Multi-template tensor-based morphometry: Application to analysis of Alzheimer's disease

Juha Koikkalainen (Corresponding Author), Jyrki Lötjönen, Lennart Thurfjell, Daniel Rueckert, Gunhild Waldemar, Hilkka Soininen

Research output: Contribution to journalArticleScientificpeer-review

56 Citations (Scopus)

Abstract

In this paper methods for using multiple templates in tensor-based morphometry (TBM) are presented and compared to the conventional single-template approach. TBM analysis requires non-rigid registrations which are often subject to registration errors. When using multiple templates and, therefore, multiple registrations, it can be assumed that the registration errors are averaged and eventually compensated. Four different methods are proposed for multi-template TBM. The methods were evaluated using magnetic resonance (MR) images of healthy controls, patients with stable or progressive mild cognitive impairment (MCI), and patients with Alzheimer's disease (AD) from the ADNI database (N = 772). The performance of TBM features in classifying images was evaluated both quantitatively and qualitatively. Classification results show that the multi-template methods are statistically significantly better than the single-template method. The overall classification accuracy was 86.0% for the classification of control and AD subjects, and 72.1% for the classification of stable and progressive MCI subjects. The statistical group-level difference maps produced using multi-template TBM were smoother, formed larger continuous regions, and had larger t-values than the maps obtained with single-template TBM.
Original languageEnglish
Pages (from-to)1134-1144
JournalNeuroImage
Volume56
Issue number3
DOIs
Publication statusPublished - 2011
MoE publication typeA1 Journal article-refereed

Fingerprint

Alzheimer Disease
Magnetic Resonance Spectroscopy
Databases
Cognitive Dysfunction

Keywords

  • Tensor-based morphometry
  • Multi-template
  • Multi-atlas
  • Data classification
  • Alzheimer's disease

Cite this

Koikkalainen, J., Lötjönen, J., Thurfjell, L., Rueckert, D., Waldemar, G., & Soininen, H. (2011). Multi-template tensor-based morphometry: Application to analysis of Alzheimer's disease. NeuroImage, 56(3), 1134-1144. https://doi.org/10.1016/j.neuroimage.2011.03.029
Koikkalainen, Juha ; Lötjönen, Jyrki ; Thurfjell, Lennart ; Rueckert, Daniel ; Waldemar, Gunhild ; Soininen, Hilkka. / Multi-template tensor-based morphometry : Application to analysis of Alzheimer's disease. In: NeuroImage. 2011 ; Vol. 56, No. 3. pp. 1134-1144.
@article{332f96723dab42b9b85d9a402d5af581,
title = "Multi-template tensor-based morphometry: Application to analysis of Alzheimer's disease",
abstract = "In this paper methods for using multiple templates in tensor-based morphometry (TBM) are presented and compared to the conventional single-template approach. TBM analysis requires non-rigid registrations which are often subject to registration errors. When using multiple templates and, therefore, multiple registrations, it can be assumed that the registration errors are averaged and eventually compensated. Four different methods are proposed for multi-template TBM. The methods were evaluated using magnetic resonance (MR) images of healthy controls, patients with stable or progressive mild cognitive impairment (MCI), and patients with Alzheimer's disease (AD) from the ADNI database (N = 772). The performance of TBM features in classifying images was evaluated both quantitatively and qualitatively. Classification results show that the multi-template methods are statistically significantly better than the single-template method. The overall classification accuracy was 86.0{\%} for the classification of control and AD subjects, and 72.1{\%} for the classification of stable and progressive MCI subjects. The statistical group-level difference maps produced using multi-template TBM were smoother, formed larger continuous regions, and had larger t-values than the maps obtained with single-template TBM.",
keywords = "Tensor-based morphometry, Multi-template, Multi-atlas, Data classification, Alzheimer's disease",
author = "Juha Koikkalainen and Jyrki L{\"o}tj{\"o}nen and Lennart Thurfjell and Daniel Rueckert and Gunhild Waldemar and Hilkka Soininen",
year = "2011",
doi = "10.1016/j.neuroimage.2011.03.029",
language = "English",
volume = "56",
pages = "1134--1144",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press",
number = "3",

}

Koikkalainen, J, Lötjönen, J, Thurfjell, L, Rueckert, D, Waldemar, G & Soininen, H 2011, 'Multi-template tensor-based morphometry: Application to analysis of Alzheimer's disease', NeuroImage, vol. 56, no. 3, pp. 1134-1144. https://doi.org/10.1016/j.neuroimage.2011.03.029

Multi-template tensor-based morphometry : Application to analysis of Alzheimer's disease. / Koikkalainen, Juha (Corresponding Author); Lötjönen, Jyrki; Thurfjell, Lennart; Rueckert, Daniel; Waldemar, Gunhild; Soininen, Hilkka.

In: NeuroImage, Vol. 56, No. 3, 2011, p. 1134-1144.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Multi-template tensor-based morphometry

T2 - Application to analysis of Alzheimer's disease

AU - Koikkalainen, Juha

AU - Lötjönen, Jyrki

AU - Thurfjell, Lennart

AU - Rueckert, Daniel

AU - Waldemar, Gunhild

AU - Soininen, Hilkka

PY - 2011

Y1 - 2011

N2 - In this paper methods for using multiple templates in tensor-based morphometry (TBM) are presented and compared to the conventional single-template approach. TBM analysis requires non-rigid registrations which are often subject to registration errors. When using multiple templates and, therefore, multiple registrations, it can be assumed that the registration errors are averaged and eventually compensated. Four different methods are proposed for multi-template TBM. The methods were evaluated using magnetic resonance (MR) images of healthy controls, patients with stable or progressive mild cognitive impairment (MCI), and patients with Alzheimer's disease (AD) from the ADNI database (N = 772). The performance of TBM features in classifying images was evaluated both quantitatively and qualitatively. Classification results show that the multi-template methods are statistically significantly better than the single-template method. The overall classification accuracy was 86.0% for the classification of control and AD subjects, and 72.1% for the classification of stable and progressive MCI subjects. The statistical group-level difference maps produced using multi-template TBM were smoother, formed larger continuous regions, and had larger t-values than the maps obtained with single-template TBM.

AB - In this paper methods for using multiple templates in tensor-based morphometry (TBM) are presented and compared to the conventional single-template approach. TBM analysis requires non-rigid registrations which are often subject to registration errors. When using multiple templates and, therefore, multiple registrations, it can be assumed that the registration errors are averaged and eventually compensated. Four different methods are proposed for multi-template TBM. The methods were evaluated using magnetic resonance (MR) images of healthy controls, patients with stable or progressive mild cognitive impairment (MCI), and patients with Alzheimer's disease (AD) from the ADNI database (N = 772). The performance of TBM features in classifying images was evaluated both quantitatively and qualitatively. Classification results show that the multi-template methods are statistically significantly better than the single-template method. The overall classification accuracy was 86.0% for the classification of control and AD subjects, and 72.1% for the classification of stable and progressive MCI subjects. The statistical group-level difference maps produced using multi-template TBM were smoother, formed larger continuous regions, and had larger t-values than the maps obtained with single-template TBM.

KW - Tensor-based morphometry

KW - Multi-template

KW - Multi-atlas

KW - Data classification

KW - Alzheimer's disease

U2 - 10.1016/j.neuroimage.2011.03.029

DO - 10.1016/j.neuroimage.2011.03.029

M3 - Article

VL - 56

SP - 1134

EP - 1144

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 3

ER -

Koikkalainen J, Lötjönen J, Thurfjell L, Rueckert D, Waldemar G, Soininen H. Multi-template tensor-based morphometry: Application to analysis of Alzheimer's disease. NeuroImage. 2011;56(3):1134-1144. https://doi.org/10.1016/j.neuroimage.2011.03.029