Automated classification of discrete human thoughts using functional magnetic resonance imaging (fMRI)

Comparison between voxel-based and atlas-based feature selection methods

Jong-Hwan Lee, Jung Hoe Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

It has been reported that human thoughts processes of sensory-motor functions as well as high level of cognitive processes may be highly reproducible between multiple trials as measured via functional MRI data. This trend of the reproducibility seems consistent between multiple subjects as well. We have also presented in our earlier study that six distinct thought processes were shown highly consistent spatial patterns of activations as evaluated from automated classification performance. In the present study, this automated classification performance was compared depending on the feature vector selection methods. A general linear model (GLM) was adopted to define a neuronal activity and voxel-based or atlas-based approaches were adopted as feature vector selection methods. The classification results showed superior performance from the voxel-based feature selection method than the atlas-based method. Nonetheless, when multiple atlases were used to defined feature vector elements, the resulting performance was comparable to that of the voxel-based method with greatly reduced computational time.

Original languageEnglish
Title of host publicationProceedings - International Workshop on Pattern Recognition in NeuroImaging, PRNI 2011
Pages13-16
Number of pages4
DOIs
Publication statusPublished - 2011 Aug 29
EventInternational Workshop on Pattern Recognition in NeuroImaging, PRNI 2011 - Seoul, Korea, Republic of
Duration: 2011 May 162011 May 18

Other

OtherInternational Workshop on Pattern Recognition in NeuroImaging, PRNI 2011
CountryKorea, Republic of
CitySeoul
Period11/5/1611/5/18

Fingerprint

Atlases
Feature extraction
Magnetic Resonance Imaging
Chemical activation
Linear Models

Keywords

  • Brain decoding
  • Functional MRI
  • Imagery task
  • Neuroimaging
  • Support vector machine
  • Thought process

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Automated classification of discrete human thoughts using functional magnetic resonance imaging (fMRI) : Comparison between voxel-based and atlas-based feature selection methods. / Lee, Jong-Hwan; Kim, Jung Hoe.

Proceedings - International Workshop on Pattern Recognition in NeuroImaging, PRNI 2011. 2011. p. 13-16 5961300.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lee, J-H & Kim, JH 2011, Automated classification of discrete human thoughts using functional magnetic resonance imaging (fMRI): Comparison between voxel-based and atlas-based feature selection methods. in Proceedings - International Workshop on Pattern Recognition in NeuroImaging, PRNI 2011., 5961300, pp. 13-16, International Workshop on Pattern Recognition in NeuroImaging, PRNI 2011, Seoul, Korea, Republic of, 11/5/16. https://doi.org/10.1109/PRNI.2011.25
@inproceedings{c96bd0ad83d246d58cae958ebd15c4ba,
title = "Automated classification of discrete human thoughts using functional magnetic resonance imaging (fMRI): Comparison between voxel-based and atlas-based feature selection methods",
abstract = "It has been reported that human thoughts processes of sensory-motor functions as well as high level of cognitive processes may be highly reproducible between multiple trials as measured via functional MRI data. This trend of the reproducibility seems consistent between multiple subjects as well. We have also presented in our earlier study that six distinct thought processes were shown highly consistent spatial patterns of activations as evaluated from automated classification performance. In the present study, this automated classification performance was compared depending on the feature vector selection methods. A general linear model (GLM) was adopted to define a neuronal activity and voxel-based or atlas-based approaches were adopted as feature vector selection methods. The classification results showed superior performance from the voxel-based feature selection method than the atlas-based method. Nonetheless, when multiple atlases were used to defined feature vector elements, the resulting performance was comparable to that of the voxel-based method with greatly reduced computational time.",
keywords = "Brain decoding, Functional MRI, Imagery task, Neuroimaging, Support vector machine, Thought process",
author = "Jong-Hwan Lee and Kim, {Jung Hoe}",
year = "2011",
month = "8",
day = "29",
doi = "10.1109/PRNI.2011.25",
language = "English",
isbn = "9780769543994",
pages = "13--16",
booktitle = "Proceedings - International Workshop on Pattern Recognition in NeuroImaging, PRNI 2011",

}

TY - GEN

T1 - Automated classification of discrete human thoughts using functional magnetic resonance imaging (fMRI)

T2 - Comparison between voxel-based and atlas-based feature selection methods

AU - Lee, Jong-Hwan

AU - Kim, Jung Hoe

PY - 2011/8/29

Y1 - 2011/8/29

N2 - It has been reported that human thoughts processes of sensory-motor functions as well as high level of cognitive processes may be highly reproducible between multiple trials as measured via functional MRI data. This trend of the reproducibility seems consistent between multiple subjects as well. We have also presented in our earlier study that six distinct thought processes were shown highly consistent spatial patterns of activations as evaluated from automated classification performance. In the present study, this automated classification performance was compared depending on the feature vector selection methods. A general linear model (GLM) was adopted to define a neuronal activity and voxel-based or atlas-based approaches were adopted as feature vector selection methods. The classification results showed superior performance from the voxel-based feature selection method than the atlas-based method. Nonetheless, when multiple atlases were used to defined feature vector elements, the resulting performance was comparable to that of the voxel-based method with greatly reduced computational time.

AB - It has been reported that human thoughts processes of sensory-motor functions as well as high level of cognitive processes may be highly reproducible between multiple trials as measured via functional MRI data. This trend of the reproducibility seems consistent between multiple subjects as well. We have also presented in our earlier study that six distinct thought processes were shown highly consistent spatial patterns of activations as evaluated from automated classification performance. In the present study, this automated classification performance was compared depending on the feature vector selection methods. A general linear model (GLM) was adopted to define a neuronal activity and voxel-based or atlas-based approaches were adopted as feature vector selection methods. The classification results showed superior performance from the voxel-based feature selection method than the atlas-based method. Nonetheless, when multiple atlases were used to defined feature vector elements, the resulting performance was comparable to that of the voxel-based method with greatly reduced computational time.

KW - Brain decoding

KW - Functional MRI

KW - Imagery task

KW - Neuroimaging

KW - Support vector machine

KW - Thought process

UR - http://www.scopus.com/inward/record.url?scp=80051973135&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051973135&partnerID=8YFLogxK

U2 - 10.1109/PRNI.2011.25

DO - 10.1109/PRNI.2011.25

M3 - Conference contribution

SN - 9780769543994

SP - 13

EP - 16

BT - Proceedings - International Workshop on Pattern Recognition in NeuroImaging, PRNI 2011

ER -