Riemannian nonlinear mixed effects models: Analyzing longitudinal deformations in neuroimaging

Hyun Woo Kim, Nagesh Adluru, Heemanshu Suri, Baba C. Vemuri, Sterling C. Johnson, Vikas Singh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Statistical machine learning models that operate on manifold-valued data are being extensively studied in vision, motivated by applications in activity recognition, feature tracking and medical imaging. While non-parametric methods have been relatively well studied in the literature, efficient formulations for parametric models (which may offer benefits in small sample size regimes) have only emerged recently. So far, manifold-valued regression models (such as geodesic regression) are restricted to the analysis of cross-sectional data, i.e., the so-called “fixed effects” in statistics. But in most “longitudinal analysis” (e.g., when a participant provides multiple measurements, over time) the application of fixed effects models is problematic. In an effort to answer this need, this paper generalizes non-linear mixed effects model to the regime where the response variable is manifold-valued, i.e., f : Rd → M. We derive the underlying model and estimation schemes and demonstrate the immediate benefits such a model can provide - both for group level and individual level analysis - on longitudinal brain imaging data. The direct consequence of our results is that longitudinal analysis of manifold-valued measurements (especially, the symmetric positive definite manifold) can be conducted in a computationally tractable manner.

Original languageEnglish
Title of host publicationProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5777-5786
Number of pages10
ISBN (Electronic)9781538604571
DOIs
Publication statusPublished - 2017 Nov 6
Externally publishedYes
Event30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 - Honolulu, United States
Duration: 2017 Jul 212017 Jul 26

Publication series

NameProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
Volume2017-January

Other

Other30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
CountryUnited States
CityHonolulu
Period17/7/2117/7/26

Fingerprint

Neuroimaging
Medical imaging
Learning systems
Brain
Statistics
Imaging techniques

ASJC Scopus subject areas

  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Kim, H. W., Adluru, N., Suri, H., Vemuri, B. C., Johnson, S. C., & Singh, V. (2017). Riemannian nonlinear mixed effects models: Analyzing longitudinal deformations in neuroimaging. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 (pp. 5777-5786). (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017; Vol. 2017-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CVPR.2017.612

Riemannian nonlinear mixed effects models : Analyzing longitudinal deformations in neuroimaging. / Kim, Hyun Woo; Adluru, Nagesh; Suri, Heemanshu; Vemuri, Baba C.; Johnson, Sterling C.; Singh, Vikas.

Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 5777-5786 (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017; Vol. 2017-January).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kim, HW, Adluru, N, Suri, H, Vemuri, BC, Johnson, SC & Singh, V 2017, Riemannian nonlinear mixed effects models: Analyzing longitudinal deformations in neuroimaging. in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 5777-5786, 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, United States, 17/7/21. https://doi.org/10.1109/CVPR.2017.612
Kim HW, Adluru N, Suri H, Vemuri BC, Johnson SC, Singh V. Riemannian nonlinear mixed effects models: Analyzing longitudinal deformations in neuroimaging. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 5777-5786. (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017). https://doi.org/10.1109/CVPR.2017.612
Kim, Hyun Woo ; Adluru, Nagesh ; Suri, Heemanshu ; Vemuri, Baba C. ; Johnson, Sterling C. ; Singh, Vikas. / Riemannian nonlinear mixed effects models : Analyzing longitudinal deformations in neuroimaging. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 5777-5786 (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017).
@inproceedings{31ef5f6aa3b44b16a455576ed4075c37,
title = "Riemannian nonlinear mixed effects models: Analyzing longitudinal deformations in neuroimaging",
abstract = "Statistical machine learning models that operate on manifold-valued data are being extensively studied in vision, motivated by applications in activity recognition, feature tracking and medical imaging. While non-parametric methods have been relatively well studied in the literature, efficient formulations for parametric models (which may offer benefits in small sample size regimes) have only emerged recently. So far, manifold-valued regression models (such as geodesic regression) are restricted to the analysis of cross-sectional data, i.e., the so-called “fixed effects” in statistics. But in most “longitudinal analysis” (e.g., when a participant provides multiple measurements, over time) the application of fixed effects models is problematic. In an effort to answer this need, this paper generalizes non-linear mixed effects model to the regime where the response variable is manifold-valued, i.e., f : Rd → M. We derive the underlying model and estimation schemes and demonstrate the immediate benefits such a model can provide - both for group level and individual level analysis - on longitudinal brain imaging data. The direct consequence of our results is that longitudinal analysis of manifold-valued measurements (especially, the symmetric positive definite manifold) can be conducted in a computationally tractable manner.",
author = "Kim, {Hyun Woo} and Nagesh Adluru and Heemanshu Suri and Vemuri, {Baba C.} and Johnson, {Sterling C.} and Vikas Singh",
year = "2017",
month = "11",
day = "6",
doi = "10.1109/CVPR.2017.612",
language = "English",
series = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "5777--5786",
booktitle = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017",

}

TY - GEN

T1 - Riemannian nonlinear mixed effects models

T2 - Analyzing longitudinal deformations in neuroimaging

AU - Kim, Hyun Woo

AU - Adluru, Nagesh

AU - Suri, Heemanshu

AU - Vemuri, Baba C.

AU - Johnson, Sterling C.

AU - Singh, Vikas

PY - 2017/11/6

Y1 - 2017/11/6

N2 - Statistical machine learning models that operate on manifold-valued data are being extensively studied in vision, motivated by applications in activity recognition, feature tracking and medical imaging. While non-parametric methods have been relatively well studied in the literature, efficient formulations for parametric models (which may offer benefits in small sample size regimes) have only emerged recently. So far, manifold-valued regression models (such as geodesic regression) are restricted to the analysis of cross-sectional data, i.e., the so-called “fixed effects” in statistics. But in most “longitudinal analysis” (e.g., when a participant provides multiple measurements, over time) the application of fixed effects models is problematic. In an effort to answer this need, this paper generalizes non-linear mixed effects model to the regime where the response variable is manifold-valued, i.e., f : Rd → M. We derive the underlying model and estimation schemes and demonstrate the immediate benefits such a model can provide - both for group level and individual level analysis - on longitudinal brain imaging data. The direct consequence of our results is that longitudinal analysis of manifold-valued measurements (especially, the symmetric positive definite manifold) can be conducted in a computationally tractable manner.

AB - Statistical machine learning models that operate on manifold-valued data are being extensively studied in vision, motivated by applications in activity recognition, feature tracking and medical imaging. While non-parametric methods have been relatively well studied in the literature, efficient formulations for parametric models (which may offer benefits in small sample size regimes) have only emerged recently. So far, manifold-valued regression models (such as geodesic regression) are restricted to the analysis of cross-sectional data, i.e., the so-called “fixed effects” in statistics. But in most “longitudinal analysis” (e.g., when a participant provides multiple measurements, over time) the application of fixed effects models is problematic. In an effort to answer this need, this paper generalizes non-linear mixed effects model to the regime where the response variable is manifold-valued, i.e., f : Rd → M. We derive the underlying model and estimation schemes and demonstrate the immediate benefits such a model can provide - both for group level and individual level analysis - on longitudinal brain imaging data. The direct consequence of our results is that longitudinal analysis of manifold-valued measurements (especially, the symmetric positive definite manifold) can be conducted in a computationally tractable manner.

UR - http://www.scopus.com/inward/record.url?scp=85041895927&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041895927&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2017.612

DO - 10.1109/CVPR.2017.612

M3 - Conference contribution

AN - SCOPUS:85041895927

T3 - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

SP - 5777

EP - 5786

BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -