CENTS: Cortical enhanced neonatal tissue segmentation

Feng Shi, Dinggang Shen, Pew Thian Yap, Yong Fan, Jie Zhi Cheng, Hongyu An, Lawrence L. Wald, Guido Gerig, John H. Gilmore, Weili Lin

Research output: Contribution to journalArticle

35 Citations (Scopus)

Abstract

The acquisition of high-quality magnetic resonance (MR) images of neonatal brains is largely hampered by their characteristically small head size and insufficient tissue contrast. As a result, subsequent image processing and analysis, especially brain tissue segmentation, are often affected. To overcome this problem, a dedicated phased array neonatal head coil is utilized to improve MR image quality by augmenting signal-to-noise ratio and spatial resolution without lengthening data acquisition time. In addition, a specialized hybrid atlas-based tissue segmentation algorithm is developed for the delineation of fine structures in the acquired neonatal brain MR images. The proposed tissue segmentation method first enhances the sheet-like cortical gray matter (GM) structures in the to-be-segmented neonatal image with a Hessian filter for generation of a cortical GM confidence map. A neonatal population atlas is then generated by averaging the presegmented images of a population, weighted by their cortical GM similarity with respect to the to-be-segmented image. Finally, the neonatal population atlas is combined with the GM confidence map, and the resulting enhanced tissue probability maps for each tissue form a hybrid atlas is used for atlas-based segmentation. Various experiments are conducted to compare the segmentations of the proposed method with manual segmentation (on both images acquired with a dedicated phased array coil and a conventional volume coil), as well as with the segmentations of two population-atlas-based methods. Results show the proposed method is capable of segmenting the neonatal brain with the best accuracy, and also preserving the most structural details in the cortical regions.

Original languageEnglish
Pages (from-to)382-396
Number of pages15
JournalHuman Brain Mapping
Volume32
Issue number3
DOIs
Publication statusPublished - 2011 Mar 1
Externally publishedYes

Fingerprint

Atlases
Magnetic Resonance Spectroscopy
Brain
Population
Head
Signal-To-Noise Ratio
Gray Matter

Keywords

  • Atlas construction
  • Neonatal segmentation
  • Subject-specific atlas
  • Tissue segmentation

ASJC Scopus subject areas

  • Clinical Neurology
  • Anatomy
  • Neurology
  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology

Cite this

Shi, F., Shen, D., Yap, P. T., Fan, Y., Cheng, J. Z., An, H., ... Lin, W. (2011). CENTS: Cortical enhanced neonatal tissue segmentation. Human Brain Mapping, 32(3), 382-396. https://doi.org/10.1002/hbm.21023

CENTS : Cortical enhanced neonatal tissue segmentation. / Shi, Feng; Shen, Dinggang; Yap, Pew Thian; Fan, Yong; Cheng, Jie Zhi; An, Hongyu; Wald, Lawrence L.; Gerig, Guido; Gilmore, John H.; Lin, Weili.

In: Human Brain Mapping, Vol. 32, No. 3, 01.03.2011, p. 382-396.

Research output: Contribution to journalArticle

Shi, F, Shen, D, Yap, PT, Fan, Y, Cheng, JZ, An, H, Wald, LL, Gerig, G, Gilmore, JH & Lin, W 2011, 'CENTS: Cortical enhanced neonatal tissue segmentation', Human Brain Mapping, vol. 32, no. 3, pp. 382-396. https://doi.org/10.1002/hbm.21023
Shi, Feng ; Shen, Dinggang ; Yap, Pew Thian ; Fan, Yong ; Cheng, Jie Zhi ; An, Hongyu ; Wald, Lawrence L. ; Gerig, Guido ; Gilmore, John H. ; Lin, Weili. / CENTS : Cortical enhanced neonatal tissue segmentation. In: Human Brain Mapping. 2011 ; Vol. 32, No. 3. pp. 382-396.
@article{b7359d4b547a4a048105d47092dca0cd,
title = "CENTS: Cortical enhanced neonatal tissue segmentation",
abstract = "The acquisition of high-quality magnetic resonance (MR) images of neonatal brains is largely hampered by their characteristically small head size and insufficient tissue contrast. As a result, subsequent image processing and analysis, especially brain tissue segmentation, are often affected. To overcome this problem, a dedicated phased array neonatal head coil is utilized to improve MR image quality by augmenting signal-to-noise ratio and spatial resolution without lengthening data acquisition time. In addition, a specialized hybrid atlas-based tissue segmentation algorithm is developed for the delineation of fine structures in the acquired neonatal brain MR images. The proposed tissue segmentation method first enhances the sheet-like cortical gray matter (GM) structures in the to-be-segmented neonatal image with a Hessian filter for generation of a cortical GM confidence map. A neonatal population atlas is then generated by averaging the presegmented images of a population, weighted by their cortical GM similarity with respect to the to-be-segmented image. Finally, the neonatal population atlas is combined with the GM confidence map, and the resulting enhanced tissue probability maps for each tissue form a hybrid atlas is used for atlas-based segmentation. Various experiments are conducted to compare the segmentations of the proposed method with manual segmentation (on both images acquired with a dedicated phased array coil and a conventional volume coil), as well as with the segmentations of two population-atlas-based methods. Results show the proposed method is capable of segmenting the neonatal brain with the best accuracy, and also preserving the most structural details in the cortical regions.",
keywords = "Atlas construction, Neonatal segmentation, Subject-specific atlas, Tissue segmentation",
author = "Feng Shi and Dinggang Shen and Yap, {Pew Thian} and Yong Fan and Cheng, {Jie Zhi} and Hongyu An and Wald, {Lawrence L.} and Guido Gerig and Gilmore, {John H.} and Weili Lin",
year = "2011",
month = "3",
day = "1",
doi = "10.1002/hbm.21023",
language = "English",
volume = "32",
pages = "382--396",
journal = "Human Brain Mapping",
issn = "1065-9471",
publisher = "Wiley-Liss Inc.",
number = "3",

}

TY - JOUR

T1 - CENTS

T2 - Cortical enhanced neonatal tissue segmentation

AU - Shi, Feng

AU - Shen, Dinggang

AU - Yap, Pew Thian

AU - Fan, Yong

AU - Cheng, Jie Zhi

AU - An, Hongyu

AU - Wald, Lawrence L.

AU - Gerig, Guido

AU - Gilmore, John H.

AU - Lin, Weili

PY - 2011/3/1

Y1 - 2011/3/1

N2 - The acquisition of high-quality magnetic resonance (MR) images of neonatal brains is largely hampered by their characteristically small head size and insufficient tissue contrast. As a result, subsequent image processing and analysis, especially brain tissue segmentation, are often affected. To overcome this problem, a dedicated phased array neonatal head coil is utilized to improve MR image quality by augmenting signal-to-noise ratio and spatial resolution without lengthening data acquisition time. In addition, a specialized hybrid atlas-based tissue segmentation algorithm is developed for the delineation of fine structures in the acquired neonatal brain MR images. The proposed tissue segmentation method first enhances the sheet-like cortical gray matter (GM) structures in the to-be-segmented neonatal image with a Hessian filter for generation of a cortical GM confidence map. A neonatal population atlas is then generated by averaging the presegmented images of a population, weighted by their cortical GM similarity with respect to the to-be-segmented image. Finally, the neonatal population atlas is combined with the GM confidence map, and the resulting enhanced tissue probability maps for each tissue form a hybrid atlas is used for atlas-based segmentation. Various experiments are conducted to compare the segmentations of the proposed method with manual segmentation (on both images acquired with a dedicated phased array coil and a conventional volume coil), as well as with the segmentations of two population-atlas-based methods. Results show the proposed method is capable of segmenting the neonatal brain with the best accuracy, and also preserving the most structural details in the cortical regions.

AB - The acquisition of high-quality magnetic resonance (MR) images of neonatal brains is largely hampered by their characteristically small head size and insufficient tissue contrast. As a result, subsequent image processing and analysis, especially brain tissue segmentation, are often affected. To overcome this problem, a dedicated phased array neonatal head coil is utilized to improve MR image quality by augmenting signal-to-noise ratio and spatial resolution without lengthening data acquisition time. In addition, a specialized hybrid atlas-based tissue segmentation algorithm is developed for the delineation of fine structures in the acquired neonatal brain MR images. The proposed tissue segmentation method first enhances the sheet-like cortical gray matter (GM) structures in the to-be-segmented neonatal image with a Hessian filter for generation of a cortical GM confidence map. A neonatal population atlas is then generated by averaging the presegmented images of a population, weighted by their cortical GM similarity with respect to the to-be-segmented image. Finally, the neonatal population atlas is combined with the GM confidence map, and the resulting enhanced tissue probability maps for each tissue form a hybrid atlas is used for atlas-based segmentation. Various experiments are conducted to compare the segmentations of the proposed method with manual segmentation (on both images acquired with a dedicated phased array coil and a conventional volume coil), as well as with the segmentations of two population-atlas-based methods. Results show the proposed method is capable of segmenting the neonatal brain with the best accuracy, and also preserving the most structural details in the cortical regions.

KW - Atlas construction

KW - Neonatal segmentation

KW - Subject-specific atlas

KW - Tissue segmentation

UR - http://www.scopus.com/inward/record.url?scp=79951490018&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951490018&partnerID=8YFLogxK

U2 - 10.1002/hbm.21023

DO - 10.1002/hbm.21023

M3 - Article

C2 - 20690143

AN - SCOPUS:79951490018

VL - 32

SP - 382

EP - 396

JO - Human Brain Mapping

JF - Human Brain Mapping

SN - 1065-9471

IS - 3

ER -