Early detection of Alzheimer's disease using histograms in a dissimilarity-based classification framework

Anne Luchtenberg; Rita Lopes Simoes; Anne-Marie van Cappellen van Walsum; Cornelis H. Slump

doi:10.1117/12.2042670

Early detection of Alzheimer's disease using histograms in a dissimilarity-based classification framework

Anne Luchtenberg, Rita Lopes Simoes, Anne-Marie van Cappellen van Walsum, Cornelis H. Slump

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Classication methods have been proposed to detect early-stage Alzheimer's disease using Magnetic Resonance images. In particular, dissimilarity-based classication has been applied using a deformation-based distance measure. However, such approach is not only computationally expensive but it also considers large-scale alterations in the brain only. In this work, we propose the use of image histogram distance measures, determined both globally and locally, to detect very mild to mild Alzheimer's disease. Using an ensemble of local patches over the entire brain, we obtain an accuracy of 84% (sensitivity 80% and specicity 88%).

Original language	Undefined
Title of host publication	Medical Imaging 2014: Computer-Aided Diagnosis
Editors	S. Aylward, L.M. Hadjiski
Place of Publication	Bellingham, WA, USA
Publisher	SPIE
Pages	903502
Number of pages	10
ISBN (Print)	978-0-8194-9835-9
DOIs	https://doi.org/10.1117/12.2042670
Publication status	Published - 15 Feb 2014
Event	Medical Imaging 2014 - San Diego, United States Duration: 15 Feb 2014 → 20 Feb 2014

Publication series

Name	Proceedings of SPIE
Publisher	SPIE
Volume	9035

Conference

Conference	Medical Imaging 2014
Country/Territory	United States
City	San Diego
Period	15/02/14 → 20/02/14

Keywords

EWI-24913
local patches
histogram
dissimilarity-based classication
METIS-305946
IR-92126
MRI
Alzheimer's disease
Early detection

Access to Document

10.1117/12.2042670

http://eprints.eemcs.utwente.nl/secure2/24913/01/Luchtenberg,_Anne_ea_-_SPIE_2014.pdf

Cite this

Luchtenberg, A., Lopes Simoes, R., van Cappellen van Walsum, A-M., & Slump, C. H. (2014). Early detection of Alzheimer's disease using histograms in a dissimilarity-based classification framework. In S. Aylward, & L. M. Hadjiski (Eds.), Medical Imaging 2014: Computer-Aided Diagnosis (pp. 903502). (Proceedings of SPIE; Vol. 9035). SPIE. https://doi.org/10.1117/12.2042670

@inproceedings{925387e174a84e1797aaa5a37e1b733d,

title = "Early detection of Alzheimer's disease using histograms in a dissimilarity-based classification framework",

abstract = "Classication methods have been proposed to detect early-stage Alzheimer's disease using Magnetic Resonance images. In particular, dissimilarity-based classication has been applied using a deformation-based distance measure. However, such approach is not only computationally expensive but it also considers large-scale alterations in the brain only. In this work, we propose the use of image histogram distance measures, determined both globally and locally, to detect very mild to mild Alzheimer's disease. Using an ensemble of local patches over the entire brain, we obtain an accuracy of 84% (sensitivity 80% and specicity 88%).",

keywords = "EWI-24913, local patches, histogram, dissimilarity-based classication, METIS-305946, IR-92126, MRI, Alzheimer's disease, Early detection",

author = "Anne Luchtenberg and {Lopes Simoes}, Rita and {van Cappellen van Walsum}, Anne-Marie and Slump, {Cornelis H.}",

note = "903502-1 ; null ; Conference date: 15-02-2014 Through 20-02-2014",

year = "2014",

month = feb,

day = "15",

doi = "10.1117/12.2042670",

language = "Undefined",

isbn = "978-0-8194-9835-9",

series = "Proceedings of SPIE",

publisher = "SPIE",

pages = "903502",

editor = "S. Aylward and L.M. Hadjiski",

booktitle = "Medical Imaging 2014: Computer-Aided Diagnosis",

}

Luchtenberg, A, Lopes Simoes, R, van Cappellen van Walsum, A-M & Slump, CH 2014, Early detection of Alzheimer's disease using histograms in a dissimilarity-based classification framework. in S Aylward & LM Hadjiski (eds), Medical Imaging 2014: Computer-Aided Diagnosis. Proceedings of SPIE, vol. 9035, SPIE, Bellingham, WA, USA, pp. 903502, Medical Imaging 2014, San Diego, California, United States, 15/02/14. https://doi.org/10.1117/12.2042670

Early detection of Alzheimer's disease using histograms in a dissimilarity-based classification framework. / Luchtenberg, Anne; Lopes Simoes, Rita; van Cappellen van Walsum, Anne-Marie et al.

Medical Imaging 2014: Computer-Aided Diagnosis. ed. / S. Aylward; L.M. Hadjiski. Bellingham, WA, USA : SPIE, 2014. p. 903502 (Proceedings of SPIE; Vol. 9035).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Early detection of Alzheimer's disease using histograms in a dissimilarity-based classification framework

AU - Luchtenberg, Anne

AU - Lopes Simoes, Rita

AU - van Cappellen van Walsum, Anne-Marie

AU - Slump, Cornelis H.

N1 - 903502-1

PY - 2014/2/15

Y1 - 2014/2/15

N2 - Classication methods have been proposed to detect early-stage Alzheimer's disease using Magnetic Resonance images. In particular, dissimilarity-based classication has been applied using a deformation-based distance measure. However, such approach is not only computationally expensive but it also considers large-scale alterations in the brain only. In this work, we propose the use of image histogram distance measures, determined both globally and locally, to detect very mild to mild Alzheimer's disease. Using an ensemble of local patches over the entire brain, we obtain an accuracy of 84% (sensitivity 80% and specicity 88%).

AB - Classication methods have been proposed to detect early-stage Alzheimer's disease using Magnetic Resonance images. In particular, dissimilarity-based classication has been applied using a deformation-based distance measure. However, such approach is not only computationally expensive but it also considers large-scale alterations in the brain only. In this work, we propose the use of image histogram distance measures, determined both globally and locally, to detect very mild to mild Alzheimer's disease. Using an ensemble of local patches over the entire brain, we obtain an accuracy of 84% (sensitivity 80% and specicity 88%).

KW - EWI-24913

KW - local patches

KW - histogram

KW - dissimilarity-based classication

KW - METIS-305946

KW - IR-92126

KW - MRI

KW - Alzheimer's disease

KW - Early detection

U2 - 10.1117/12.2042670

DO - 10.1117/12.2042670

M3 - Conference contribution

SN - 978-0-8194-9835-9

T3 - Proceedings of SPIE

SP - 903502

BT - Medical Imaging 2014: Computer-Aided Diagnosis

A2 - Aylward, S.

A2 - Hadjiski, L.M.

PB - SPIE

CY - Bellingham, WA, USA

Y2 - 15 February 2014 through 20 February 2014

ER -