Application of multidimensional scaling to quantify shape in Alzheimer's disease and its correlation with Mini Mental State Examination: A feasibility study

Hyunjin Park, Jongbum Seo

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Today, high-resolution MRI scans are able to reveal even the fine details of brain structure. Several methods have been developed to quantify shape differences specific to scans of diseased brains. We have developed a novel method for quantifying shape information based on multidimensional scaling (MDS), a well-known statistical tool. Multidimensional scaling uses distance measures computed from pair-wise image registration of the training set. Image registration establishes spatial correspondence between scans in order to compare them in the same spatial framework. Our novel method has several advantages, including robustness to errors in registrations. Applying our method to 44 brain MRIs showed clear separation between normal and Alzheimer scans. Using our method as basis for classification between normal and Alzheimer scans yielded better performance results compared with using the volume of hippocampus as basis for classification. We also devised a simple measure derived from the MDS approach that was shown to correlate with the Mini Mental State Examination (MMSE), a well-known cognitive test for Alzheimer's disease.

Original languageEnglish
Pages (from-to)380-385
Number of pages6
JournalJournal of Neuroscience Methods
Volume194
Issue number2
DOIs
Publication statusPublished - 2011 Jan 15

Fingerprint

Feasibility Studies
Alzheimer Disease
Brain
Brain Diseases
Hippocampus
Magnetic Resonance Imaging

All Science Journal Classification (ASJC) codes

  • Neuroscience(all)

Cite this

@article{c2a591e582cc4b87b56af3b1db17a623,
title = "Application of multidimensional scaling to quantify shape in Alzheimer's disease and its correlation with Mini Mental State Examination: A feasibility study",
abstract = "Today, high-resolution MRI scans are able to reveal even the fine details of brain structure. Several methods have been developed to quantify shape differences specific to scans of diseased brains. We have developed a novel method for quantifying shape information based on multidimensional scaling (MDS), a well-known statistical tool. Multidimensional scaling uses distance measures computed from pair-wise image registration of the training set. Image registration establishes spatial correspondence between scans in order to compare them in the same spatial framework. Our novel method has several advantages, including robustness to errors in registrations. Applying our method to 44 brain MRIs showed clear separation between normal and Alzheimer scans. Using our method as basis for classification between normal and Alzheimer scans yielded better performance results compared with using the volume of hippocampus as basis for classification. We also devised a simple measure derived from the MDS approach that was shown to correlate with the Mini Mental State Examination (MMSE), a well-known cognitive test for Alzheimer's disease.",
author = "Hyunjin Park and Jongbum Seo",
year = "2011",
month = "1",
day = "15",
doi = "10.1016/j.jneumeth.2010.10.019",
language = "English",
volume = "194",
pages = "380--385",
journal = "Journal of Neuroscience Methods",
issn = "0165-0270",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Application of multidimensional scaling to quantify shape in Alzheimer's disease and its correlation with Mini Mental State Examination

T2 - A feasibility study

AU - Park, Hyunjin

AU - Seo, Jongbum

PY - 2011/1/15

Y1 - 2011/1/15

N2 - Today, high-resolution MRI scans are able to reveal even the fine details of brain structure. Several methods have been developed to quantify shape differences specific to scans of diseased brains. We have developed a novel method for quantifying shape information based on multidimensional scaling (MDS), a well-known statistical tool. Multidimensional scaling uses distance measures computed from pair-wise image registration of the training set. Image registration establishes spatial correspondence between scans in order to compare them in the same spatial framework. Our novel method has several advantages, including robustness to errors in registrations. Applying our method to 44 brain MRIs showed clear separation between normal and Alzheimer scans. Using our method as basis for classification between normal and Alzheimer scans yielded better performance results compared with using the volume of hippocampus as basis for classification. We also devised a simple measure derived from the MDS approach that was shown to correlate with the Mini Mental State Examination (MMSE), a well-known cognitive test for Alzheimer's disease.

AB - Today, high-resolution MRI scans are able to reveal even the fine details of brain structure. Several methods have been developed to quantify shape differences specific to scans of diseased brains. We have developed a novel method for quantifying shape information based on multidimensional scaling (MDS), a well-known statistical tool. Multidimensional scaling uses distance measures computed from pair-wise image registration of the training set. Image registration establishes spatial correspondence between scans in order to compare them in the same spatial framework. Our novel method has several advantages, including robustness to errors in registrations. Applying our method to 44 brain MRIs showed clear separation between normal and Alzheimer scans. Using our method as basis for classification between normal and Alzheimer scans yielded better performance results compared with using the volume of hippocampus as basis for classification. We also devised a simple measure derived from the MDS approach that was shown to correlate with the Mini Mental State Examination (MMSE), a well-known cognitive test for Alzheimer's disease.

UR - http://www.scopus.com/inward/record.url?scp=78650509592&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650509592&partnerID=8YFLogxK

U2 - 10.1016/j.jneumeth.2010.10.019

DO - 10.1016/j.jneumeth.2010.10.019

M3 - Article

C2 - 21074558

AN - SCOPUS:78650509592

VL - 194

SP - 380

EP - 385

JO - Journal of Neuroscience Methods

JF - Journal of Neuroscience Methods

SN - 0165-0270

IS - 2

ER -