Fast and robust extraction of hippocampus from MR images for diagnostics of Alzheimer's disease

Jyrki Lötjönen (Corresponding Author), Robin Wolz, Juha Koikkalainen, Valtteri Julkunen, Lennart Thurfjell, Roger Lundqvist, Gunhild Waldemar, Hilkka Soininen, Daniel Rueckert, The Alzheimer’s Disease Neuroimaging Initiative

Research output: Contribution to journalArticleScientificpeer-review

77 Citations (Scopus)

Abstract

Assessment of temporal lobe atrophy from magnetic resonance images is a part of clinical guidelines for the diagnosis of prodromal Alzheimer's disease. As hippocampus is known to be among the first areas affected by the disease, fast and robust definition of hippocampus volume would be of great importance in the clinical decision making. We propose a method for computing automatically the volume of hippocampus using a modified multi-atlas segmentation framework, including an improved initialization of the framework and the correction of partial volume effect. The method produced a high similarity index, 0.87, and correlation coefficient, 0.94, with semi-automatically generated segmentations. When comparing hippocampus volumes extracted from 1.5 T and 3 T images, the absolute value of the difference was low: 3.2% of the volume. The correct classification rate for Alzheimer's disease and cognitively normal cases was about 80% while the accuracy 65% was obtained for classifying stable and progressive mild cognitive impairment cases. The method was evaluated in three cohorts consisting altogether about 1000 cases, the main emphasis being in the analysis of the ADNI cohort. The computation time of the method is about 2 minutes on a standard laptop computer. The results show a clear potential for applying the method in clinical practice.

Original languageEnglish
Pages (from-to)185-196
Number of pages12
JournalNeuroImage
Volume56
Issue number1
DOIs
Publication statusPublished - 2011
MoE publication typeA1 Journal article-refereed

Fingerprint

Hippocampus
Alzheimer Disease
Atlases
Temporal Lobe
Atrophy
Cohort Studies
Magnetic Resonance Spectroscopy
Guidelines

Keywords

  • Alzheimer's disease
  • Hippocampus
  • Segmentation
  • Atlases

Cite this

Lötjönen, J., Wolz, R., Koikkalainen, J., Julkunen, V., Thurfjell, L., Lundqvist, R., ... The Alzheimer’s Disease Neuroimaging Initiative (2011). Fast and robust extraction of hippocampus from MR images for diagnostics of Alzheimer's disease. NeuroImage, 56(1), 185-196. https://doi.org/10.1016/j.neuroimage.2011.01.062
Lötjönen, Jyrki ; Wolz, Robin ; Koikkalainen, Juha ; Julkunen, Valtteri ; Thurfjell, Lennart ; Lundqvist, Roger ; Waldemar, Gunhild ; Soininen, Hilkka ; Rueckert, Daniel ; The Alzheimer’s Disease Neuroimaging Initiative. / Fast and robust extraction of hippocampus from MR images for diagnostics of Alzheimer's disease. In: NeuroImage. 2011 ; Vol. 56, No. 1. pp. 185-196.
@article{dcdab6546e324fa881481cac52ef5143,
title = "Fast and robust extraction of hippocampus from MR images for diagnostics of Alzheimer's disease",
abstract = "Assessment of temporal lobe atrophy from magnetic resonance images is a part of clinical guidelines for the diagnosis of prodromal Alzheimer's disease. As hippocampus is known to be among the first areas affected by the disease, fast and robust definition of hippocampus volume would be of great importance in the clinical decision making. We propose a method for computing automatically the volume of hippocampus using a modified multi-atlas segmentation framework, including an improved initialization of the framework and the correction of partial volume effect. The method produced a high similarity index, 0.87, and correlation coefficient, 0.94, with semi-automatically generated segmentations. When comparing hippocampus volumes extracted from 1.5 T and 3 T images, the absolute value of the difference was low: 3.2{\%} of the volume. The correct classification rate for Alzheimer's disease and cognitively normal cases was about 80{\%} while the accuracy 65{\%} was obtained for classifying stable and progressive mild cognitive impairment cases. The method was evaluated in three cohorts consisting altogether about 1000 cases, the main emphasis being in the analysis of the ADNI cohort. The computation time of the method is about 2 minutes on a standard laptop computer. The results show a clear potential for applying the method in clinical practice.",
keywords = "Alzheimer's disease, Hippocampus, Segmentation, Atlases",
author = "Jyrki L{\"o}tj{\"o}nen and Robin Wolz and Juha Koikkalainen and Valtteri Julkunen and Lennart Thurfjell and Roger Lundqvist and Gunhild Waldemar and Hilkka Soininen and Daniel Rueckert and {The Alzheimer’s Disease Neuroimaging Initiative}",
year = "2011",
doi = "10.1016/j.neuroimage.2011.01.062",
language = "English",
volume = "56",
pages = "185--196",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press",
number = "1",

}

Lötjönen, J, Wolz, R, Koikkalainen, J, Julkunen, V, Thurfjell, L, Lundqvist, R, Waldemar, G, Soininen, H, Rueckert, D & The Alzheimer’s Disease Neuroimaging Initiative 2011, 'Fast and robust extraction of hippocampus from MR images for diagnostics of Alzheimer's disease', NeuroImage, vol. 56, no. 1, pp. 185-196. https://doi.org/10.1016/j.neuroimage.2011.01.062

Fast and robust extraction of hippocampus from MR images for diagnostics of Alzheimer's disease. / Lötjönen, Jyrki (Corresponding Author); Wolz, Robin; Koikkalainen, Juha; Julkunen, Valtteri; Thurfjell, Lennart; Lundqvist, Roger; Waldemar, Gunhild; Soininen, Hilkka; Rueckert, Daniel; The Alzheimer’s Disease Neuroimaging Initiative.

In: NeuroImage, Vol. 56, No. 1, 2011, p. 185-196.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Fast and robust extraction of hippocampus from MR images for diagnostics of Alzheimer's disease

AU - Lötjönen, Jyrki

AU - Wolz, Robin

AU - Koikkalainen, Juha

AU - Julkunen, Valtteri

AU - Thurfjell, Lennart

AU - Lundqvist, Roger

AU - Waldemar, Gunhild

AU - Soininen, Hilkka

AU - Rueckert, Daniel

AU - The Alzheimer’s Disease Neuroimaging Initiative

PY - 2011

Y1 - 2011

N2 - Assessment of temporal lobe atrophy from magnetic resonance images is a part of clinical guidelines for the diagnosis of prodromal Alzheimer's disease. As hippocampus is known to be among the first areas affected by the disease, fast and robust definition of hippocampus volume would be of great importance in the clinical decision making. We propose a method for computing automatically the volume of hippocampus using a modified multi-atlas segmentation framework, including an improved initialization of the framework and the correction of partial volume effect. The method produced a high similarity index, 0.87, and correlation coefficient, 0.94, with semi-automatically generated segmentations. When comparing hippocampus volumes extracted from 1.5 T and 3 T images, the absolute value of the difference was low: 3.2% of the volume. The correct classification rate for Alzheimer's disease and cognitively normal cases was about 80% while the accuracy 65% was obtained for classifying stable and progressive mild cognitive impairment cases. The method was evaluated in three cohorts consisting altogether about 1000 cases, the main emphasis being in the analysis of the ADNI cohort. The computation time of the method is about 2 minutes on a standard laptop computer. The results show a clear potential for applying the method in clinical practice.

AB - Assessment of temporal lobe atrophy from magnetic resonance images is a part of clinical guidelines for the diagnosis of prodromal Alzheimer's disease. As hippocampus is known to be among the first areas affected by the disease, fast and robust definition of hippocampus volume would be of great importance in the clinical decision making. We propose a method for computing automatically the volume of hippocampus using a modified multi-atlas segmentation framework, including an improved initialization of the framework and the correction of partial volume effect. The method produced a high similarity index, 0.87, and correlation coefficient, 0.94, with semi-automatically generated segmentations. When comparing hippocampus volumes extracted from 1.5 T and 3 T images, the absolute value of the difference was low: 3.2% of the volume. The correct classification rate for Alzheimer's disease and cognitively normal cases was about 80% while the accuracy 65% was obtained for classifying stable and progressive mild cognitive impairment cases. The method was evaluated in three cohorts consisting altogether about 1000 cases, the main emphasis being in the analysis of the ADNI cohort. The computation time of the method is about 2 minutes on a standard laptop computer. The results show a clear potential for applying the method in clinical practice.

KW - Alzheimer's disease

KW - Hippocampus

KW - Segmentation

KW - Atlases

U2 - 10.1016/j.neuroimage.2011.01.062

DO - 10.1016/j.neuroimage.2011.01.062

M3 - Article

VL - 56

SP - 185

EP - 196

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 1

ER -

Lötjönen J, Wolz R, Koikkalainen J, Julkunen V, Thurfjell L, Lundqvist R et al. Fast and robust extraction of hippocampus from MR images for diagnostics of Alzheimer's disease. NeuroImage. 2011;56(1):185-196. https://doi.org/10.1016/j.neuroimage.2011.01.062