Automated Multi-Atlas Segmentation of Hippocampal and Extrahippocampal Subregions in Alzheimer's Disease at 3T and 7T : What Atlas Composition Works Best?
(2018) In Journal of Alzheimer's disease : JAD 63(1). p.217-225- Abstract
BACKGROUND: Multi-atlas segmentation, a popular technique implemented in the Automated Segmentation of Hippocampal Subfields (ASHS) software, utilizes multiple expert-labelled images ("atlases") to delineate medial temporal lobe substructures. This multi-atlas method is increasingly being employed in early Alzheimer's disease (AD) research, it is therefore becoming important to know how the construction of the atlas set in terms of proportions of controls and patients with mild cognitive impairment (MCI) and/or AD affects segmentation accuracy.
OBJECTIVE: To evaluate whether the proportion of controls in the training sets affects the segmentation accuracy of both controls and patients with MCI and/or early AD at 3T and... (More)
BACKGROUND: Multi-atlas segmentation, a popular technique implemented in the Automated Segmentation of Hippocampal Subfields (ASHS) software, utilizes multiple expert-labelled images ("atlases") to delineate medial temporal lobe substructures. This multi-atlas method is increasingly being employed in early Alzheimer's disease (AD) research, it is therefore becoming important to know how the construction of the atlas set in terms of proportions of controls and patients with mild cognitive impairment (MCI) and/or AD affects segmentation accuracy.
OBJECTIVE: To evaluate whether the proportion of controls in the training sets affects the segmentation accuracy of both controls and patients with MCI and/or early AD at 3T and 7T.
METHODS: We performed cross-validation experiments varying the proportion of control subjects in the training set, ranging from a patient-only to a control-only set. Segmentation accuracy of the test set was evaluated by the Dice similarity coeffiecient (DSC). A two-stage statistical analysis was applied to determine whether atlas composition is linked to segmentation accuracy in control subjects and patients, for 3T and 7T.
RESULTS: The different atlas compositions did not significantly affect segmentation accuracy at 3T and for patients at 7T. For controls at 7T, including more control subjects in the training set significantly improves the segmentation accuracy, but only marginally, with the maximum of 0.0003 DSC improvement per percent increment of control subject in the training set.
CONCLUSION: ASHS is robust in this study, and the results indicate that future studies investigating hippocampal subfields in early AD populations can be flexible in the selection of their atlas compositions.
(Less)
- author
- Xie, Long
; Shinohara, Russell T
; Ittyerah, Ranjit
; Kuijf, Hugo J
; Pluta, John B
; Blom, Kim
; Kooistra, Minke
; Reijmer, Yael D
; Koek, Huiberdina L
; Zwanenburg, Jaco J M
; Wang, Hongzhi
; Luijten, Peter R
; Geerlings, Mirjam I
; Das, Sandhitsu R
; Biessels, Geert Jan
; Wolk, David A
; Yushkevich, Paul A
and Wisse, Laura E M
LU
(Less) - publishing date
- 2018
- type
- Contribution to journal
- publication status
- published
- keywords
- Aged, Aged, 80 and over, Alzheimer Disease/diagnostic imaging, Brain Mapping, Cognitive Dysfunction/diagnostic imaging, Female, Hippocampus/diagnostic imaging, Humans, Image Processing, Computer-Assisted/methods, Magnetic Resonance Imaging, Male, Middle Aged
- in
- Journal of Alzheimer's disease : JAD
- volume
- 63
- issue
- 1
- pages
- 217 - 225
- publisher
- IOS Press
- external identifiers
-
- scopus:85060934319
- pmid:29614654
- ISSN
- 1387-2877
- DOI
- 10.3233/JAD-170932
- language
- English
- LU publication?
- no
- id
- d36c5a94-3fcd-4813-a991-958566d5640c
- date added to LUP
- 2024-02-28 14:50:15
- date last changed
- 2024-02-29 14:16:32
@article{d36c5a94-3fcd-4813-a991-958566d5640c,
abstract = {{<p>BACKGROUND: Multi-atlas segmentation, a popular technique implemented in the Automated Segmentation of Hippocampal Subfields (ASHS) software, utilizes multiple expert-labelled images ("atlases") to delineate medial temporal lobe substructures. This multi-atlas method is increasingly being employed in early Alzheimer's disease (AD) research, it is therefore becoming important to know how the construction of the atlas set in terms of proportions of controls and patients with mild cognitive impairment (MCI) and/or AD affects segmentation accuracy.</p><p>OBJECTIVE: To evaluate whether the proportion of controls in the training sets affects the segmentation accuracy of both controls and patients with MCI and/or early AD at 3T and 7T.</p><p>METHODS: We performed cross-validation experiments varying the proportion of control subjects in the training set, ranging from a patient-only to a control-only set. Segmentation accuracy of the test set was evaluated by the Dice similarity coeffiecient (DSC). A two-stage statistical analysis was applied to determine whether atlas composition is linked to segmentation accuracy in control subjects and patients, for 3T and 7T.</p><p>RESULTS: The different atlas compositions did not significantly affect segmentation accuracy at 3T and for patients at 7T. For controls at 7T, including more control subjects in the training set significantly improves the segmentation accuracy, but only marginally, with the maximum of 0.0003 DSC improvement per percent increment of control subject in the training set.</p><p>CONCLUSION: ASHS is robust in this study, and the results indicate that future studies investigating hippocampal subfields in early AD populations can be flexible in the selection of their atlas compositions.</p>}},
author = {{Xie, Long and Shinohara, Russell T and Ittyerah, Ranjit and Kuijf, Hugo J and Pluta, John B and Blom, Kim and Kooistra, Minke and Reijmer, Yael D and Koek, Huiberdina L and Zwanenburg, Jaco J M and Wang, Hongzhi and Luijten, Peter R and Geerlings, Mirjam I and Das, Sandhitsu R and Biessels, Geert Jan and Wolk, David A and Yushkevich, Paul A and Wisse, Laura E M}},
issn = {{1387-2877}},
keywords = {{Aged; Aged, 80 and over; Alzheimer Disease/diagnostic imaging; Brain Mapping; Cognitive Dysfunction/diagnostic imaging; Female; Hippocampus/diagnostic imaging; Humans; Image Processing, Computer-Assisted/methods; Magnetic Resonance Imaging; Male; Middle Aged}},
language = {{eng}},
number = {{1}},
pages = {{217--225}},
publisher = {{IOS Press}},
series = {{Journal of Alzheimer's disease : JAD}},
title = {{Automated Multi-Atlas Segmentation of Hippocampal and Extrahippocampal Subregions in Alzheimer's Disease at 3T and 7T : What Atlas Composition Works Best?}},
url = {{http://dx.doi.org/10.3233/JAD-170932}},
doi = {{10.3233/JAD-170932}},
volume = {{63}},
year = {{2018}},
}