The NPAIRS Computational Statistics Framework for Data Analysis in Neuroimaging

被引：17

作者：

Strother, Stephen ^{[1
,2
]}

Oder, Anita ^{[1
]}

Spring, Robyn ^{[1
,2
]}

Grady, Cheryl ^{[1
]}

机构：

[1] Baycrest, Rotman Res Inst, 3560 Bathurst St, Toronto, ON, Canada

[2] Univ Toronto, Dept Med Biophys, Toronto, ON, Canada

来源：

COMPSTAT'2010: 19TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL STATISTICS | 2010年

关键词：

prediction; reproducibility; penalized discriminant analysis; fMRI; QUANTITATIVE-EVALUATION; FMRI; PIPELINES;

D O I：

10.1007/978-3-7908-2604-3_10

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

We introduce the role of resampling and prediction (p) metrics for flexible discriminant modeling in neuroimaging, and highlight the importance of combining these with measurements of the reproducibility (r) of extracted brain activation patterns. Using the NPAIRS resampling framework we illustrate the use of (p, r) plots as a function of the size of the principal component subspace (Q) for a penalized discriminant analysis (PDA) to: optimize processing pipelines in functional magnetic resonance imaging (fMRI), and measure the global SNR (gSNR) and dimensionality of fMRI data sets. We show that the gSNRs of typical fMRI data sets cause the optimal Q for a PDA to often lie in a phase transition region between gSNR similar or equal to 1 with large optimal Q versus SNR >> 1 with small optimal Q.

引用

页码：111 / 120

页数：10

共 17 条

[1]

AFSHINPOUR B, HUM BRAIN M IN PRESS

[2] Improvements on cross-validation: The .632+ bootstrap method [J].

Efron, B ;

Tibshirani, R .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1997, 92 (438) :548-560

[3]

Efron B., 1993, INTRO BOOTSTRAP, DOI 10.1007/978-1-4899-4541-9

[4] Group specific optimisation of fMRI processing steps for child and adult data [J].

Evans, J. W. ;

Todd, R. M. ;

Taylor, M. J. ;

Strother, S. C. .

NEUROIMAGE, 2010, 50 (02) :479-490

[5] Age-related changes in brain activity across the adult lifespan [J].

Grady, CL ;

Springer, MV ;

Hongwanishkul, D ;

McIntosh, AR ;

Winocur, G .

JOURNAL OF COGNITIVE NEUROSCIENCE, 2006, 18 (02) :227-241

[6] Bayesian model comparison in nonlinear BOLD fMRI hemodynamics [J].

Jacobsen, Daniel J. ;

Hansen, Lars Kai ;

Madsen, Kristoffer Hougaard .

NEURAL COMPUTATION, 2008, 20 (03) :738-755

[7] The quantitative evaluation of functional neuroimaging experiments: Mutual information learning curves [J].

Kjems, U ;

Hansen, LK ;

Anderson, J ;

Frutiger, S ;

Muley, S ;

Sidtis, J ;

Rottenberg, D ;

Strother, SC .

NEUROIMAGE, 2002, 15 (04) :772-786

[8] Penalized discriminant analysis of [15O]-water PET brain images with prediction error selection of smoothness and regularization hyperparameters [J].

Kustra, R ;

Strother, S .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 2001, 20 (05) :376-387

[9] The evaluation of preprocessing choices in single-subject BOLD fMRI using NPAIRS performance metrics [J].

LaConte, S ;

Anderson, J ;

Muley, S ;

Ashe, J ;

Frutiger, S ;

Rehm, K ;

Hansen, LK ;

Yacoub, E ;

Hu, XP ;

Rottenberg, D ;

Strother, S .

NEUROIMAGE, 2003, 18 (01) :10-27

[10]

Mardia K. V., 1979, Multivariate Analysis

← 1 2 →