Multiple testing for neuroimaging via hidden Markov random field

Traditional voxel‐level multiple testing procedures in neuroimaging, mostly p‐value based, often ignore the spatial correlations among neighboring voxels and thus suffer from substantial loss of power. We extend the local‐significance‐index based procedure originally developed for the hidden Markov chain models, which aims to minimize the false nondiscovery rate subject to a constraint on the false discovery rate, to three‐dimensional neuroimaging data using a hidden Markov random field model. A generalized expectation–maximization algorithm for maximizing the penalized likelihood is proposed for estimating the model parameters. Extensive simulations show that the proposed approach is more powerful than conventional false discovery rate procedures. We apply the method to the comparison between mild cognitive impairment, a disease status with increased risk of developing Alzheimer's or another dementia, and normal controls in the FDG‐PET imaging study of the Alzheimer's Disease Neuroimaging Initiative.

• Publication year

  2014

• Venue

  Biometrics

• Publication date

  2014-04-04

• Fields of study

  Medicine, Computer Science, Mathematics

• Identifiers
  DOI 10.1111/biom.12329arXiv 1404.1371PMID 26012881PMCID PMC4579542
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• False discovery control in large‐scale spatial multiple testing

  2015cited by this paper
• COMPOSITE LIKELIHOOD UNDER HIDDEN MARKOV MODEL

  2015cited by this paper
• PET Approaches for Diagnosis of Dementia

  2014cited by this paper
• Regularized Functional Regression Models with Applications to Brain Imaging.

  2013influential reference
• A Bayesian non-parametric Potts model with application to pre-surgical FMRI data

  2013cited by this paper
• Bayesian scalar-on-image regression with application to association between intracranial DTI and cognitive outcomes

  2013cited by this paper
• Multi-region analysis of longitudinal FDG-PET for the classification of Alzheimer's disease

  2012cited by this paper
• MULTIPLE TESTING VIA FDRL FOR LARGE SCALE IMAGING DATA

  2011cited by this paper
• Associations between cognitive, functional, and FDG-PET measures of decline in AD and MCI.

  2011cited by this paper
• One-dimensional Markov random fields, Markov chains and topological Markov fields

  2011cited by this paper
• Diagnosis of Dementia Using Nuclear Medicine Imaging Modalities

  2011influential reference
• Relative capability of MR imaging and FDG PET to depict changes associated with prodromal and early Alzheimer disease.

  2010cited by this paper
• A hidden Markov random field model for genome-wide association studies.

  2010cited by this paper
• Topological FDR for neuroimaging

  2010cited by this paper
• A First Course in Bayesian Statistical Methods

  2009cited by this paper
• Large‐scale multiple testing under dependence

  2009cited by this paper
• Multiple testing in genome-wide association studies via hidden Markov models

  2009influential reference
• Simultaneous Testing of Grouped Hypotheses: Finding Needles in Multiple Haystacks

  2009cited by this paper
• False discovery rate revisited: FDR and topological inference using Gaussian random fields

  2009cited by this paper
• Longitudinal brain metabolic changes from amnestic mild cognitive impairment to Alzheimer's disease.

  2009influential reference
• Categorical and correlational analyses of baseline fluorodeoxyglucose positron emission tomography images from the Alzheimer's Disease Neuroimaging Initiative (ADNI)

  2009influential reference
• INFERENCE FOR NORMAL MIXTURES IN MEAN AND VARIANCE

  2008cited by this paper
• On false discovery control under dependence

  2008cited by this paper
• Multicenter Standardized 18F-FDG PET Diagnosis of Mild Cognitive Impairment, Alzheimer's Disease, and Other Dementias

  2008cited by this paper
• QUANTITATIVE MAGNETIC RESONANCE IMAGE ANALYSIS VIA THE EM ALGORITHM WITH STOCHASTIC VARIATION.

  2008cited by this paper
• Large-Scale Simultaneous Hypothesis Testing: The Choice of a Null Hypothesis

  2008cited by this paper
• Gender differences in brain reserve : an (18)F-FDG PET study in Alzheimer's disease.

  2007cited by this paper
• Oracle and Adaptive Compound Decision Rules for False Discovery Rate Control

  2007influential reference
• Maximum likelihood from spatial random effects models via the stochastic approximation expectation maximization algorithm

  2007cited by this paper
• False Discovery Rates for Spatial Signals

  2007cited by this paper
• Size, power and false discovery rates

  2007cited by this paper
• Some Results on the Control of the False Discovery Rate under Dependence

  2007cited by this paper
• Forecasting the global burden of Alzheimer's disease

  2007influential reference
• False discovery control with p-value weighting

  2006cited by this paper
• Brain glucose metabolism in the early and specific diagnosis of Alzheimer’s disease

  2005cited by this paper
• Reduced hippocampal metabolism in MCI and AD

  2005cited by this paper
• 18F-FDG PET findings in frontotemporal dementia: an SPM analysis of 29 patients.

  2005cited by this paper
• A stochastic process approach to false discovery control

  2004cited by this paper
• Large-Scale Simultaneous Hypothesis Testing

  2004cited by this paper
• Hidden Markov Measure Field Models for Image Segmentation

  2003cited by this paper
• Controlling the familywise error rate in functional neuroimaging: a comparative review

  2003cited by this paper
• Limbic hypometabolism in Alzheimer's disease and mild cognitive impairment

  2003cited by this paper
• The positive false discovery rate: a Bayesian interpretation and the q-value

  2003cited by this paper
• Operating characteristics and extensions of the false discovery rate procedure

  2002cited by this paper
• Thresholding of Statistical Maps in Functional Neuroimaging Using the False Discovery Rate

  2002cited by this paper
• Longitudinal PET Evaluation of Cerebral Metabolic Decline in Dementia: A Potential Outcome Measure in Alzheimer's Disease Treatment Studies.

  2002cited by this paper
• Clinical application of positron emission tomography for diagnosis of dementia

  2002influential reference
• Introduction to Numerical Analysis

  2002cited by this paper
• Image Analysis, Random Fields and Markov Chain Monte Carlo Methods: A Mathematical Introduction

  2002cited by this paper
• THE CONTROL OF THE FALSE DISCOVERY RATE IN MULTIPLE TESTING UNDER DEPENDENCY

  2001cited by this paper
• Penalized Maximum Likelihood Estimator for Normal Mixtures

  2000influential reference
• On the Adaptive Control of the False Discovery Rate in Multiple Testing With Independent Statistics

  2000cited by this paper
• Markov Chains: Gibbs Fields, Monte Carlo Simulation, and Queues

  2000cited by this paper
• Brodmann's localisation in the cerebral cortex

  1999cited by this paper
• Resampling-based false discovery rate controlling multiple test procedures for correlated test statistics

  1999cited by this paper
• Maximizing generalized linear mixed model likelihoods with an automated Monte Carlo EM algorithm

  1999cited by this paper
• Simulating Normalizing Constants: From Importance Sampling to Bridge Sampling to Path Sampling

  1998cited by this paper
• Maximum Likelihood Estimation of Hidden Markov Model Parameters, with Application to Medical Image Segmentation

  1997cited by this paper
• Markov chain Monte Carlo in Practice

  1996cited by this paper
• A Smooth Nonparametric Estimate of a Mixing Distribution Using Mixtures of Gaussians

  1996cited by this paper
• Controlling the false discovery rate: a practical and powerful approach to multiple testing

  1995influential reference
• A diagnostic approach in Alzheimer's disease using three-dimensional stereotactic surface projections of fluorine-18-FDG PET.

  1995cited by this paper
• Simple conditions for the convergence of the Gibbs sampler and Metropolis-Hastings algorithms

  1994cited by this paper
• Constrained Monte Carlo Maximum Likelihood for Dependent Data

  1992cited by this paper
• the Mean Field Theory in EM Procedures for Markov Random Fields

  1991cited by this paper
• An iterative Gibbsian technique for reconstruction of m-ary images

  1989cited by this paper
• Introduction to numerical analysis: 2nd edition

  1987cited by this paper
• Introduction To Modern Statistical Mechanics

  1987cited by this paper
• Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images

  1984cited by this paper
• The fluorodeoxyglucose 18F scan in Alzheimer's disease and multi-infarct dementia.

  1983cited by this paper
• Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper

  1977cited by this paper
• Spatial Interaction and the Statistical Analysis of Lattice Systems

  1974cited by this paper
• THE GENERALIZATION OF ‘STUDENT'S’ PROBLEM WHEN SEVERAL DIFFERENT POPULATION VARLANCES ARE INVOLVED

  1947cited by this paper
• The generalisation of student's problems when several different population variances are involved.

  1947cited by this paper

• A False Discovery Rate Control Method Using a Fully Connected Hidden Markov Random Field for Neuroimaging Data

  2025influential citation
• Nonparametric Density Estimation in a Mixed Model Using Wavelets

  2025cites this paper
• Spatially adaptive variable screening in presurgical functional magnetic resonance imaging data analysis.

  2024cites this paper
• DART: Distance Assisted Recursive Testing

  2024cites this paper
• DeepFDR: A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data

  2023influential citation
• Large-scale dependent multiple testing via hidden semi-Markov models

  2023cites this paper
• Covariate-modulated large-scale multiple testing under dependence

  2023cites this paper
• Spatially Adaptive Variable Screening in Presurgical fMRI Data Analysis

  2023cites this paper
• False Discovery Rate Control For Structured Multiple Testing: Asymmetric Rules And Conformal Q-values

  2023cites this paper
• Large‐scale covariate‐assisted two‐sample inference under dependence

  2022cites this paper
• Multiple testing in genome-wide association studies via hierarchical hidden Markov models

  2022cites this paper
• Inference with approximate local false discovery rates.

  2022cites this paper
• Semi-parametric hidden Markov model for large-scale multiple testing under dependency

  2022cites this paper
• Large-scale multiple testing via multivariate hidden Markov models

  2022cites this paper
• Multiple Testing in Nonparametric Hidden Markov Models: An Empirical Bayes Approach

  2021influential citation
• Covariate-adjusted multiple testing in genome-wide association studies via factorial hidden Markov models

  2021cites this paper
• Distance Assisted Recursive Testing

  2021cites this paper
• Multiple Hypothesis Testing Framework for Spatial Signals

  2021cites this paper
• Hidden Markov model in multiple testing on dependent count data

  2020cites this paper
• Effect-Size Estimation Using Semiparametric Hierarchical Mixture Models in Disease-Association Studies with Neuroimaging Data

  2020influential citation
• LAWS: A Locally Adaptive Weighting and Screening Approach to Spatial Multiple Testing

  2020cites this paper
• 36 52-4 3 Structural Magnetic Resonance Imaging

  2019cites this paper
• Bayesian hidden Markov models for dependent large-scale multiple testing

  2019cites this paper
• Bayesian Multiple Hypothesis Testing For Distributed Detection In Sensor Networks

  2019cites this paper
• Detected Changes in Precipitation Extremes at Their Native Scales Derived from In Situ Measurements

  2019cites this paper
• A Model-Based Framework for Voxel and Region Level Inferences in Neuroimaging Disease-Association Studies

  2019cites this paper
• Bayesian analysis of functional magnetic resonance imaging data with spatially varying auto‐regressive orders

  2018cites this paper
• Statistical disease mapping for heterogeneous neuroimaging studies

  2018cites this paper
• A peeling algorithm for multiple testing on a random field

  2018cites this paper
• Bayesian Analysis of fMRI data with Spatially-Varying Autoregressive Orders

  2017cites this paper
• Recent publications from the Alzheimer's Disease Neuroimaging Initiative: Reviewing progress toward improved AD clinical trials

  2017cites this paper
• Spatially Dependent Multiple Testing Under Model Misspecification, With Application to Detection of Anthropogenic Influence on Extreme Climate Events

  2017influential citation
• Bayesian Computation with Application to Spatial Models and Neuroimaging

  2017influential citation
• A peeling algorithm for multiple testing on a random field

  2017cites this paper
• A Feasibility Study of Using the NeuCube Spiking Neural Network Architecture for Modelling Alzheimer's Disease EEG Data

  2015cites this paper
• False Discovery Rate Smoothing

  2014cites this paper