4D Multi-Modality Tissue Segmentation of Serial Infant Images

Li Wang, Feng Shi, Pew Thian Yap, John H. Gilmore, Weili Lin, Dinggang Shen

Research output: Contribution to journalArticle

53 Citations (Scopus)

Abstract

Accurate and consistent segmentation of infant brain MR images plays an important role in quantifying patterns of early brain development, especially in longitudinal studies. However, due to rapid maturation and myelination of brain tissues in the first year of life, the intensity contrast of gray and white matter undergoes dramatic changes. In fact, the contrast inverse around 6-8 months of age, when the white and gray matter tissues are isointense and hence exhibit the lowest contrast, posing significant challenges for segmentation algorithms. In this paper, we propose a longitudinally guided level set method to segment serial infant brain MR images acquired from 2 weeks up to 1.5 years of age, including the isointense images. At each single-time-point, the proposed method makes optimal use of T1, T2 and the diffusion-weighted images for complimentary tissue distribution information to address the difficulty caused by the low contrast. Moreover, longitudinally consistent term, which constrains the distance across the serial images within a biologically reasonable range, is employed to obtain temporally consistent segmentation results. Application of our method on 28 longitudinal infant subjects, each with 5 longitudinal scans, shows that the automated segmentations from the proposed method match the manual ground-truth with much higher Dice Ratios than other single-modality, single-time-point based methods and the longitudinal but voxel-wise based methods. The software of the proposed method is publicly available in NITRC (http://www.nitrc.org/projects/ibeat).

Original languageEnglish
Article numbere44596
JournalPLoS One
Volume7
Issue number9
DOIs
Publication statusPublished - 2012 Sep 25
Externally publishedYes

Fingerprint

Brain
Tissue
brain
methodology
myelination
tissue distribution
infants
longitudinal studies
application methods
Tissue Distribution
tissues
Longitudinal Studies
Software

ASJC Scopus subject areas

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

Cite this

4D Multi-Modality Tissue Segmentation of Serial Infant Images. / Wang, Li; Shi, Feng; Yap, Pew Thian; Gilmore, John H.; Lin, Weili; Shen, Dinggang.

In: PLoS One, Vol. 7, No. 9, e44596, 25.09.2012.

Research output: Contribution to journalArticle

Wang, Li ; Shi, Feng ; Yap, Pew Thian ; Gilmore, John H. ; Lin, Weili ; Shen, Dinggang. / 4D Multi-Modality Tissue Segmentation of Serial Infant Images. In: PLoS One. 2012 ; Vol. 7, No. 9.
@article{96b1381a50e84dd4972c35ab35daf6d7,
title = "4D Multi-Modality Tissue Segmentation of Serial Infant Images",
abstract = "Accurate and consistent segmentation of infant brain MR images plays an important role in quantifying patterns of early brain development, especially in longitudinal studies. However, due to rapid maturation and myelination of brain tissues in the first year of life, the intensity contrast of gray and white matter undergoes dramatic changes. In fact, the contrast inverse around 6-8 months of age, when the white and gray matter tissues are isointense and hence exhibit the lowest contrast, posing significant challenges for segmentation algorithms. In this paper, we propose a longitudinally guided level set method to segment serial infant brain MR images acquired from 2 weeks up to 1.5 years of age, including the isointense images. At each single-time-point, the proposed method makes optimal use of T1, T2 and the diffusion-weighted images for complimentary tissue distribution information to address the difficulty caused by the low contrast. Moreover, longitudinally consistent term, which constrains the distance across the serial images within a biologically reasonable range, is employed to obtain temporally consistent segmentation results. Application of our method on 28 longitudinal infant subjects, each with 5 longitudinal scans, shows that the automated segmentations from the proposed method match the manual ground-truth with much higher Dice Ratios than other single-modality, single-time-point based methods and the longitudinal but voxel-wise based methods. The software of the proposed method is publicly available in NITRC (http://www.nitrc.org/projects/ibeat).",
author = "Li Wang and Feng Shi and Yap, {Pew Thian} and Gilmore, {John H.} and Weili Lin and Dinggang Shen",
year = "2012",
month = "9",
day = "25",
doi = "10.1371/journal.pone.0044596",
language = "English",
volume = "7",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "9",

}

TY - JOUR

T1 - 4D Multi-Modality Tissue Segmentation of Serial Infant Images

AU - Wang, Li

AU - Shi, Feng

AU - Yap, Pew Thian

AU - Gilmore, John H.

AU - Lin, Weili

AU - Shen, Dinggang

PY - 2012/9/25

Y1 - 2012/9/25

N2 - Accurate and consistent segmentation of infant brain MR images plays an important role in quantifying patterns of early brain development, especially in longitudinal studies. However, due to rapid maturation and myelination of brain tissues in the first year of life, the intensity contrast of gray and white matter undergoes dramatic changes. In fact, the contrast inverse around 6-8 months of age, when the white and gray matter tissues are isointense and hence exhibit the lowest contrast, posing significant challenges for segmentation algorithms. In this paper, we propose a longitudinally guided level set method to segment serial infant brain MR images acquired from 2 weeks up to 1.5 years of age, including the isointense images. At each single-time-point, the proposed method makes optimal use of T1, T2 and the diffusion-weighted images for complimentary tissue distribution information to address the difficulty caused by the low contrast. Moreover, longitudinally consistent term, which constrains the distance across the serial images within a biologically reasonable range, is employed to obtain temporally consistent segmentation results. Application of our method on 28 longitudinal infant subjects, each with 5 longitudinal scans, shows that the automated segmentations from the proposed method match the manual ground-truth with much higher Dice Ratios than other single-modality, single-time-point based methods and the longitudinal but voxel-wise based methods. The software of the proposed method is publicly available in NITRC (http://www.nitrc.org/projects/ibeat).

AB - Accurate and consistent segmentation of infant brain MR images plays an important role in quantifying patterns of early brain development, especially in longitudinal studies. However, due to rapid maturation and myelination of brain tissues in the first year of life, the intensity contrast of gray and white matter undergoes dramatic changes. In fact, the contrast inverse around 6-8 months of age, when the white and gray matter tissues are isointense and hence exhibit the lowest contrast, posing significant challenges for segmentation algorithms. In this paper, we propose a longitudinally guided level set method to segment serial infant brain MR images acquired from 2 weeks up to 1.5 years of age, including the isointense images. At each single-time-point, the proposed method makes optimal use of T1, T2 and the diffusion-weighted images for complimentary tissue distribution information to address the difficulty caused by the low contrast. Moreover, longitudinally consistent term, which constrains the distance across the serial images within a biologically reasonable range, is employed to obtain temporally consistent segmentation results. Application of our method on 28 longitudinal infant subjects, each with 5 longitudinal scans, shows that the automated segmentations from the proposed method match the manual ground-truth with much higher Dice Ratios than other single-modality, single-time-point based methods and the longitudinal but voxel-wise based methods. The software of the proposed method is publicly available in NITRC (http://www.nitrc.org/projects/ibeat).

UR - http://www.scopus.com/inward/record.url?scp=84866719092&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866719092&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0044596

DO - 10.1371/journal.pone.0044596

M3 - Article

C2 - 23049751

AN - SCOPUS:84866719092

VL - 7

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 9

M1 - e44596

ER -