Feature selection improves the accuracy of classifying Alzheimer disease using diffusion tensor images

Ayse Demirhan; Talia M. Nir; Artemis Zavaliangos-Petropulu; Clifford R. Jack; Michael W. Weiner; Matt A. Bernstein; Paul M. Thompson; Neda Jahanshad

doi:10.1109/ISBI.2015.7163832

Feature selection improves the accuracy of classifying Alzheimer disease using diffusion tensor images

Ayse Demirhan, Talia M. Nir, Artemis Zavaliangos-Petropulu, Clifford R. Jack, Michael W. Weiner, Matt A. Bernstein, Paul M. Thompson, Neda Jahanshad

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

21 Scopus citations

Abstract

Diffusion tensor imaging (DTI) has recently been added to several large-scale studies of Alzheimer's disease (AD), such as the Alzheimer's Disease Neuroimaging Initiative (ADNI), to investigate white matter (WM) abnormalities not detectable on standard anatomical MRI. Disease effects can be widespread, and the profile of WM abnormalities across tracts is still not fully understood. Here we analyzed image-wide measures from DTI fractional anisotropy (FA) maps to classify AD patients (n=43), mild cognitive impairment (n=114) and cognitively healthy elderly controls (n=70). We used voxelwise maps of FA along with averages in WM regions of interest (ROI) to drive a Support Vector Machine. We further used the ReliefF algorithm to select the most discriminative WM voxels for classification. This improved accuracy for all classification tasks by up to 15%. We found several clusters formed by the ReliefF algorithm, highlighting specific pathways affected in AD but not always captured when analyzing ROIs.

Original language	English (US)
Title of host publication	2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015
Publisher	IEEE Computer Society
Pages	126-130
Number of pages	5
ISBN (Electronic)	9781479923748
DOIs	https://doi.org/10.1109/ISBI.2015.7163832
State	Published - Jul 21 2015
Event	12th IEEE International Symposium on Biomedical Imaging, ISBI 2015 - Brooklyn, United States Duration: Apr 16 2015 → Apr 19 2015

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2015-July
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Other

Other	12th IEEE International Symposium on Biomedical Imaging, ISBI 2015
Country/Territory	United States
City	Brooklyn
Period	4/16/15 → 4/19/15

Keywords

Alzheimer's disease
diffusion tensor imaging
fractional anisotropy
support vector machines
voxel-based analysis

ASJC Scopus subject areas

Biomedical Engineering
Radiology Nuclear Medicine and imaging

Access to Document

10.1109/ISBI.2015.7163832

Cite this

Demirhan, A., Nir, T. M., Zavaliangos-Petropulu, A., Jack, C. R., Weiner, M. W., Bernstein, M. A., Thompson, P. M., & Jahanshad, N. (2015). Feature selection improves the accuracy of classifying Alzheimer disease using diffusion tensor images. In 2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015 (pp. 126-130). Article 7163832 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2015-July). IEEE Computer Society. https://doi.org/10.1109/ISBI.2015.7163832

Feature selection improves the accuracy of classifying Alzheimer disease using diffusion tensor images. / Demirhan, Ayse; Nir, Talia M.; Zavaliangos-Petropulu, Artemis et al.
2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015. IEEE Computer Society, 2015. p. 126-130 7163832 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2015-July).

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

Demirhan, A, Nir, TM, Zavaliangos-Petropulu, A, Jack, CR, Weiner, MW, Bernstein, MA, Thompson, PM & Jahanshad, N 2015, Feature selection improves the accuracy of classifying Alzheimer disease using diffusion tensor images. in 2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015., 7163832, Proceedings - International Symposium on Biomedical Imaging, vol. 2015-July, IEEE Computer Society, pp. 126-130, 12th IEEE International Symposium on Biomedical Imaging, ISBI 2015, Brooklyn, United States, 4/16/15. https://doi.org/10.1109/ISBI.2015.7163832

Demirhan A, Nir TM, Zavaliangos-Petropulu A, Jack CR, Weiner MW, Bernstein MA et al. Feature selection improves the accuracy of classifying Alzheimer disease using diffusion tensor images. In 2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015. IEEE Computer Society. 2015. p. 126-130. 7163832. (Proceedings - International Symposium on Biomedical Imaging). doi: 10.1109/ISBI.2015.7163832

@inproceedings{92c144822d754a5680d0b5a1509c41f3,

title = "Feature selection improves the accuracy of classifying Alzheimer disease using diffusion tensor images",

abstract = "Diffusion tensor imaging (DTI) has recently been added to several large-scale studies of Alzheimer's disease (AD), such as the Alzheimer's Disease Neuroimaging Initiative (ADNI), to investigate white matter (WM) abnormalities not detectable on standard anatomical MRI. Disease effects can be widespread, and the profile of WM abnormalities across tracts is still not fully understood. Here we analyzed image-wide measures from DTI fractional anisotropy (FA) maps to classify AD patients (n=43), mild cognitive impairment (n=114) and cognitively healthy elderly controls (n=70). We used voxelwise maps of FA along with averages in WM regions of interest (ROI) to drive a Support Vector Machine. We further used the ReliefF algorithm to select the most discriminative WM voxels for classification. This improved accuracy for all classification tasks by up to 15%. We found several clusters formed by the ReliefF algorithm, highlighting specific pathways affected in AD but not always captured when analyzing ROIs.",

keywords = "Alzheimer's disease, diffusion tensor imaging, fractional anisotropy, support vector machines, voxel-based analysis",

author = "Ayse Demirhan and Nir, {Talia M.} and Artemis Zavaliangos-Petropulu and Jack, {Clifford R.} and Weiner, {Michael W.} and Bernstein, {Matt A.} and Thompson, {Paul M.} and Neda Jahanshad",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 12th IEEE International Symposium on Biomedical Imaging, ISBI 2015 ; Conference date: 16-04-2015 Through 19-04-2015",

year = "2015",

month = jul,

day = "21",

doi = "10.1109/ISBI.2015.7163832",

language = "English (US)",

series = "Proceedings - International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

pages = "126--130",

booktitle = "2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015",

}

TY - GEN

T1 - Feature selection improves the accuracy of classifying Alzheimer disease using diffusion tensor images

AU - Demirhan, Ayse

AU - Nir, Talia M.

AU - Zavaliangos-Petropulu, Artemis

AU - Jack, Clifford R.

AU - Weiner, Michael W.

AU - Bernstein, Matt A.

AU - Thompson, Paul M.

AU - Jahanshad, Neda

PY - 2015/7/21

Y1 - 2015/7/21

N2 - Diffusion tensor imaging (DTI) has recently been added to several large-scale studies of Alzheimer's disease (AD), such as the Alzheimer's Disease Neuroimaging Initiative (ADNI), to investigate white matter (WM) abnormalities not detectable on standard anatomical MRI. Disease effects can be widespread, and the profile of WM abnormalities across tracts is still not fully understood. Here we analyzed image-wide measures from DTI fractional anisotropy (FA) maps to classify AD patients (n=43), mild cognitive impairment (n=114) and cognitively healthy elderly controls (n=70). We used voxelwise maps of FA along with averages in WM regions of interest (ROI) to drive a Support Vector Machine. We further used the ReliefF algorithm to select the most discriminative WM voxels for classification. This improved accuracy for all classification tasks by up to 15%. We found several clusters formed by the ReliefF algorithm, highlighting specific pathways affected in AD but not always captured when analyzing ROIs.

AB - Diffusion tensor imaging (DTI) has recently been added to several large-scale studies of Alzheimer's disease (AD), such as the Alzheimer's Disease Neuroimaging Initiative (ADNI), to investigate white matter (WM) abnormalities not detectable on standard anatomical MRI. Disease effects can be widespread, and the profile of WM abnormalities across tracts is still not fully understood. Here we analyzed image-wide measures from DTI fractional anisotropy (FA) maps to classify AD patients (n=43), mild cognitive impairment (n=114) and cognitively healthy elderly controls (n=70). We used voxelwise maps of FA along with averages in WM regions of interest (ROI) to drive a Support Vector Machine. We further used the ReliefF algorithm to select the most discriminative WM voxels for classification. This improved accuracy for all classification tasks by up to 15%. We found several clusters formed by the ReliefF algorithm, highlighting specific pathways affected in AD but not always captured when analyzing ROIs.

KW - Alzheimer's disease

KW - diffusion tensor imaging

KW - fractional anisotropy

KW - support vector machines

KW - voxel-based analysis

UR - http://www.scopus.com/inward/record.url?scp=84944311785&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944311785&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2015.7163832

DO - 10.1109/ISBI.2015.7163832

M3 - Conference contribution

AN - SCOPUS:84944311785

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 126

EP - 130

BT - 2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015

PB - IEEE Computer Society

T2 - 12th IEEE International Symposium on Biomedical Imaging, ISBI 2015

Y2 - 16 April 2015 through 19 April 2015

ER -

Feature selection improves the accuracy of classifying Alzheimer disease using diffusion tensor images

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this