Voxel Weight Matrix-Based Feature Extraction for Biomedical Applications

Functional Magnetic Resonance Imaging (fMRI) is an emerging medical tool used to measure brain activities that were induced normally such as cognitive states (e.g., reading a sentence or viewing a picture) or abnormally (e.g., brain activity occurs after a stroke or brain injury). These measured data can be used to construct a model via machine learning techniques to predict the occurrence of a certain cognitive behavior or brain disease. The difficulty of this prediction problem can be summarized in two points: first, the size of the dataset is very small due to the small number of subjects (i.e., patients) who can contribute to these research-based experiments. Second, the size of the feature vector resulted from these medical tools is very large compared to the few number of samples that were collected. One possible way to overcome these obstacles is to develop a feature generation methodology that can produce a small-sized and descriptive feature vector that may improve the overall prediction performance. Motivated by these considerations, this paper proposes a novel feature generation methodology termed Voxel Weight Matrix (VWM) method. This feature generation technique can transform the original high-dimensional feature vector to a two-dimensional discriminative feature domain. The main contribution of this feature generation technique is its ability to represent the statistical measures of the original feature vector via two-dimensional feature vector. After generating the VWM-based feature set, various classification tools such as logistic regression (LR) models and Support Vector Machine (SVM) are used for cognitive state prediction based on publicly available fMRI dataset called state/plus dataset. The classification models with the proposed VWM features outperformed the best two reported prediction models associated with the star/plus dataset with an average accuracy of 99.8%. To further illustrate the effectiveness of the proposed feature generation methodology, another publicly available Electroencephalography (EEG) dataset are used for Epileptic Seizure Prediction.

[1]  N. Jamal,et al.  An fMRI study of English and Spanish word reading in bilingual adults , 2020, Brain and Language.

[2]  Nikola Kasabov,et al.  Integrating Time-Space and Orientation. A Case Study on fMRI + DTI Brain Data , 2018, Springer Series on Bio- and Neurosystems.

[3]  Jun Zhang,et al.  Pharmacologically informed machine learning approach for identifying pathological states of unconsciousness via resting-state fMRI , 2020, NeuroImage.

[4]  P. Bucher.  Weight matrix descriptions of four eukaryotic RNA polymerase II promoter elements derived from 502 unrelated promoter sequences. , 1990, Journal of molecular biology.

[5]  Jasmin Kevric,et al.  Epileptic seizure detection using hybrid machine learning methods , 2017, Neural Computing and Applications.

[6]  F. Pukelsheim.  The Three Sigma Rule , 1994 .

[7]  N. Logothetis,et al.  Neurophysiological investigation of the basis of the fMRI signal , 2001, Nature.

[8]  R. McCarley,et al.  A review of MRI findings in schizophrenia , 2001, Schizophrenia Research.

[9]  Stuart D. Washington,et al.  A Machine Learning Approach to the Differentiation of Functional Magnetic Resonance Imaging Data of Chronic Fatigue Syndrome (CFS) From a Sedentary Control , 2020, Frontiers in Computational Neuroscience.

[10]  Fahad Albalawi,et al.  Hybrid model for efficient prediction of poly(A) signals in human genomic DNA. , 2019, Methods.

[11]  Chadia Zayane-Aissa,et al.  Nonlinear neural network for hemodynamic model state and input estimation using fMRI data , 2014, Biomed. Signal Process. Control..

[12]  Wenjian Wang,et al.  Granular support vector machine: a review , 2017, Artificial Intelligence Review.

[13]  Alfred Mertins,et al.  Machine Learning Based Classification of Resting-State fMRI Features Exemplified by Metabolic State (Hunger/Satiety) , 2019, Front. Hum. Neurosci..

[14]  David Pollard,et al.  Quantization and the method of k -means , 1982, IEEE Trans. Inf. Theory.

[15]  S. Ogawa,et al.  Oxygenation‐sensitive contrast in magnetic resonance image of rodent brain at high magnetic fields , 1990, Magnetic resonance in medicine.

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

[17]  Jonathan D. Cohen,et al.  A Developmental Functional MRI Study of Prefrontal Activation during Performance of a Go-No-Go Task , 1997, Journal of Cognitive Neuroscience.

[18]  K Lehnertz,et al.  Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[19]  Saurabh Sinha,et al.  On counting position weight matrix matches in a sequence, with application to discriminative motif finding , 2006, ISMB.

[20]  S. Rombouts,et al.  Altered resting state networks in mild cognitive impairment and mild Alzheimer's disease: An fMRI study , 2005, Human brain mapping.

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

[22]  Hariharan Ramasangu,et al.  Classification of cognitive state using clustering based maximum margin feature selection framework , 2017, 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[23]  Paul J. Laurienti,et al.  An automated method for neuroanatomic and cytoarchitectonic atlas-based interrogation of fMRI data sets , 2003, NeuroImage.

[24]  Geoffrey J. Gordon,et al.  The support vector decomposition machine , 2006, ICML.

[25]  Toufik Bouden,et al.  A deconvolution scheme for the stochastic metabolic/hemodynamic model (sMHM) based on the square root cubature Kalman filter and maximum likelihood estimation , 2018, Biomed. Signal Process. Control..

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

[27]  Tom Mitchell,et al.  Detecting Cognitive States Using Machine Learning , 2002 .

[28]  Neelam Sinha,et al.  Cognitive state classification using transformed fMRI data , 2014, 2014 International Conference on Signal Processing and Communications (SPCOM).

[29]  Hariharan Ramasangu,et al.  Classification of cognitive state using statistics of split time series , 2016, 2016 IEEE Annual India Conference (INDICON).

[30]  Zixiang Xiong,et al.  Optimal number of features as a function of sample size for various classification rules , 2005, Bioinform..

[31]  Yingli Lu,et al.  Regional homogeneity approach to fMRI data analysis , 2004, NeuroImage.

[32]  Patricia Figueiredo,et al.  Decoding visual brain states from fMRI using an ensemble of classifiers , 2012, Pattern Recognit..

[33]  J. Thompson,et al.  CLUSTAL W: improving the sensitivity of progressive multiple sequence alignment through sequence weighting, position-specific gap penalties and weight matrix choice. , 1994, Nucleic acids research.