National Alliance for Medical Image Computing

The Publication Database hosted by SPL

All Publications | Upload | Advanced Search | Gallery View | Download Statistics | Help | Import | Log in

Bayesian Covariate Selection in Mixed-Effects Models For Longitudinal Shape Analysis

Institution:
1School of Computing & SCI Institute, University of Utah, Salt Lake City, UT, USA.
2Computer Science & Engineering, New York University, NY, USA.
3Department of Psychiatry, Carver College of Medicine, University of Iowa, IA, USA.
Publication Date:
Apr-2016
Journal:
Proc IEEE Int Symp Biomed Imaging.
Volume Number:
2016
Pages:
656-9
Citation:
Proc IEEE Int Symp Biomed Imaging. 2016 Apr; 2016: 656-9.
PubMed ID:
28090246
PMCID:
PMC5225990
Keywords:
Bayesian analysis, Huntington's disease, Longitudinal shape analysis, model selection
Appears in Collections:
NA-MIC
Sponsors:
U01 NS082086/NS/NINDS NIH HHS/United States
R01 NS40068/NS/NINDS NIH HHS/United States
R01 NS050568/NS/NINDS NIH HHS/United States
U54 EB005149/EB/NIBIB NIH HHS/United States
S10 RR023392/RR/NCRR NIH HHS/United States
R01 NS054893/NS/NINDS NIH HHS/United States
NSF CAREER grant 1054057
Generated Citation:
Muralidharan P., Fishbaugh J., Kim E.Y., Johnson H.J., Paulsen J.S., Gerig G., Fletcher P.T. Bayesian Covariate Selection in Mixed-Effects Models For Longitudinal Shape Analysis. Proc IEEE Int Symp Biomed Imaging. 2016 Apr; 2016: 656-9. PMID: 28090246 . PMCID: PMC5225990.
Downloaded: 80 times. [view map]
Paper: Download, View online
Export citation:
Google Scholar: link

The goal of longitudinal shape analysis is to understand how anatomical shape changes over time, in response to biological processes, including growth, aging, or disease. In many imaging studies, it is also critical to understand how these shape changes are affected by other factors, such as sex, disease diagnosis, IQ, etc. Current approaches to longitudinal shape analysis have focused on modeling age-related shape changes, but have not included the ability to handle covariates. In this paper, we present a novel Bayesian mixed-effects shape model that incorporates simultaneous relationships between longitudinal shape data and multiple predictors or covariates to the model. Moreover, we place an Automatic Relevance Determination (ARD) prior on the parameters, that lets us automatically select which covariates are most relevant to the model based on observed data. We evaluate our proposed model and inference procedure on a longitudinal study of Huntington's disease from PREDICT-HD. We first show the utility of the ARD prior for model selection in a univariate modeling of striatal volume, and next we apply the full high-dimensional longitudinal shape model to putamen shapes.

Additional Material
1 File (40.965kB)
Muralidharan-ISBI2016-fig2.jpg (40.965kB)