QUANTITATIVE MAGNETIC RESONANCE IMAGE ANALYSIS VIA THE EM ALGORITHM WITH STOCHASTIC VARIATION.

Quantitative Magnetic Resonance Imaging (qMRI) provides researchers insight into pathological and physiological alterations of living tissue, with the help of which, researchers hope to predict (local) therapeutic efficacy early and determine optimal treatment schedule. However, the analysis of qMRI has been limited to ad-hoc heuristic methods. Our research provides a powerful statistical framework for image analysis and sheds light on future localized adaptive treatment regimes tailored to the individual's response. We assume in an imperfect world we only observe a blurred and noisy version of the underlying pathological/physiological changes via qMRI, due to measurement errors or unpredictable influences. We use a hidden Markov Random Field to model the spatial dependence in the data and develop a maximum likelihood approach via the Expectation-Maximization algorithm with stochastic variation. An important improvement over previous work is the assessment of variability in parameter estimation, which is the valid basis for statistical inference. More importantly, we focus on the expected changes rather than image segmentation. Our research has shown that the approach is powerful in both simulation studies and on a real dataset, while quite robust in the presence of some model assumption violations.

• Publication year

  2008

• Venue

  Annals of Applied Statistics

• Publication date

  2008-07-29

• Fields of study

  Medicine, Mathematics, Engineering

• Identifiers
  DOI 10.1214/07-AOAS157arXiv 0807.4672PMID 20046819PMCID PMC2799942
• 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.

• Inference in hidden Markov models

  2010cited by this paper
• Contextual modeling of functional MR images with conditional random fields

  2006cited by this paper
• Inference in Hidden Markov Models

  2006cited by this paper
• Unsupervised Image Segmentation Using Markov Random Fields

  2005cited by this paper
• A stochastic method for Bayesian estimation of hidden Markov random field models with application to a color model

  2005cited by this paper
• Use of magnetic resonance imaging to assess blood-brain/blood-glioma barrier opening during conformal radiotherapy.

  2005cited by this paper
• Mixture models with adaptive spatial regularization for segmentation with an application to FMRI data

  2005cited by this paper
• Evaluation of the functional diffusion map as an early biomarker of time-to-progression and overall survival in high-grade glioma.

  2005cited by this paper
• Functional diffusion map: a noninvasive MRI biomarker for early stratification of clinical brain tumor response.

  2005influential reference
• Unsupervised image segmentation using a simple MRF model with a new implementation scheme

  2004influential reference
• The Focused Information Criterion

  2003cited by this paper
• Frequentist Model Average Estimators

  2003cited by this paper
• Image analysis: reconstructing the true scene from noisy images

  2003cited by this paper
• Model Selection and Multimodel Inference: A Practical Information-Theoretic Approach (2nd ed.)

  2003cited by this paper
• Model selection and multimodel inference : a practical information-theoretic approach

  2003cited by this paper
• GLOBAL OPTIMIZATION WITH EXPLORATION/SELECTION ALGORITHMS AND SIMULATED ANNEALING

  2002influential reference
• Double Markov random fields and Bayesian image segmentation

  2002cited by this paper
• Statistical properties of x-ray CT and MRI: from imaging physics to image statistics

  2002cited by this paper
• Bayesian approach to segmentation of statistical parametric maps

  2001influential reference
• Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm

  2001influential reference
• Probabilistic modeling of single-trial fMRI data

  2000cited by this paper
• Convergence of a stochastic approximation version of the EM algorithm

  1999cited by this paper
• Principles of magnetic resonance imaging : a signal processing perspective

  1999influential reference
• Model selection and multi-model inference

  1998cited by this paper
• Spatio-temporal fMRI analysis using Markov random fields

  1998cited by this paper
• fMRI signal restoration using a spatio-temporal Markov Random Field preserving transitions.

  1998cited by this paper
• Model selection: An integral part of inference

  1997cited by this paper
• Reversible jump Markov chain Monte Carlo computation and Bayesian model determination

  1995cited by this paper
• Analysis of fMRI time-series revisited--again.

  1995influential reference
• Parameter estimation and tissue segmentation from multispectral MR images

  1994cited by this paper
• Maximum-likelihood parameter estimation for unsupervised stochastic model-based image segmentation

  1994cited by this paper
• Unsupervised segmentation of noisy and textured images using Markov random fields

  1992cited by this paper
• A Monte Carlo Implementation of the EM Algorithm and the Poor Man's Data Augmentation Algorithms

  1990influential reference
• Simultaneous Parameter Estimation and Segmentation of Gibbs Random Fields Using Simulated Annealing

  1989influential reference
• An iterative Gibbsian technique for reconstruction of m-ary images

  1989cited by this paper
• Nonuniversal critical dynamics in Monte Carlo simulations.

  1987cited by this paper
• On the Statistical Analysis of Dirty Pictures

  1986cited by this paper
• On Jointly Estimating Parameters and Missing Data by Maximizing the Complete-Data Likelihood

  1983cited by this paper
• Finding the Observed Information Matrix When Using the EM Algorithm

  1982cited by this paper
• Estimating the Dimension of a Model

  1978cited 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
• Information Theory and an Extension of the Maximum Likelihood Principle

  1973cited by this paper
• Some generalized order-disorder transformations

  1952influential reference

• Exploring the Potential of Machine Learning Algorithms to Improve Diffusion Nuclear Magnetic Resonance Imaging Models Analysis

  2024cites this paper
• Ordered homogeneity pursuit lasso for group variable selection with applications to spectroscopic data

  2017cites this paper
• High Dimensional Dependent Data Analysis for Neuroimaging.

  2016cites this paper
• Evaluation of image registration spatial accuracy using a Bayesian hierarchical model

  2014cites this paper
• Multiple testing for neuroimaging via hidden Markov random field

  2014cites this paper
• Model-Based Image Segmentation via Monte Carlo EM , with Application to DCE-MRI

  2013influential citation
• Functional magnetic resonance imaging data clustering

  2013cites this paper
• Change point estimation in multi-subject fMRI studies

  2010cites this paper
• SOCIAL NETWORK MODELS FOR IDENTIFYING ACTIVE BRAIN REGIONS FROM FMRI DATA

  2010cites this paper
• Longitudinal image analysis of tumour–healthy brain change in contrast uptake induced by radiation

  2010influential citation
• A Bayesian Image Analysis of Radiation Induced Changes in Tumor Vascular Permeability.

  2010influential citation