Feature selection of fMRI data based on normalized mutual information and fisher discriminant ratio.

Pattern classification has been increasingly used in functional magnetic resonance imaging (fMRI) data analysis. However, the classification performance is restricted by the high dimensional property and noises of the fMRI data. In this paper, a new feature selection method (named as "NMI-F") was proposed by sequentially combining the normalized mutual information (NMI) and fisher discriminant ratio. In NMI-F, the normalized mutual information was firstly used to evaluate the relationships between features, and fisher discriminant ratio was then applied to calculate the importance of each feature involved. Two fMRI datasets (task-related and resting state) were used to test the proposed method. It was found that classification base on the NMI-F method could differentiate the brain cognitive and disease states effectively, and the proposed NMI-F method was prior to the other related methods. The current results also have implications to the future studies.

[1]  Yonggwan Won,et al.  Cognitive States Detection in fMRI using incremental P , 2007 .

[2]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[3]  Tim Schultz,et al.  Disease progression model in subjects with mild cognitive impairment from the Alzheimer's disease neuroimaging initiative: CSF biomarkers predict population subtypes. , 2013, British journal of clinical pharmacology.

[4]  C. Jack,et al.  Ways toward an early diagnosis in Alzheimer’s disease: The Alzheimer’s Disease Neuroimaging Initiative (ADNI) , 2005, Alzheimer's & Dementia.

[5]  Kaustubh Supekar,et al.  Sparse logistic regression for whole-brain classification of fMRI data , 2010, NeuroImage.

[6]  Matthew H. Davis,et al.  Do vegetative patients retain aspects of language comprehension? Evidence from fMRI. , 2007, Brain : a journal of neurology.

[7]  Ghassan Hamarneh,et al.  Generalized Sparse Classifiers for Decoding Cognitive States in fMRI , 2010, MLMI.

[8]  Peter J. Ramadge,et al.  The Pairwise Elastic Net support vector machine for automatic fMRI feature selection , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[9]  W. Art Chaovalitwongse,et al.  Sparse optimization in feature selection: application in neuroimaging , 2014, J. Glob. Optim..

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

[11]  Roland N. Boubela,et al.  On the generalizability of resting-state fMRI machine learning classifiers , 2014, Front. Hum. Neurosci..

[12]  A. Ishai,et al.  Distributed and Overlapping Representations of Faces and Objects in Ventral Temporal Cortex , 2001, Science.

[13]  Benson Mwangi,et al.  A Review of Feature Reduction Techniques in Neuroimaging , 2013, Neuroinformatics.

[14]  W. Art Chaovalitwongse,et al.  Voxel Selection Framework in Multi-Voxel Pattern Analysis of fMRI Data for Prediction of Neural Response to Visual Stimuli , 2014, IEEE Transactions on Medical Imaging.

[15]  Tom M. Mitchell,et al.  Learning to Decode Cognitive States from Brain Images , 2004, Machine Learning.

[16]  Wenbin Li,et al.  Enriched white matter connectivity networks for accurate identification of MCI patients , 2011, NeuroImage.

[17]  Klaus-Robert Müller,et al.  Introduction to machine learning for brain imaging , 2011, NeuroImage.

[18]  Paul S. Babyn,et al.  The optimal linear transformation-based fMRI feature space analysis , 2009, Medical & Biological Engineering & Computing.

[19]  Jacek M. Zurada,et al.  Normalized Mutual Information Feature Selection , 2009, IEEE Transactions on Neural Networks.

[21]  Soo-Hyung Kim,et al.  A multi-voxel-activity-based feature selection method for human cognitive states classification by functional magnetic resonance imaging data , 2014, Cluster Computing.

[22]  Stefan Klöppel,et al.  BrainAGE in Mild Cognitive Impaired Patients: Predicting the Conversion to Alzheimer’s Disease , 2013, PloS one.

[23]  Tom M. Mitchell,et al.  Machine learning classifiers and fMRI: A tutorial overview , 2009, NeuroImage.