Integration of structural and functional MRI features improves mild cognitive impairment (MCI) detection

Jung Hoe Kim, Yong Hwan Kim, Soo Hyun Ha, Hyuk Soo Shin, Jong-Hwan Lee

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

Abstract

Structural magnetic resonance imaging (sMRI) and functional MRI (fMRI) based features toward identification of mild cognitive impairment (MCI) status has gained popularity due to its non-invasiveness allowing repeated measurements. Despite of this great potential, however an effort to integrate the sMRI- and fMRI-based features to increase MCI detection accuracy has been limited. In this study, we were motivated to investigate whether the detection capability of the MCI status can be improved via the integration of feature sets from sMRI and fMRI data. The characteristic traits of regional volumes and level of neuronal activity of the brain associated with the MCI in comparison to healthy control were exploited using sMRI and fMRI data, respectively, in which these characteristic traits (i.e., biomarkers) were identified from group comparison via two-sample t-test. In the subsequent classification phase, the MCI status were automatically detected using a support vector machine (SVM) algorithm employing the identified sMRI- and fMRI-driven biomarkers as input features vectors. The results indicate that the fMRI-based biomarkers appear to increase the detection accuracy of the MCI status than the sMRI-based biomarkers. Moreover, the integrated feature sets using the sMRI- and fMRI-based biomarkers constantly showed superior performance than the feature sets based on the fMRI-driven biomarkers. This study successfully demonstrated an anecdotal evidence that the integration of the sMRI and fMRI modalities can provide a supplemental information toward diagnosis of the MCI status compared to either the sMRI or fMRI modality.

Original languageEnglish
Title of host publicationProceedings - International Workshop on Pattern Recognition in NeuroImaging, PRNI 2011
Pages5-8
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

Magnetic resonance
Magnetic Resonance Imaging
Biomarkers
Imaging techniques
Cognitive Dysfunction
Support vector machines
Brain

Keywords

  • Alzheimer's disease
  • Functional MRI
  • General linear model
  • Mild cognitive impairment
  • Pattern classification
  • Structural MRI
  • Volumetric analysis

ASJC Scopus subject areas

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

Cite this

Kim, J. H., Kim, Y. H., Ha, S. H., Shin, H. S., & Lee, J-H. (2011). Integration of structural and functional MRI features improves mild cognitive impairment (MCI) detection. In Proceedings - International Workshop on Pattern Recognition in NeuroImaging, PRNI 2011 (pp. 5-8). [5961298] https://doi.org/10.1109/PRNI.2011.24

Integration of structural and functional MRI features improves mild cognitive impairment (MCI) detection. / Kim, Jung Hoe; Kim, Yong Hwan; Ha, Soo Hyun; Shin, Hyuk Soo; Lee, Jong-Hwan.

Proceedings - International Workshop on Pattern Recognition in NeuroImaging, PRNI 2011. 2011. p. 5-8 5961298.

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

Kim, JH, Kim, YH, Ha, SH, Shin, HS & Lee, J-H 2011, Integration of structural and functional MRI features improves mild cognitive impairment (MCI) detection. in Proceedings - International Workshop on Pattern Recognition in NeuroImaging, PRNI 2011., 5961298, pp. 5-8, International Workshop on Pattern Recognition in NeuroImaging, PRNI 2011, Seoul, Korea, Republic of, 11/5/16. https://doi.org/10.1109/PRNI.2011.24
Kim JH, Kim YH, Ha SH, Shin HS, Lee J-H. Integration of structural and functional MRI features improves mild cognitive impairment (MCI) detection. In Proceedings - International Workshop on Pattern Recognition in NeuroImaging, PRNI 2011. 2011. p. 5-8. 5961298 https://doi.org/10.1109/PRNI.2011.24
Kim, Jung Hoe ; Kim, Yong Hwan ; Ha, Soo Hyun ; Shin, Hyuk Soo ; Lee, Jong-Hwan. / Integration of structural and functional MRI features improves mild cognitive impairment (MCI) detection. Proceedings - International Workshop on Pattern Recognition in NeuroImaging, PRNI 2011. 2011. pp. 5-8
@inproceedings{a4b59a48396640c2b662c02b23b2a6a5,
title = "Integration of structural and functional MRI features improves mild cognitive impairment (MCI) detection",
abstract = "Structural magnetic resonance imaging (sMRI) and functional MRI (fMRI) based features toward identification of mild cognitive impairment (MCI) status has gained popularity due to its non-invasiveness allowing repeated measurements. Despite of this great potential, however an effort to integrate the sMRI- and fMRI-based features to increase MCI detection accuracy has been limited. In this study, we were motivated to investigate whether the detection capability of the MCI status can be improved via the integration of feature sets from sMRI and fMRI data. The characteristic traits of regional volumes and level of neuronal activity of the brain associated with the MCI in comparison to healthy control were exploited using sMRI and fMRI data, respectively, in which these characteristic traits (i.e., biomarkers) were identified from group comparison via two-sample t-test. In the subsequent classification phase, the MCI status were automatically detected using a support vector machine (SVM) algorithm employing the identified sMRI- and fMRI-driven biomarkers as input features vectors. The results indicate that the fMRI-based biomarkers appear to increase the detection accuracy of the MCI status than the sMRI-based biomarkers. Moreover, the integrated feature sets using the sMRI- and fMRI-based biomarkers constantly showed superior performance than the feature sets based on the fMRI-driven biomarkers. This study successfully demonstrated an anecdotal evidence that the integration of the sMRI and fMRI modalities can provide a supplemental information toward diagnosis of the MCI status compared to either the sMRI or fMRI modality.",
keywords = "Alzheimer's disease, Functional MRI, General linear model, Mild cognitive impairment, Pattern classification, Structural MRI, Volumetric analysis",
author = "Kim, {Jung Hoe} and Kim, {Yong Hwan} and Ha, {Soo Hyun} and Shin, {Hyuk Soo} and Jong-Hwan Lee",
year = "2011",
month = "8",
day = "29",
doi = "10.1109/PRNI.2011.24",
language = "English",
isbn = "9780769543994",
pages = "5--8",
booktitle = "Proceedings - International Workshop on Pattern Recognition in NeuroImaging, PRNI 2011",

}

TY - GEN

T1 - Integration of structural and functional MRI features improves mild cognitive impairment (MCI) detection

AU - Kim, Jung Hoe

AU - Kim, Yong Hwan

AU - Ha, Soo Hyun

AU - Shin, Hyuk Soo

AU - Lee, Jong-Hwan

PY - 2011/8/29

Y1 - 2011/8/29

N2 - Structural magnetic resonance imaging (sMRI) and functional MRI (fMRI) based features toward identification of mild cognitive impairment (MCI) status has gained popularity due to its non-invasiveness allowing repeated measurements. Despite of this great potential, however an effort to integrate the sMRI- and fMRI-based features to increase MCI detection accuracy has been limited. In this study, we were motivated to investigate whether the detection capability of the MCI status can be improved via the integration of feature sets from sMRI and fMRI data. The characteristic traits of regional volumes and level of neuronal activity of the brain associated with the MCI in comparison to healthy control were exploited using sMRI and fMRI data, respectively, in which these characteristic traits (i.e., biomarkers) were identified from group comparison via two-sample t-test. In the subsequent classification phase, the MCI status were automatically detected using a support vector machine (SVM) algorithm employing the identified sMRI- and fMRI-driven biomarkers as input features vectors. The results indicate that the fMRI-based biomarkers appear to increase the detection accuracy of the MCI status than the sMRI-based biomarkers. Moreover, the integrated feature sets using the sMRI- and fMRI-based biomarkers constantly showed superior performance than the feature sets based on the fMRI-driven biomarkers. This study successfully demonstrated an anecdotal evidence that the integration of the sMRI and fMRI modalities can provide a supplemental information toward diagnosis of the MCI status compared to either the sMRI or fMRI modality.

AB - Structural magnetic resonance imaging (sMRI) and functional MRI (fMRI) based features toward identification of mild cognitive impairment (MCI) status has gained popularity due to its non-invasiveness allowing repeated measurements. Despite of this great potential, however an effort to integrate the sMRI- and fMRI-based features to increase MCI detection accuracy has been limited. In this study, we were motivated to investigate whether the detection capability of the MCI status can be improved via the integration of feature sets from sMRI and fMRI data. The characteristic traits of regional volumes and level of neuronal activity of the brain associated with the MCI in comparison to healthy control were exploited using sMRI and fMRI data, respectively, in which these characteristic traits (i.e., biomarkers) were identified from group comparison via two-sample t-test. In the subsequent classification phase, the MCI status were automatically detected using a support vector machine (SVM) algorithm employing the identified sMRI- and fMRI-driven biomarkers as input features vectors. The results indicate that the fMRI-based biomarkers appear to increase the detection accuracy of the MCI status than the sMRI-based biomarkers. Moreover, the integrated feature sets using the sMRI- and fMRI-based biomarkers constantly showed superior performance than the feature sets based on the fMRI-driven biomarkers. This study successfully demonstrated an anecdotal evidence that the integration of the sMRI and fMRI modalities can provide a supplemental information toward diagnosis of the MCI status compared to either the sMRI or fMRI modality.

KW - Alzheimer's disease

KW - Functional MRI

KW - General linear model

KW - Mild cognitive impairment

KW - Pattern classification

KW - Structural MRI

KW - Volumetric analysis

UR - http://www.scopus.com/inward/record.url?scp=80051993457&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051993457&partnerID=8YFLogxK

U2 - 10.1109/PRNI.2011.24

DO - 10.1109/PRNI.2011.24

M3 - Conference contribution

AN - SCOPUS:80051993457

SN - 9780769543994

SP - 5

EP - 8

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

ER -