Automated Knowledge Discovery from Functional Magnetic Resonance Images using Spatial Coherence

Functional Magnetic Resonance Imaging (fMRI) has the potential to unlock many of the mysteries of the brain. Although this imaging modality is popular for brain-mapping activities, clinical applications of this technique are relatively rare. For clinical applications, classification models are more useful than the current practice of reporting loci of neural activation associated with particular disorders. Also, since the methods used to account for anatomical variations between subjects are generally imprecise, the conventional voxel-by-voxel analysis limits the types of discoveries that are possible. This work presents a classification-based framework for knowledge discovery from fMRI data. Instead of voxel-centric knowledge discovery, this framework is segment-centric, where functional segments are clumps of voxels that represent a functional unit in the brain. With simulated activation images, it is shown that this segment-based approach can be more successful for knowledge discovery than conventional voxel-based approaches. The spatial coherence principle refers to the homogeneity of behavior of spatially contiguous voxels. Auto-threshold Contrast Enhancing Iterative Clustering (ACEIC) - a new algorithm based on the spatial coherence principle is presented here for functional segmentation. With benchmark data, it is shown that the ACEIC method can achieve higher segmentation accuracy than Probabilistic Independent Component Analysis - a popular method used for fMRI data analysis. The spatial coherence principle can also be exploited for voxel-centric image-classification problems. Spatially Coherent Voxels (SCV) is a new feature selection method that uses the spatial coherence principle to eliminate features that are unlikely to be useful for classification. For a Substance Use Disorder dataset, it is demonstrated that feature selection with SCV can achieve higher classification accuracies than conventional feature selection methods.

[1]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[2]  W. W. Hansen,et al.  The Nuclear Induction Experiment , 1946 .

[3]  Vince D. Calhoun,et al.  ICA of functional MRI data: an overview. , 2003 .

[4]  Zoran Obradovic,et al.  Subjective Probability , 1994 .

[5]  L. Sirovich.  Turbulence and the dynamics of coherent structures. I. Coherent structures , 1987 .

[6]  J. Ashburner,et al.  Nonlinear spatial normalization using basis functions , 1999, Human brain mapping.

[7]  Yingli Lu,et al.  Region growing method for the analysis of functional MRI data , 2003, NeuroImage.

[8]  P. Lauterbur,et al.  Image Formation by Induced Local Interactions: Examples Employing Nuclear Magnetic Resonance , 1973, Nature.

[9]  Karl J. Friston,et al.  Statistical parametric maps in functional imaging: A general linear approach , 1994 .

[10]  Jean-Baptiste Poline,et al.  Dealing with the shortcomings of spatial normalization: Multi‐subject parcellation of fMRI datasets , 2006, Human brain mapping.

[11]  L. K. Hansen,et al.  On Clustering fMRI Time Series , 1999, NeuroImage.

[12]  S C Strother,et al.  Comparison of voxel- and volume-of-interest-based analyses in FDG PET scans of HIV positive and healthy individuals. , 2000, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[13]  M. D’Esposito,et al.  Experimental Design for Brain fMRI , 2000 .

[14]  Beatriz Luna,et al.  Combining Brains: A Survey of Methods for Statistical Pooling of Information , 2002, NeuroImage.

[15]  Ray L. Somorjai,et al.  Exploring regions of interest with cluster analysis (EROICA) using a spectral peak statistic for selecting and testing the significance of fMRI activation time-series , 2002, Artif. Intell. Medicine.

[16]  Stephen M. Smith,et al.  Improved Optimization for the Robust and Accurate Linear Registration and Motion Correction of Brain Images , 2002, NeuroImage.

[17]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[18]  Lei Zhang,et al.  Machine learning for clinical diagnosis from functional magnetic resonance imaging , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[19]  Karl J. Friston,et al.  To Smooth or Not to Smooth? Bias and Efficiency in fMRI Time-Series Analysis , 2000, NeuroImage.

[20]  M. Paulus,et al.  An fMRI Study of Response Inhibition in Youths with a Family History of Alcoholism , 2004, Annals of the New York Academy of Sciences.

[21]  S. C. Johnson.  Hierarchical clustering schemes , 1967, Psychometrika.

[22]  Fillia Makedon,et al.  Patient Classification of fMRI Activation Maps , 2003, MICCAI.

[23]  R Baumgartner,et al.  A hierarchical clustering method for analyzing functional MR images. , 1999, Magnetic resonance imaging.

[24]  Ali S. Hadi,et al.  Finding Groups in Data: An Introduction to Chster Analysis , 1991 .

[25]  M. J. Meloy,et al.  Blood oxygen level dependent response and spatial working memory in adolescents with alcohol use disorders. , 2004, Alcoholism, clinical and experimental research.

[26]  Gregory G. Brown,et al.  fMRI response to spatial working memory in adolescents with comorbid marijuana and alcohol use disorders. , 2005, Drug and alcohol dependence.

[27]  Nicole A Lazar,et al.  Assessing the sensitivity of fMRI group maps , 2004, NeuroImage.

[28]  S Makeig,et al.  Analysis of fMRI data by blind separation into independent spatial components , 1998, Human brain mapping.

[29]  Satrajit S. Ghosh,et al.  Region of interest based analysis of functional imaging data , 2003, NeuroImage.

[30]  Stephen M. Smith,et al.  Probabilistic independent component analysis for functional magnetic resonance imaging , 2004, IEEE Transactions on Medical Imaging.

[31]  E. Capaldi,et al.  The organization of behavior. , 1992, Journal of applied behavior analysis.

[32]  X Hu,et al.  Retrospective estimation and correction of physiological fluctuation in functional MRI , 1995, Magnetic resonance in medicine.

[33]  Ewald Moser,et al.  On the origin of respiratory artifacts in BOLD-EPI of the human brain. , 2002, Magnetic resonance imaging.

[34]  R W Cox,et al.  AFNI: software for analysis and visualization of functional magnetic resonance neuroimages. , 1996, Computers and biomedical research, an international journal.

[35]  Cor J. Veenman,et al.  A Maximum Variance Cluster Algorithm , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[36]  Mark W. Woolrich,et al.  Advances in functional and structural MR image analysis and implementation as FSL , 2004, NeuroImage.

[37]  B. J. McCurtain,et al.  Dorsal cortical regions subserving visually guided saccades in humans: an fMRI study. , 1998, Cerebral cortex.

[38]  D. P. Russell,et al.  Functional Clustering: Identifying Strongly Interactive Brain Regions in Neuroimaging Data , 1998, NeuroImage.

[39]  G. Barker,et al.  Study design in fMRI: Basic principles , 2006, Brain and Cognition.

[40]  Vanathi Gopalakrishnan,et al.  Segmentation of fMRI Data by Maximization of Region Contrast , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[41]  Michael Brady,et al.  Improved Optimization for the Robust and Accurate Linear Registration and Motion Correction of Brain Images , 2002, NeuroImage.

[42]  I. Johnsrude,et al.  The problem of functional localization in the human brain , 2002, Nature Reviews Neuroscience.

[43]  N. Minshew,et al.  Maturation of Widely Distributed Brain Function Subserves Cognitive Development , 2001, NeuroImage.

[44]  Nikolas P. Galatsanos,et al.  Segmentation of dynamic PET or fMRI images based on a similarity metric , 2003 .

[45]  C. Genovese,et al.  Functional Imaging Analysis Software — Computational Olio , 1996 .

[46]  D. Tank,et al.  Brain magnetic resonance imaging with contrast dependent on blood oxygenation. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[47]  Lawrence Sirovich,et al.  Management and Analysis of Large Scientific Datasets , 1992 .

[48]  Tom M. Mitchell,et al.  Classifying Instantaneous Cognitive States from fMRI Data , 2003, AMIA.

[49]  Isaac N. Bankman,et al.  Handbook of medical imaging , 2000 .

[50]  Bernard Widrow,et al.  30 years of adaptive neural networks: perceptron, Madaline, and backpropagation , 1990, Proc. IEEE.

[51]  Jean-Francois Mangin,et al.  Coordinate-based versus structural approaches to brain image analysis , 2004, Artif. Intell. Medicine.

[52]  Josef Kittler,et al.  Region growing: a new approach , 1998, IEEE Trans. Image Process..

[53]  Graham J. Williams,et al.  Data Mining , 2000, Communications in Computer and Information Science.

[54]  E. Purcell,et al.  Resonance Absorption by Nuclear Magnetic Moments in a Solid , 1946 .

[55]  Mark S. Cohen.  Echo-Planar Imaging and Functional MRI , 2000 .

[56]  D. Heeger,et al.  Linear Systems Analysis of Functional Magnetic Resonance Imaging in Human V1 , 1996, The Journal of Neuroscience.

[57]  S. Ruan,et al.  A multistep Unsupervised Fuzzy Clustering Analysis of fMRI time series , 2000, Human brain mapping.

[58]  G H Glover,et al.  Image‐based method for retrospective correction of physiological motion effects in fMRI: RETROICOR , 2000, Magnetic resonance in medicine.

[59]  W. Eric L. Grimson,et al.  Discriminative Analysis for Image-Based Studies , 2002, MICCAI.

[60]  Stuart Clare,et al.  Functional MRI : Methods and Applications , 1997 .

[61]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[62]  Marcus E. Raichle,et al.  Functional Neuroimaging: A Historical and Physiological Perspective , 2001 .

[63]  Randy L. Buckner,et al.  Functional Neuroimaging Methods: PET and fMRI , 2001 .

[64]  Peter J. Rousseeuw,et al.  Finding Groups in Data: An Introduction to Cluster Analysis , 1990 .

[65]  Karl J. Friston,et al.  Movement‐Related effects in fMRI time‐series , 1996, Magnetic resonance in medicine.

[66]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

[67]  V D Calhoun,et al.  Spatial and temporal independent component analysis of functional MRI data containing a pair of task‐related waveforms , 2001, Human brain mapping.

[68]  R. Turner,et al.  Characterization and Correction of Interpolation Effects in the Realignment of fMRI Time Series , 2000, NeuroImage.

[69]  Takeshi Yokoo,et al.  Multivariate Statistical Analysis of Functional Neuroimaging Data , 2004 .

[70]  C. Pierrot-Deseilligny,et al.  Eye movement control by the cerebral cortex , 2004, Current opinion in neurology.

[71]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[72]  William Gardner,et al.  Neurobehavioral disinhibition in childhood predicts early age at onset of substance use disorder. , 2003, The American journal of psychiatry.

[73]  Jonathan D. Cohen,et al.  Improved Assessment of Significant Activation in Functional Magnetic Resonance Imaging (fMRI): Use of a Cluster‐Size Threshold , 1995, Magnetic resonance in medicine.

[74]  Kurt Hornik,et al.  A quantitative comparison of functional MRI cluster analysis , 2004, Artif. Intell. Medicine.

[75]  Karl J. Friston,et al.  Human Brain Function , 1997 .