimation |
| 62G20 | Asymptotic properties of nonparametric inference |
Keywords:
Cholesky factorization; diffusion tensor imaging; matrix regression function; minimaxity; Stein loss; Wishart distributionReferences:
| [1] | Anderson, TW, An introduction to multivariate statistical analysis (2003), Hoboken: Wiley, Hoboken · Zbl 1039.62044 |
| [2] | Barmpoutis, A.; Vemuri, BC; Shepherd, TM; Forder, JR, Tensor splines for interpolation and approximation of DT-MRI with applications to segmentation of isolated rat hippocampi, IEEE Transactions on Medical Imaging, 26, 1537-1546 (2007) · doi:10.1109/TMI.2007.903195 |
| [3] | Basser, PJ; Jones, DK, Diffusion-tensor MRI: theory, experimental design and data analysis—a technical review, NMR in Biomedicine, 15, 456-467 (2002) · doi:10.1002/nbm.783 |
| [4] | Basser, P.; Pierpaoli, C., Microstructural and physiological features of tissues elucidated by quantitative-diffusion-tensor MRI, Journal of Magnetic Resonance, 111, 209-219 (1996) · doi:10.1006/jmrb.1996.0086 |
| [5] | Bihan, DL, Looking into the functional architecture of the brain with diffusion MRI, Nature Reviews Neuroscience, 4, 469-480 (2003) · doi:10.1038/nrn1119 |
| [6] | Cai, TT; Zhou, HH, Optimal rates of convergence for sparse covariance matrix estimation, Annals of Statistics, 40, 5, 2389-2420 (2012) · Zbl 1373.62247 · doi:10.1214/12-AOS998 |
| [7] | Chau, J.; von Sachs, R., Intrinsic wavelet regression for curves of Hermitian positive definite matrices, Journal of the American Statistical Association (2020) · Zbl 1464.62377 · doi:10.1080/01621459.2019.1700129 |
| [8] | Davis, B. C., Bullitt, E., Fletcher, P. T., & Joshi, S. (2007). Population shape regression from random design data. In IEEE 11th international conference on computer vision (pp 1-7). Rio de Janeiro |
| [9] | de Boor, C., A practical guide to splines (2001), New York: Springer, New York · Zbl 0987.65015 |
| [10] | DeVore, RA; Popov, VA, Interpolation of Besov spaces, Transactions of the American Mathematical Society, 305, 397-414 (1988) · Zbl 0646.46030 · doi:10.1090/S0002-9947-1988-0920166-3 |
| [11] | Donoho, DL; Johnstone, IM; Kerkyacharian, G.; Picard, D., Density estimation by wavelet thresholding, Annals of Statistics, 24, 508-539 (1996) · Zbl 0860.62032 · doi:10.1214/aos/1032894451 |
| [12] | Dryden, IL; Koloydenko, A.; Zhou, D., Non-Euclidean statistics for covariance matrices with applications to diffusion tensor imaging, Annals of Applied Statistics, 3, 1102-1123 (2009) · Zbl 1196.62063 · doi:10.1214/09-AOAS249 |
| [13] | Golub, GH; Loan, CF, Matrix computations (1989), Baltimore: The Johns Hopkins University Press, Baltimore · Zbl 0733.65016 |
| [14] | Grenander, U.; Miller, MI, Pattern theory from representation to inference (2007), Oxford: Oxford University Press, Oxford · Zbl 1259.62089 |
| [15] | Härdle, W.; Kerkyacharian, G.; Picard, D.; Tsybakov, A., Wavelets, approximation and statistical applications. Lecture notes in statistics (1998), New York: Springer, New York · Zbl 0899.62002 · doi:10.1007/978-1-4612-2222-4 |
| [16] | Hasan, KM; Narayana, PA, Computation of the fractional anisotropy and mean diffusivity maps without tensor decoding and diagonalization: theoretical analysis and validation, Magnetic Resonance in Medicine, 50, 589-598 (2003) · doi:10.1002/mrm.10552 |
| [17] | Hasan, KM; Basser, PJ; Parker, DL; Alexander, AL, Analytical computation of the eigenvalues and eigenvectors in DT-MRI, Journal of Magnetic Resonance, 152, 41-47 (2001) · doi:10.1006/jmre.2001.2400 |
| [18] | James, W., & Stein, C. (1961). Estimation with quadratic loss. In Proceedings of the fourth Berkeley symposium on mathematical statistics and probability. Contributions to the theory of statistics (Vol. 1, pp. 361-379). Berkeley, Calif.: University of California Press. · Zbl 1281.62026 |
| [19] | Jaquier, N., & Calinon, S. (2017). Gaussian mixture regression on symmetric positive definite matrices manifolds: Application to wrist motion estimation with sEMG. In 2017 IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 59-64), Vancouver, BC. |
| [20] | Kim, P. T., & Richards, D. S. P. (2011). Deconvolution density estimation on the space of positive definite symmetric matrices. In Nonparametric statistics and mixture models: A Festschrift in honor of Thomas P Hettmansperger (pp 147-168). · Zbl 1414.62184 |
| [21] | Koo, J-Y; Kim, W-C, Wavelet density estimation by approximation of log-densities, Statistics & Probability Letters, 26, 271-278 (1996) · Zbl 0843.62040 · doi:10.1016/0167-7152(95)00020-8 |
| [22] | Osborne, D.; Patrangenaru, V.; Ellingson, L.; Groisser, D.; Schwartzman, A., Nonparametric two-sample tests on homogeneous Riemannian manifolds, Cholesky decompositions and diffusion tensor image analysis, Journal of Multivariate Analysis, 119, 163-175 (2013) · Zbl 1277.62127 · doi:10.1016/j.jmva.2013.04.006 |
| [23] | Pierpaoli, C.; Basser, P., Toward a quantitative assessment of diffusion anisotropy, Magnetic Resonance in Medicine, 36, 893-906 (1996) · doi:10.1002/mrm.1910360612 |
| [24] | Pietrzykowski, T., A generalization of the potential method for conditional maxima on Banach, reflexive spaces, Numerische Mathematik, 18, 367-372 (1972) · Zbl 0282.65054 · doi:10.1007/BF01404687 |
| [25] | Pourahmadi, M., Joint mean-covariance models with applications to longitudinal data: unconstrained parameterisation, Biometrika, 86, 677-690 (1999) · Zbl 0949.62066 · doi:10.1093/biomet/86.3.677 |
| [26] | Pourahmadi, M., Maximum likelihood estimation of generalized linear models for multivariate normal covariance matrix, Biometrika, 87, 425-435 (2000) · Zbl 0954.62091 · doi:10.1093/biomet/87.2.425 |
| [27] | Said, S.; Bombrun, L.; Berthoumieu, Y.; Manton, JH, Riemannian gaussian distributions on the space of symmetric positive definite matrices, IEEE Transactions on Information Theory, 63, 4, 2153-2170 (2017) · Zbl 1366.15029 · doi:10.1109/TIT.2017.2653803 |
| [28] | Schott, JR, Matrix analysis for statistics (2005), Hoboken: Wiley, Hoboken · Zbl 1076.15002 |
| [29] | Schwartzman, A.; Mascarenhas, WF; Taylor, JE, Inference for eigenvalues and eigenvectors of Gaussian symmetric matrices, Annals of Statistics, 36, 1423-1431 (2008) · Zbl 1196.62067 · doi:10.1214/08-AOS628 |
| [30] | Schwarz, G., Estimating the dimension of a model, Annals of Statistics, 6, 461-464 (1978) · Zbl 0379.62005 · doi:10.1214/aos/1176344136 |
| [31] | Stone, CJ, The dimensionality reduction principle for generalized additive models, Annals of Statistics, 14, 590-606 (1986) · Zbl 0603.62050 · doi:10.1214/aos/1176349940 |
| [32] | Stone, CJ, The use of polynomial splines and their tensor products in multivariate function estimation, Annals of Statistics, 22, 118-183 (1994) · Zbl 0827.62038 |
| [33] | Tsybakov, AB, Introduction to nonparametric estimation (2009), New York: Springer, New York · Zbl 1176.62032 · doi:10.1007/b13794 |
| [34] | Yatracos, YG, A lower bound on the error in nonparametric regression type problems, Annals of Statistics, 16, 1180-1187 (1988) · Zbl 0651.62028 · doi:10.1214/aos/1176350954 |
| [35] | Yuan, Y.; Zhu, H.; Lin, W.; Marron, JS, Local polynomial regression for symmetric positive definite matrices, Journal of the Royal Statistical Society: Series B, 74, 697-719 (2012) · Zbl 1411.62110 · doi:10.1111/j.1467-9868.2011.01022.x |
| [36] | Zhu, H.; Xu, D.; Raz, A.; Hao, X.; Zhang, H.; Kangarlu, A.; Bansal, R.; Peterson, BS, A statistical framework for the classification of tensor morphologies in diffusion tensor images, Magnetic Resonance Imaging, 24, 569-582 (2006) · doi:10.1016/j.mri.2006.01.004 |
| [37] | Zhu, HT; Chen, YS; Ibrahim, JG; Li, YM; Lin, WL, Intrinsic regression models for positive-definite matrices with applications to diffusion tensor imaging, Journal of the American Statistical Association, 104, 1203-1212 (2009) · Zbl 1388.62198 · doi:10.1198/jasa.2009.tm08096 |
| [38] | Zhu, HT; Kong, L.; Li, R.; Styner, M.; Gerig, G.; Lin, W.; Gilmore, JH, Fadtts: Functional analysis of diffusion tensor tract statistics, NeuroImage, 56, 1412-1425 (2011) · doi:10.1016/j.neuroimage.2011.01.075 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
