Classification of autism spectrum disorder from resting-state fMRI with mutual connectivity analysis

In this study, we investigate if differences in interaction between different brain regions for subjects with autism spectrum disorder (ASD) and healthy controls can be captured using resting-state fMRI. To this end, we investigate the use of mutual connectivity analysis with Local Models (MCA-LM), which estimates nonlinear measures of interaction between pairs of time-series in terms of cross-predictability. These pairwise measures provide a high-dimensional representation of connectivity profiles for subjects and are used as features for classification. Subsequently, we perform feature selection, reducing the dimension of the input space with the Kendall’s τ coefficient method. The Random Forests (RF) and AdaBoost classifiers are used. Performing machine learning on functional connectivity measures is commonly known as multi-voxel pattern analysis (MVPA). Traditionally, measures of functional connectivity are obtained with cross-correlation. Hence, as a metric to evaluate MCA-LM against, we also investigate classification performance with cross-correlation. The high area under receiver operating curve (AUC) and accuracy values for 100 different train/test separations across both classifiers using MCA-LM (mean AUC ranges between 0.78 - 0.85 and mean accuracy between 0.7 - 0.81) compared with standard MVPA analysis using cross-correlation between fMRI time-series (mean AUC ranges between 0.54 - 0.6 and mean accuracy between 0.50 - 0.57), across all the number of features selected demonstrates that such a nonlinear measure may be better suited at extracting information from the time-series data and has potential for the development of novel neuro-imaging biomarkers for ASD.

[1]  Anke Meyer-Bäse,et al.  Segmentation and classification of dynamic breast magnetic resonance image data , 2006, J. Electronic Imaging.

[2]  T. Nattkemper,et al.  Breast MRI data analysis by LLE , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[3]  C. Lord,et al.  Autism Diagnostic Observation Schedule , 2016 .

[4]  Axel Wismüller,et al.  The Exploration Machine - A Novel Method for Data Visualization , 2009, WSOM.

[5]  Ralph-Axel Müller,et al.  Underconnected, but how? A survey of functional connectivity MRI studies in autism spectrum disorders. , 2011, Cerebral cortex.

[6]  C. F. Kossack,et al.  Rank Correlation Methods , 1949 .

[7]  H. Ritter,et al.  The Deformable Feature Map — Adaptive Plasticity for Function Approximation , 1998 .

[8]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[9]  Axel Wismüller,et al.  Segmentation with neural networks , 2000 .

[10]  Axel Wismüller,et al.  Cluster Analysis of Biomedical Image Time-Series , 2002, International Journal of Computer Vision.

[11]  Axel Wismüller,et al.  Prediction of Biomechanical Properties of Trabecular Bone in MR Images With Geometric Features and Support Vector Regression , 2011, IEEE Transactions on Biomedical Engineering.

[12]  Axel Wismüller,et al.  Mutual connectivity analysis of resting-state functional MRI data with local models , 2018, NeuroImage.

[13]  Christian Kroos,et al.  Analysis of tongue configuration in multi-speaker, multi-volume MRI data , 2000 .

[14]  M. Reiser,et al.  Classification of Small Contrast Enhancing Breast Lesions in Dynamic Magnetic Resonance Imaging Using a Combination of Morphological Criteria and Dynamic Analysis Based on Unsupervised Vector-Quantization , 2008, Investigative radiology.

[15]  Thomas Villmann,et al.  Neighbor embedding XOM for dimension reduction and visualization , 2011, Neurocomputing.

[16]  Jared A. Nielsen,et al.  Multisite functional connectivity MRI classification of autism: ABIDE results , 2013, Front. Hum. Neurosci..

[17]  Y. S. Kim,et al.  Prevalence of autism spectrum disorders in a total population sample. , 2011, The American journal of psychiatry.

[18]  Axel Wismüller,et al.  Adaptive local dissimilarity measures for discriminative dimension reduction of labeled data , 2010, Neurocomputing.

[19]  Sean M. Polyn,et al.  Beyond mind-reading: multi-voxel pattern analysis of fMRI data , 2006, Trends in Cognitive Sciences.

[20]  Helge J. Ritter,et al.  The deformable feature map - a novel neurocomputing algorithm for adaptive plasticity in pattern analysis , 2002, Neurocomputing.

[21]  Axel Wismüller,et al.  Classification of small lesions on dynamic breast MRI: Integrating dimension reduction and out-of-sample extension into CADx methodology , 2014, Artif. Intell. Medicine.

[22]  高橋 栄.  Diagnostic and Statistical Manual of Mental Disorders(DSM)-5による分類と診断 (特集 周産期メンタルヘルス : 妊婦の不安とどう立ち向かうか) , 2014 .

[23]  Axel Wismüller,et al.  Classification of small lesions in dynamic breast MRI: eliminating the need for precise lesion segmentation through spatio-temporal analysis of contrast enhancement , 2012, Machine Vision and Applications.

[24]  Axel Wismüller,et al.  Computer-Aided Diagnosis for Phase-Contrast X-ray Computed Tomography: Quantitative Characterization of Human Patellar Cartilage with High-Dimensional Geometric Features , 2014, Journal of Digital Imaging.

[25]  Axel Wismüller,et al.  A Multivariate Granger Causality Concept towards Full Brain Functional Connectivity , 2016, PloS one.

[26]  Axel Wismüller,et al.  Nonlinear functional connectivity network recovery in the human brain with mutual connectivity analysis (MCA): convergent cross-mapping and non-metric clustering , 2015, Medical Imaging.

[27]  Axel Wismüller,et al.  Computer-Aided Diagnosis in Phase Contrast Imaging X-Ray Computed Tomography for Quantitative Characterization of ex vivo Human Patellar Cartilage , 2013, IEEE Transactions on Biomedical Engineering.

[28]  A. Meyer-Base,et al.  Stability analysis of a self-organizing neural network with feedforward and feedback dynamics , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[29]  Igor Pantic,et al.  Gray Level Co-Occurrence Matrix Texture Analysis of Germinal Center Light Zone Lymphocyte Nuclei: Physiology Viewpoint with Focus on Apoptosis , 2012, Microscopy and Microanalysis.

[30]  Peter Hastreiter,et al.  Bildverarbeitung für die Medizin 2003 , 2003 .

[31]  N. Tzourio-Mazoyer,et al.  Automated Anatomical Labeling of Activations in SPM Using a Macroscopic Anatomical Parcellation of the MNI MRI Single-Subject Brain , 2002, NeuroImage.

[32]  Dimitris Samaras,et al.  Deriving reproducible biomarkers from multi-site resting-state data: An Autism-based example , 2016, NeuroImage.

[33]  Michel Verleysen,et al.  Recent Advances in Nonlinear Dimensionality Reduction, Manifold and Topological Learning , 2010, ESANN.

[34]  B HuberMarkus,et al.  Texture feature ranking with relevance learning to classify interstitial lung disease patterns , 2012 .

[35]  Axel Wismüller.  The exploration machine: a novel method for analyzing high-dimensional data in computer-aided diagnosis , 2009, Medical Imaging.

[36]  Axel Wismüller,et al.  Texture feature ranking with relevance learning to classify interstitial lung disease patterns , 2012, Artif. Intell. Medicine.

[37]  Huafu Chen,et al.  Multivariate classification of autism spectrum disorder using frequency-specific resting-state functional connectivity—A multi-center study , 2016, Progress in Neuro-psychopharmacology and Biological Psychiatry.

[38]  Thomas Villmann,et al.  Exploratory Observation Machine (XOM) with Kullback-Leibler Divergence for Dimensionality Reduction and Visualization , 2010, ESANN.

[39]  George Sugihara,et al.  Detecting Causality in Complex Ecosystems , 2012, Science.

[40]  Anke Meyer-Bäse,et al.  Fully automated biomedical image segmentation by self-organized model adaptation , 2004, Neural Networks.

[41]  M. Reiser,et al.  Cluster analysis of signal-intensity time course in dynamic breast MRI: does unsupervised vector quantization help to evaluate small mammographic lesions? , 2006, European Radiology.

[42]  Axel Wismüller,et al.  A Neural Network Approach to Functional MRI Pattern Analysis — Clustering of Time-Series by Hierarchical Vector Quantization , 1998 .

[43]  Axel Wismüller,et al.  A Framework for Exploring Non-Linear Functional Connectivity and Causality in the Human Brain: Mutual Connectivity Analysis (MCA) of Resting-State Functional MRI with Convergent Cross-Mapping and Non-Metric Clustering , 2014, ArXiv.

[44]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[45]  M.Kleinberg Jon,et al.  Advances in Self-Organizing Maps, 7th International Workshop, WSOM 2009, St. Augustine, FL, USA, June 8-10, 2009. Proceedings , 2009, WSOM.

[46]  Axel Wismüller.  A Computational Framework for Nonlinear Dimensionality Reduction and Clustering , 2009, WSOM.

[47]  Axel Wismüller,et al.  Classification of interstitial lung disease patterns with topological texture features , 2010, Medical Imaging.

[48]  Thomas Martinetz,et al.  Medical image compression using topology-preserving neural networks , 2005, Eng. Appl. Artif. Intell..

[49]  M. First,et al.  Structured Clinical Interview for DSM-IV Axis I Disorders , 1997 .

[50]  Anke Meyer-Baese,et al.  Model-free functional MRI analysis using cluster-based methods , 2003, SPIE Defense + Commercial Sensing.

[51]  Alex Martin,et al.  Functional connectivity classification of autism identifies highly predictive brain features but falls short of biomarker standards , 2014, NeuroImage: Clinical.

[52]  T. Twellmann,et al.  Detection of suspicious lesions in dynamic contrast enhanced MRI data , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[53]  Phil Hoole,et al.  A Segmentation and Analysis Method for MRI Data of the Human Vocal Tract , 2003, Bildverarbeitung für die Medizin.