Role of Voxel Selection and ROI in fMRI Data Analysis

Raheel Zafar; Aamir Saeed Malik; Nidal Kamel; Sarat C. Dass

doi:10.1109/MeMeA.2016.7533739

Role of Voxel Selection and ROI in fMRI Data Analysis

Raheel Zafar, Aamir Saeed Malik, Nidal Kamel, Sarat C. Dass

School of Mathematical & Computer Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Citations (Scopus)

Abstract

Functional magnetic resonance imaging (fMRI) is one of the most popular and reliable modality to measure brain activities. The quality of fMRI data is best among other modalities such as Electroencephalography (EEG) and Magnetoencephalography (MEG). In fMRI, normally number of features are more than the number of instances so it is necessary to select the features and do dimension reduction to remove noisy and redundant data. Many techniques and methods are used to select the significant features (voxels). In this paper, the significant voxels are selected within the anatomical region of interest (ROI) based on the absolute values. In this study, we have predicted the brain states using two machine learning algorithm, i.e, Radial basis function (RBF) network and Naïve Bayes. A visual experiment with two categories is done. In conclusion, it is shown that less number of voxels and specific brain regions can increase the accuracy of prediction.

Original language	English
Title of host publication	2016 IEEE International Symposium on Medical Measurements and Applications (MeMeA)
Publisher	IEEE
ISBN (Electronic)	9781467391726
DOIs	https://doi.org/10.1109/MeMeA.2016.7533739
Publication status	Published - 8 Aug 2016

Keywords

fMRI
ROI
Feature selection
Classification
Generalized linear model
voxel

Access to Document

10.1109/MeMeA.2016.7533739

Cite this

@inproceedings{9f8d8e92dfc1407aa4acee7a81f358fa,

title = "Role of Voxel Selection and ROI in fMRI Data Analysis",

abstract = "Functional magnetic resonance imaging (fMRI) is one of the most popular and reliable modality to measure brain activities. The quality of fMRI data is best among other modalities such as Electroencephalography (EEG) and Magnetoencephalography (MEG). In fMRI, normally number of features are more than the number of instances so it is necessary to select the features and do dimension reduction to remove noisy and redundant data. Many techniques and methods are used to select the significant features (voxels). In this paper, the significant voxels are selected within the anatomical region of interest (ROI) based on the absolute values. In this study, we have predicted the brain states using two machine learning algorithm, i.e, Radial basis function (RBF) network and Na{\"i}ve Bayes. A visual experiment with two categories is done. In conclusion, it is shown that less number of voxels and specific brain regions can increase the accuracy of prediction.",

keywords = "fMRI, ROI, Feature selection, Classification, Generalized linear model, voxel",

author = "Raheel Zafar and Malik, {Aamir Saeed} and Nidal Kamel and Dass, {Sarat C.}",

year = "2016",

month = aug,

day = "8",

doi = "10.1109/MeMeA.2016.7533739",

language = "English",

booktitle = "2016 IEEE International Symposium on Medical Measurements and Applications (MeMeA)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Role of Voxel Selection and ROI in fMRI Data Analysis

AU - Zafar, Raheel

AU - Malik, Aamir Saeed

AU - Kamel, Nidal

AU - Dass, Sarat C.

PY - 2016/8/8

Y1 - 2016/8/8

N2 - Functional magnetic resonance imaging (fMRI) is one of the most popular and reliable modality to measure brain activities. The quality of fMRI data is best among other modalities such as Electroencephalography (EEG) and Magnetoencephalography (MEG). In fMRI, normally number of features are more than the number of instances so it is necessary to select the features and do dimension reduction to remove noisy and redundant data. Many techniques and methods are used to select the significant features (voxels). In this paper, the significant voxels are selected within the anatomical region of interest (ROI) based on the absolute values. In this study, we have predicted the brain states using two machine learning algorithm, i.e, Radial basis function (RBF) network and Naïve Bayes. A visual experiment with two categories is done. In conclusion, it is shown that less number of voxels and specific brain regions can increase the accuracy of prediction.

AB - Functional magnetic resonance imaging (fMRI) is one of the most popular and reliable modality to measure brain activities. The quality of fMRI data is best among other modalities such as Electroencephalography (EEG) and Magnetoencephalography (MEG). In fMRI, normally number of features are more than the number of instances so it is necessary to select the features and do dimension reduction to remove noisy and redundant data. Many techniques and methods are used to select the significant features (voxels). In this paper, the significant voxels are selected within the anatomical region of interest (ROI) based on the absolute values. In this study, we have predicted the brain states using two machine learning algorithm, i.e, Radial basis function (RBF) network and Naïve Bayes. A visual experiment with two categories is done. In conclusion, it is shown that less number of voxels and specific brain regions can increase the accuracy of prediction.

KW - fMRI

KW - ROI

KW - Feature selection

KW - Classification

KW - Generalized linear model

KW - voxel

U2 - 10.1109/MeMeA.2016.7533739

DO - 10.1109/MeMeA.2016.7533739

M3 - Conference contribution

BT - 2016 IEEE International Symposium on Medical Measurements and Applications (MeMeA)

PB - IEEE

ER -

Role of Voxel Selection and ROI in fMRI Data Analysis

Abstract

Keywords

Access to Document

Fingerprint

Cite this