Locally linear embedding (LLE) for MRI based Alzheimer's disease classification

Modern machine learning algorithms are increasingly being used in neuroimaging studies, such as the prediction of Alzheimer's disease (AD) from structural MRI. However, finding a good representation for multivariate brain MRI features in which their essential structure is revealed and easily extractable has been difficult. We report a successful application of a machine learning framework that significantly improved the use of brain MRI for predictions. Specifically, we used the unsupervised learning algorithm of local linear embedding (LLE) to transform multivariate MRI data of regional brain volume and cortical thickness to a locally linear space with fewer dimensions, while also utilizing the global nonlinear data structure. The embedded brain features were then used to train a classifier for predicting future conversion to AD based on a baseline MRI. We tested the approach on 413 individuals from the Alzheimer's Disease Neuroimaging Initiative (ADNI) who had baseline MRI scans and complete clinical follow-ups over 3 years with the following diagnoses: cognitive normal (CN; n=137), stable mild cognitive impairment (s-MCI; n=93), MCI converters to AD (c-MCI, n=97), and AD (n=86). We found that classifications using embedded MRI features generally outperformed (p<0.05) classifications using the original features directly. Moreover, the improvement from LLE was not limited to a particular classifier but worked equally well for regularized logistic regressions, support vector machines, and linear discriminant analysis. Most strikingly, using LLE significantly improved (p=0.007) predictions of MCI subjects who converted to AD and those who remained stable (accuracy/sensitivity/specificity: =0.68/0.80/0.56). In contrast, predictions using the original features performed not better than by chance (accuracy/sensitivity/specificity: =0.56/0.65/0.46). In conclusion, LLE is a very effective tool for classification studies of AD using multivariate MRI data. The improvement in predicting conversion to AD in MCI could have important implications for health management and for powering therapeutic trials by targeting non-demented subjects who later convert to AD.

[1]  Christos Davatzikos,et al.  Why voxel-based morphometric analysis should be used with great caution when characterizing group differences , 2004, NeuroImage.

[2]  Ramon Casanova,et al.  High Dimensional Classification of Structural MRI Alzheimer’s Disease Data Based on Large Scale Regularization , 2011, Front. Neuroinform..

[3]  Joarder Kamruzzaman,et al.  z-SVM: An SVM for Improved Classification of Imbalanced Data , 2006, Australian Conference on Artificial Intelligence.

[4]  Vikas Singh,et al.  Predictive markers for AD in a multi-modality framework: An analysis of MCI progression in the ADNI population , 2011, NeuroImage.

[5]  René Vidal,et al.  Segmenting Fiber Bundles in Diffusion Tensor Images , 2008, ECCV.

[6]  Marie Chupin,et al.  Automatic classi fi cation of patients with Alzheimer ' s disease from structural MRI : A comparison of ten methods using the ADNI database , 2010 .

[7]  Zhi-Hua Zhou,et al.  Supervised nonlinear dimensionality reduction for visualization and classification , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[8]  D. Rueckert,et al.  Multi-Method Analysis of MRI Images in Early Diagnostics of Alzheimer's Disease , 2011, PloS one.

[9]  T. Chan,et al.  Independent component analysis-based classification of Alzheimer's disease MRI data. , 2011, Journal of Alzheimer's disease : JAD.

[10]  J. Trojanowski,et al.  Prediction of MCI to AD conversion, via MRI, CSF biomarkers, and pattern classification , 2011, Neurobiology of Aging.

[11]  Li Ma,et al.  Local Manifold Learning-Based $k$ -Nearest-Neighbor for Hyperspectral Image Classification , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[12]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[13]  Daoqiang Zhang,et al.  Multimodal classification of Alzheimer's disease and mild cognitive impairment , 2011, NeuroImage.

[14]  Joachim Selbig,et al.  Non-linear PCA: a missing data approach , 2005, Bioinform..

[15]  Dit-Yan Yeung,et al.  Robust locally linear embedding , 2006, Pattern Recognit..

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

[17]  J. Pariente,et al.  Early diagnosis of Alzheimer's disease using cortical thickness: impact of cognitive reserve , 2009, Brain : a journal of neurology.

[18]  Kathryn Ziegler-Graham,et al.  Forecasting the global burden of Alzheimer’s disease , 2007, Alzheimer's & Dementia.

[19]  David C. Reutens,et al.  Development of a new tool to correlate stroke outcome with infarct topography: A proof-of-concept study , 2010, NeuroImage.

[20]  Bruce Fischl,et al.  Within-subject template estimation for unbiased longitudinal image analysis , 2012, NeuroImage.

[21]  C. Davatzikos.  Baseline and longitudinal patterns of brain atrophy in MCI patients, and their use in prediction of short-term conversion to AD: Results from ADNI , 2009, Alzheimer's & Dementia.

[22]  Sung Yong Shin,et al.  Individual subject classification for Alzheimer's disease based on incremental learning using a spatial frequency representation of cortical thickness data , 2012, NeuroImage.

[23]  Christian Böhm,et al.  Automated detection of brain atrophy patterns based on MRI for the prediction of Alzheimer's disease , 2010, NeuroImage.

[24]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[25]  Vladimir Fonov,et al.  Prediction of Alzheimer's disease in subjects with mild cognitive impairment from the ADNI cohort using patterns of cortical thinning , 2013, NeuroImage.

[26]  Kilian Q. Weinberger,et al.  Unsupervised Learning of Image Manifolds by Semidefinite Programming , 2004, CVPR.

[27]  Nick C Fox,et al.  The Alzheimer's disease neuroimaging initiative (ADNI): MRI methods , 2008, Journal of magnetic resonance imaging : JMRI.

[28]  Juha Koikkalainen,et al.  Multi-template tensor-based morphometry: Application to analysis of Alzheimer's disease , 2011, NeuroImage.

[29]  Arthur W. Toga,et al.  Automated hippocampal shape analysis predicts the onset of dementia in mild cognitive impairment , 2011, NeuroImage.

[30]  Stefan Klöppel,et al.  Estimating the age of healthy subjects from T1-weighted MRI scans using kernel methods: Exploring the influence of various parameters , 2010, NeuroImage.

[31]  Markus Nilsson,et al.  Dimensionality reduction of fMRI time series data using locally linear embedding , 2010, Magnetic Resonance Materials in Physics, Biology and Medicine.

[32]  J. Morris.  The Clinical Dementia Rating (CDR) , 1993, Neurology.

[33]  Peter A. Bandettini,et al.  Does feature selection improve classification accuracy? Impact of sample size and feature selection on classification using anatomical magnetic resonance images , 2012, NeuroImage.

[34]  Clifford R. Jack,et al.  Alzheimer's disease diagnosis in individual subjects using structural MR images: Validation studies , 2008, NeuroImage.

[35]  H. Benali,et al.  Fully automatic hippocampus segmentation and classification in Alzheimer's disease and mild cognitive impairment applied on data from ADNI , 2009, Hippocampus.

[36]  D. D. Ridder,et al.  Locally linear embedding for classification , 2002 .

[37]  Junsong Yin,et al.  Growing Locally Linear Embedding for Manifold Learning , 2007 .

[38]  Zheng Zhonglong,et al.  Non-negative matrix factorization with Log Gabor wavelets for image representation and classification , 2012 .

[39]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[40]  et al.,et al.  Spatial patterns of brain atrophy in MCI patients, identified via high-dimensional pattern classification, predict subsequent cognitive decline , 2008, NeuroImage.

[41]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[42]  Venkatesh Saligrama,et al.  Structural similarity and distance in learning , 2011, 2011 49th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[43]  Daoqiang Zhang,et al.  Predicting Future Clinical Changes of MCI Patients Using Longitudinal and Multimodal Biomarkers , 2012, PloS one.

[44]  Imam Samil Yetik,et al.  New methods for fMRI data processing based on locally linear embeddings , 2008, Electronic Imaging.

[45]  A. Dale,et al.  Whole Brain Segmentation Automated Labeling of Neuroanatomical Structures in the Human Brain , 2002, Neuron.

[46]  Mikhail Belkin,et al.  Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering , 2001, NIPS.

[47]  Nikos Makris,et al.  Automatically parcellating the human cerebral cortex. , 2004, Cerebral cortex.

[48]  Alireza Akhbardeh,et al.  Comparative analysis of nonlinear dimensionality reduction techniques for breast MRI segmentation. , 2012, Medical physics.

[49]  Clifford R. Jack,et al.  Predicting Clinical Scores from Magnetic Resonance Scans in Alzheimer's Disease , 2010, NeuroImage.

[50]  Olga Kayo,et al.  Locally linear embedding algorithm: extensions and applications , 2006 .

[51]  Michel Verleysen,et al.  DD-HDS: A Method for Visualization and Exploration of High-Dimensional Data , 2007, IEEE Transactions on Neural Networks.

[52]  Trevor Hastie,et al.  Regularization Paths for Generalized Linear Models via Coordinate Descent. , 2010, Journal of statistical software.

[53]  Salvador Olmos,et al.  Discrimination of AD and normal subjects from MRI: Anatomical versus statistical regions , 2011, Neuroscience Letters.

[54]  S. Folstein,et al.  "Mini-mental state". A practical method for grading the cognitive state of patients for the clinician. , 1975, Journal of psychiatric research.

[55]  Xiaoming Zhang,et al.  Feature Fusion Using Locally Linear Embedding for Classification , 2010, IEEE Transactions on Neural Networks.

[56]  Wen Gao,et al.  Enhancing Human Face Detection by Resampling Examples Through Manifolds , 2007, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[57]  G. Frisoni,et al.  Morphological hippocampal markers for automated detection of Alzheimer's disease and mild cognitive impairment converters in magnetic resonance images. , 2009, Journal of Alzheimer's disease : JAD.

[58]  Mark A. Tipton.  Wechsler adult intelligence scale (4th edition) and the validity of supplementary/core subtest substitution , 2014 .

[59]  Stefan J. Teipel,et al.  Long-term cost-effectiveness of donepezil for the treatment of Alzheimer’s disease , 2007, European Archives of Psychiatry and Clinical Neuroscience.

[60]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[61]  Lei Li,et al.  Improved Locally Linear Embedding Through New Distance Computing , 2006, ISNN.

[62]  M. Kendall.  Statistical Methods for Research Workers , 1937, Nature.

[63]  Roman Filipovych,et al.  Semi-supervised pattern classification of medical images: Application to mild cognitive impairment (MCI) , 2011, NeuroImage.

[64]  D. Louis Collins,et al.  Multivariate analysis of MRI data for Alzheimer's disease, mild cognitive impairment and healthy controls , 2011, NeuroImage.

[65]  P. Mecocci,et al.  An MRI‐based index to measure the severity of Alzheimer's disease‐like structural pattern in subjects with mild cognitive impairment , 2013, Journal of internal medicine.

[66]  R. Petersen,et al.  Development of Cognitive Instruments for Use in Clinical Trials of Antidementia Drugs: Additions to the Alzheimer's Disease Assessment Scale That Broaden Its Scope , 1997, Alzheimer disease and associated disorders.