Title | SGPP: spatial Gaussian predictive process models for neuroimaging data. |
Publication Type | Journal Article |
Year of Publication | 2014 |
Authors | Hyun, Jung Won, Yimei Li, John H. Gilmore, Zhaohua Lu, Martin Styner, and Hongtu Zhu |
Journal | Neuroimage |
Volume | 89 |
Pagination | 70-80 |
Date Published | 2014 Apr 01 |
ISSN | 1095-9572 |
Keywords | Computer Simulation, Female, Humans, Image Processing, Computer-Assisted, Infant, Lateral Ventricles, Male, Neuroimaging, Normal Distribution, Principal Component Analysis, Spatial Analysis |
Abstract | The aim of this paper is to develop a spatial Gaussian predictive process (SGPP) framework for accurately predicting neuroimaging data by using a set of covariates of interest, such as age and diagnostic status, and an existing neuroimaging data set. To achieve a better prediction, we not only delineate spatial association between neuroimaging data and covariates, but also explicitly model spatial dependence in neuroimaging data. The SGPP model uses a functional principal component model to capture medium-to-long-range (or global) spatial dependence, while SGPP uses a multivariate simultaneous autoregressive model to capture short-range (or local) spatial dependence as well as cross-correlations of different imaging modalities. We propose a three-stage estimation procedure to simultaneously estimate varying regression coefficients across voxels and the global and local spatial dependence structures. Furthermore, we develop a predictive method to use the spatial correlations as well as the cross-correlations by employing a cokriging technique, which can be useful for the imputation of missing imaging data. Simulation studies and real data analysis are used to evaluate the prediction accuracy of SGPP and show that SGPP significantly outperforms several competing methods, such as voxel-wise linear model, in prediction. Although we focus on the morphometric variation of lateral ventricle surfaces in a clinical study of neurodevelopment, it is expected that SGPP is applicable to other imaging modalities and features. |
DOI | 10.1016/j.neuroimage.2013.11.018 |
Alternate Journal | Neuroimage |
Original Publication | SGPP: Spatial Gaussian predictive process models for neuroimaging data. |
PubMed ID | 24269800 |
PubMed Central ID | PMC4134945 |
Grant List | HD053000 / HD / NICHD NIH HHS / United States P01CA142538-01 / CA / NCI NIH HHS / United States R01 MH086633 / MH / NIMH NIH HHS / United States P50 MH064065 / MH / NIMH NIH HHS / United States RR025747-01 / RR / NCRR NIH HHS / United States R01 ES017240 / ES / NIEHS NIH HHS / United States P30 HD003110 / HD / NICHD NIH HHS / United States R01 MH070890 / MH / NIMH NIH HHS / United States R01 HD053000 / HD / NICHD NIH HHS / United States U01 MH070890 / MH / NIMH NIH HHS / United States P01 CA142538 / CA / NCI NIH HHS / United States R21 AG033387 / AG / NIA NIH HHS / United States AG033387 / AG / NIA NIH HHS / United States R01 MH060352 / MH / NIMH NIH HHS / United States MH070890 / MH / NIMH NIH HHS / United States R01ES17240 / ES / NIEHS NIH HHS / United States AS1499 / / Autism Speaks / United States U54 EB005149 / EB / NIBIB NIH HHS / United States P30 HD03110 / HD / NICHD NIH HHS / United States MH086633 / MH / NIMH NIH HHS / United States R01 MH091645 / MH / NIMH NIH HHS / United States UL1 RR025747 / RR / NCRR NIH HHS / United States MH091645 / MH / NIMH NIH HHS / United States MH064065 / MH / NIMH NIH HHS / United States |
SGPP: spatial Gaussian predictive process models for neuroimaging data.
Project: