Atlas pre-selection strategies to enhance the efficiency and accuracy of multi-atlas brain segmentation tools

Chenfei Ye, Ting Ma, Dan Wu, Can Ceritoglu, Michael I. Miller, Susumu Mori

Research output: Contribution to journalArticle

Abstract

Multi-atlas brain segmentation of human brain MR images allows quantification research in structural neuroimaging. To achieve high accuracy and computational efficiency of segmentation relies on a custom subset of atlases for each target subject. However, the criterion for atlas pre-selection remains an open question. In this study, two atlas pre-selection approaches based on location-based feature matching were proposed and compared to random and mutual information-based methods using a database of 47 atlases. A varying number of atlases ranked top with hierarchical structural granularity were compared using Dice overlap. The results indicated that the proposed 4L approach consistently led to the highest level of accuracy at a given number of employed atlases in both adult and geriatric populations. In addition, the proposed two methods (4L and LV) can reduce 20 times computational time compared with the stereotypical mutual information-based method. Our pre-selection strategy would provide better segmentation performance in terms of both accuracy and efficiency. The proposed atlas pre-selection will be further implemented into our online automatic brain image segmentation system (www.mricloud.org).

Original languageEnglish (US)
Article numbere0200294
JournalPLoS One
Volume13
Issue number7
DOIs
StatePublished - Jul 1 2018

Fingerprint

Atlases
Brain
brain
Geriatrics
Neuroimaging
Computational efficiency
Set theory
Image segmentation
methodology
Databases
Research

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Atlas pre-selection strategies to enhance the efficiency and accuracy of multi-atlas brain segmentation tools. / Ye, Chenfei; Ma, Ting; Wu, Dan; Ceritoglu, Can; Miller, Michael I.; Mori, Susumu.

In: PLoS One, Vol. 13, No. 7, e0200294, 01.07.2018.

Research output: Contribution to journalArticle

Ye, Chenfei ; Ma, Ting ; Wu, Dan ; Ceritoglu, Can ; Miller, Michael I. ; Mori, Susumu. / Atlas pre-selection strategies to enhance the efficiency and accuracy of multi-atlas brain segmentation tools. In: PLoS One. 2018 ; Vol. 13, No. 7.
@article{3aa68f7ad3b24cfaa283cb7d72248a33,
title = "Atlas pre-selection strategies to enhance the efficiency and accuracy of multi-atlas brain segmentation tools",
abstract = "Multi-atlas brain segmentation of human brain MR images allows quantification research in structural neuroimaging. To achieve high accuracy and computational efficiency of segmentation relies on a custom subset of atlases for each target subject. However, the criterion for atlas pre-selection remains an open question. In this study, two atlas pre-selection approaches based on location-based feature matching were proposed and compared to random and mutual information-based methods using a database of 47 atlases. A varying number of atlases ranked top with hierarchical structural granularity were compared using Dice overlap. The results indicated that the proposed 4L approach consistently led to the highest level of accuracy at a given number of employed atlases in both adult and geriatric populations. In addition, the proposed two methods (4L and LV) can reduce 20 times computational time compared with the stereotypical mutual information-based method. Our pre-selection strategy would provide better segmentation performance in terms of both accuracy and efficiency. The proposed atlas pre-selection will be further implemented into our online automatic brain image segmentation system (www.mricloud.org).",
author = "Chenfei Ye and Ting Ma and Dan Wu and Can Ceritoglu and Miller, {Michael I.} and Susumu Mori",
year = "2018",
month = "7",
day = "1",
doi = "10.1371/journal.pone.0200294",
language = "English (US)",
volume = "13",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "7",

}

TY - JOUR

T1 - Atlas pre-selection strategies to enhance the efficiency and accuracy of multi-atlas brain segmentation tools

AU - Ye, Chenfei

AU - Ma, Ting

AU - Wu, Dan

AU - Ceritoglu, Can

AU - Miller, Michael I.

AU - Mori, Susumu

PY - 2018/7/1

Y1 - 2018/7/1

N2 - Multi-atlas brain segmentation of human brain MR images allows quantification research in structural neuroimaging. To achieve high accuracy and computational efficiency of segmentation relies on a custom subset of atlases for each target subject. However, the criterion for atlas pre-selection remains an open question. In this study, two atlas pre-selection approaches based on location-based feature matching were proposed and compared to random and mutual information-based methods using a database of 47 atlases. A varying number of atlases ranked top with hierarchical structural granularity were compared using Dice overlap. The results indicated that the proposed 4L approach consistently led to the highest level of accuracy at a given number of employed atlases in both adult and geriatric populations. In addition, the proposed two methods (4L and LV) can reduce 20 times computational time compared with the stereotypical mutual information-based method. Our pre-selection strategy would provide better segmentation performance in terms of both accuracy and efficiency. The proposed atlas pre-selection will be further implemented into our online automatic brain image segmentation system (www.mricloud.org).

AB - Multi-atlas brain segmentation of human brain MR images allows quantification research in structural neuroimaging. To achieve high accuracy and computational efficiency of segmentation relies on a custom subset of atlases for each target subject. However, the criterion for atlas pre-selection remains an open question. In this study, two atlas pre-selection approaches based on location-based feature matching were proposed and compared to random and mutual information-based methods using a database of 47 atlases. A varying number of atlases ranked top with hierarchical structural granularity were compared using Dice overlap. The results indicated that the proposed 4L approach consistently led to the highest level of accuracy at a given number of employed atlases in both adult and geriatric populations. In addition, the proposed two methods (4L and LV) can reduce 20 times computational time compared with the stereotypical mutual information-based method. Our pre-selection strategy would provide better segmentation performance in terms of both accuracy and efficiency. The proposed atlas pre-selection will be further implemented into our online automatic brain image segmentation system (www.mricloud.org).

UR - http://www.scopus.com/inward/record.url?scp=85052194356&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052194356&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0200294

DO - 10.1371/journal.pone.0200294

M3 - Article

C2 - 30052643

AN - SCOPUS:85052194356

VL - 13

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 7

M1 - e0200294

ER -