Construction of multi-region-multi-reference atlases for neonatal brain MRI segmentation

Feng Shi, Pew Thian Yap, Yong Fan, John H. Gilmore, Weili Lin, Dinggang Shen

Research output: Contribution to journalArticle

71 Citations (Scopus)

Abstract

Neonatal brain MRI segmentation is a challenging problem due to its poor image quality. Atlas-based segmentation approaches have been widely used for guiding brain tissue segmentation. Existing brain atlases are usually constructed by equally averaging pre-segmented images in a population. However, such approaches diminish local inter-subject structural variability and thus lead to lower segmentation guidance capability. To deal with this problem, we propose a multi-region-multi-reference framework for atlas-based neonatal brain segmentation. For each region of a brain parcellation, a population of spatially normalized pre-segmented images is clustered into a number of sub-populations. Each sub-population of a region represents an independent distribution from which a regional probability atlas can be generated. A selection of these regional atlases, across different sub-regions, will in the end be adaptively combined to form an overall atlas specific to the query image. Given a query image, the determination of the appropriate set of regional atlases is achieved by comparing the query image regionally with the reference, or exemplar, of each sub-population. Upon obtaining an overall atlas, an atlas-based joint registration-segmentation strategy is employed to segment the query image. Since the proposed method generates an atlas which is significant more similar to the query image than the traditional average-shape atlas, better tissue segmentation results can be expected. This is validated by applying the proposed method on a large set of neonatal brain images available in our institute. Experimental results on a randomly selected set of 10 neonatal brain images indicate that the proposed method achieves higher tissue overlap rates and lower standard deviations (SDs) in comparison with manual segmentations, i.e., 0.86 (SD 0.02) for GM, 0.83 (SD 0.03) for WM, and 0.80 (SD 0.05) for CSF. The proposed method also outperforms two other average-shape atlas-based segmentation methods.

Original languageEnglish
Pages (from-to)684-693
Number of pages10
JournalNeuroImage
Volume51
Issue number2
DOIs
Publication statusPublished - 2010 Jun 1
Externally publishedYes

Fingerprint

Atlases
Brain
Population
Joints

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

Construction of multi-region-multi-reference atlases for neonatal brain MRI segmentation. / Shi, Feng; Yap, Pew Thian; Fan, Yong; Gilmore, John H.; Lin, Weili; Shen, Dinggang.

In: NeuroImage, Vol. 51, No. 2, 01.06.2010, p. 684-693.

Research output: Contribution to journalArticle

Shi, Feng ; Yap, Pew Thian ; Fan, Yong ; Gilmore, John H. ; Lin, Weili ; Shen, Dinggang. / Construction of multi-region-multi-reference atlases for neonatal brain MRI segmentation. In: NeuroImage. 2010 ; Vol. 51, No. 2. pp. 684-693.
@article{ded6ae45bcdd4e7f94fb7b5b5d246f8a,
title = "Construction of multi-region-multi-reference atlases for neonatal brain MRI segmentation",
abstract = "Neonatal brain MRI segmentation is a challenging problem due to its poor image quality. Atlas-based segmentation approaches have been widely used for guiding brain tissue segmentation. Existing brain atlases are usually constructed by equally averaging pre-segmented images in a population. However, such approaches diminish local inter-subject structural variability and thus lead to lower segmentation guidance capability. To deal with this problem, we propose a multi-region-multi-reference framework for atlas-based neonatal brain segmentation. For each region of a brain parcellation, a population of spatially normalized pre-segmented images is clustered into a number of sub-populations. Each sub-population of a region represents an independent distribution from which a regional probability atlas can be generated. A selection of these regional atlases, across different sub-regions, will in the end be adaptively combined to form an overall atlas specific to the query image. Given a query image, the determination of the appropriate set of regional atlases is achieved by comparing the query image regionally with the reference, or exemplar, of each sub-population. Upon obtaining an overall atlas, an atlas-based joint registration-segmentation strategy is employed to segment the query image. Since the proposed method generates an atlas which is significant more similar to the query image than the traditional average-shape atlas, better tissue segmentation results can be expected. This is validated by applying the proposed method on a large set of neonatal brain images available in our institute. Experimental results on a randomly selected set of 10 neonatal brain images indicate that the proposed method achieves higher tissue overlap rates and lower standard deviations (SDs) in comparison with manual segmentations, i.e., 0.86 (SD 0.02) for GM, 0.83 (SD 0.03) for WM, and 0.80 (SD 0.05) for CSF. The proposed method also outperforms two other average-shape atlas-based segmentation methods.",
author = "Feng Shi and Yap, {Pew Thian} and Yong Fan and Gilmore, {John H.} and Weili Lin and Dinggang Shen",
year = "2010",
month = "6",
day = "1",
doi = "10.1016/j.neuroimage.2010.02.025",
language = "English",
volume = "51",
pages = "684--693",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "2",

}

TY - JOUR

T1 - Construction of multi-region-multi-reference atlases for neonatal brain MRI segmentation

AU - Shi, Feng

AU - Yap, Pew Thian

AU - Fan, Yong

AU - Gilmore, John H.

AU - Lin, Weili

AU - Shen, Dinggang

PY - 2010/6/1

Y1 - 2010/6/1

N2 - Neonatal brain MRI segmentation is a challenging problem due to its poor image quality. Atlas-based segmentation approaches have been widely used for guiding brain tissue segmentation. Existing brain atlases are usually constructed by equally averaging pre-segmented images in a population. However, such approaches diminish local inter-subject structural variability and thus lead to lower segmentation guidance capability. To deal with this problem, we propose a multi-region-multi-reference framework for atlas-based neonatal brain segmentation. For each region of a brain parcellation, a population of spatially normalized pre-segmented images is clustered into a number of sub-populations. Each sub-population of a region represents an independent distribution from which a regional probability atlas can be generated. A selection of these regional atlases, across different sub-regions, will in the end be adaptively combined to form an overall atlas specific to the query image. Given a query image, the determination of the appropriate set of regional atlases is achieved by comparing the query image regionally with the reference, or exemplar, of each sub-population. Upon obtaining an overall atlas, an atlas-based joint registration-segmentation strategy is employed to segment the query image. Since the proposed method generates an atlas which is significant more similar to the query image than the traditional average-shape atlas, better tissue segmentation results can be expected. This is validated by applying the proposed method on a large set of neonatal brain images available in our institute. Experimental results on a randomly selected set of 10 neonatal brain images indicate that the proposed method achieves higher tissue overlap rates and lower standard deviations (SDs) in comparison with manual segmentations, i.e., 0.86 (SD 0.02) for GM, 0.83 (SD 0.03) for WM, and 0.80 (SD 0.05) for CSF. The proposed method also outperforms two other average-shape atlas-based segmentation methods.

AB - Neonatal brain MRI segmentation is a challenging problem due to its poor image quality. Atlas-based segmentation approaches have been widely used for guiding brain tissue segmentation. Existing brain atlases are usually constructed by equally averaging pre-segmented images in a population. However, such approaches diminish local inter-subject structural variability and thus lead to lower segmentation guidance capability. To deal with this problem, we propose a multi-region-multi-reference framework for atlas-based neonatal brain segmentation. For each region of a brain parcellation, a population of spatially normalized pre-segmented images is clustered into a number of sub-populations. Each sub-population of a region represents an independent distribution from which a regional probability atlas can be generated. A selection of these regional atlases, across different sub-regions, will in the end be adaptively combined to form an overall atlas specific to the query image. Given a query image, the determination of the appropriate set of regional atlases is achieved by comparing the query image regionally with the reference, or exemplar, of each sub-population. Upon obtaining an overall atlas, an atlas-based joint registration-segmentation strategy is employed to segment the query image. Since the proposed method generates an atlas which is significant more similar to the query image than the traditional average-shape atlas, better tissue segmentation results can be expected. This is validated by applying the proposed method on a large set of neonatal brain images available in our institute. Experimental results on a randomly selected set of 10 neonatal brain images indicate that the proposed method achieves higher tissue overlap rates and lower standard deviations (SDs) in comparison with manual segmentations, i.e., 0.86 (SD 0.02) for GM, 0.83 (SD 0.03) for WM, and 0.80 (SD 0.05) for CSF. The proposed method also outperforms two other average-shape atlas-based segmentation methods.

UR - http://www.scopus.com/inward/record.url?scp=77951945513&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951945513&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2010.02.025

DO - 10.1016/j.neuroimage.2010.02.025

M3 - Article

VL - 51

SP - 684

EP - 693

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 2

ER -