Automated segmentation of brain tissue and white matter in cryosection images from Chinese visible human dataset

Min Li, Xiao Lin Zheng, Hong Yan Luo, Richard Castillo, Shao Xiang Zhang, Li Wen Tan, Edward Castillo, Thomas Guerrero

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Cryosection images contain fairly rich and original details of the brain anatomy. Accurate and fast segmentation of cryosection images is of great significance for research of the human brain and development of the Visible Human Project. However, most automated approaches in the literature are designed for magnetic resonance imaging or computed tomography data, and they may not be suitable for cryosection images. Cryosection image segmentation is often realized manually or semi-automatically in practice. The present study proposes an automated algorithm for cryosection image segmentation of brain tissue and white matter and evaluates its accuracy using the Chinese Visible Human (CVH) dataset. This method combines a mathematical morphological approach to delineate brain tissue and k-means clustering to uniquely identify white matter. Firstly, the region of brain tissue is detected coarsely using connected component labeling combined with morphological reconstruction. Then, morphological operations are used for final boundary determination to complete the segmentation of brain tissue. Finally, k-means clustering is employed to extract white matter based on segmented brain tissue. The algorithm was applied to the CVH dataset to automatically extract the entire brain tissue and white matter in the cerebrum, cerebellum, and brain stem. Additionally, the proposed mathematical morphological approach is compared with the region growing method and the threshold morphological method for brain segmentation, and the k-means clustering method is compared with the fuzzy c-means clustering algorithm and the Gaussian mixture model coupled with the expectation-maximization algorithm for white matter extraction. To evaluate performance, a quantitative analysis was conducted using the dice similarity index, false-positive dice, and false-negative dice for comparison with manually obtained segmentation results produced by anatomy experts. Results indicate that the proposed algorithm is capable of accurate segmentation and substantial agreement with the gold standard.

Original languageEnglish (US)
Pages (from-to)178-187
Number of pages10
JournalJournal of Medical and Biological Engineering
Volume34
Issue number2
DOIs
StatePublished - 2014
Externally publishedYes

Fingerprint

Brain
Tissue
Cluster Analysis
Image segmentation
Visible Human Projects
Anatomy
White Matter
Datasets
Cerebrum
Human Development
Magnetic resonance
Cerebellum
Brain Stem
Clustering algorithms
Labeling
Tomography
Magnetic Resonance Imaging
Imaging techniques
Research
Chemical analysis

Keywords

  • Brain tissue
  • Chinese visible human (CVH)
  • Segmentation
  • Visible human project (VHP)
  • White matter

ASJC Scopus subject areas

  • Biomedical Engineering
  • Medicine(all)

Cite this

Automated segmentation of brain tissue and white matter in cryosection images from Chinese visible human dataset. / Li, Min; Zheng, Xiao Lin; Luo, Hong Yan; Castillo, Richard; Zhang, Shao Xiang; Tan, Li Wen; Castillo, Edward; Guerrero, Thomas.

In: Journal of Medical and Biological Engineering, Vol. 34, No. 2, 2014, p. 178-187.

Research output: Contribution to journalArticle

Li, M, Zheng, XL, Luo, HY, Castillo, R, Zhang, SX, Tan, LW, Castillo, E & Guerrero, T 2014, 'Automated segmentation of brain tissue and white matter in cryosection images from Chinese visible human dataset', Journal of Medical and Biological Engineering, vol. 34, no. 2, pp. 178-187. https://doi.org/10.5405/jmbe.1336
Li, Min ; Zheng, Xiao Lin ; Luo, Hong Yan ; Castillo, Richard ; Zhang, Shao Xiang ; Tan, Li Wen ; Castillo, Edward ; Guerrero, Thomas. / Automated segmentation of brain tissue and white matter in cryosection images from Chinese visible human dataset. In: Journal of Medical and Biological Engineering. 2014 ; Vol. 34, No. 2. pp. 178-187.
@article{4521bbb2f4bd41529a31ff81f8d0769f,
title = "Automated segmentation of brain tissue and white matter in cryosection images from Chinese visible human dataset",
abstract = "Cryosection images contain fairly rich and original details of the brain anatomy. Accurate and fast segmentation of cryosection images is of great significance for research of the human brain and development of the Visible Human Project. However, most automated approaches in the literature are designed for magnetic resonance imaging or computed tomography data, and they may not be suitable for cryosection images. Cryosection image segmentation is often realized manually or semi-automatically in practice. The present study proposes an automated algorithm for cryosection image segmentation of brain tissue and white matter and evaluates its accuracy using the Chinese Visible Human (CVH) dataset. This method combines a mathematical morphological approach to delineate brain tissue and k-means clustering to uniquely identify white matter. Firstly, the region of brain tissue is detected coarsely using connected component labeling combined with morphological reconstruction. Then, morphological operations are used for final boundary determination to complete the segmentation of brain tissue. Finally, k-means clustering is employed to extract white matter based on segmented brain tissue. The algorithm was applied to the CVH dataset to automatically extract the entire brain tissue and white matter in the cerebrum, cerebellum, and brain stem. Additionally, the proposed mathematical morphological approach is compared with the region growing method and the threshold morphological method for brain segmentation, and the k-means clustering method is compared with the fuzzy c-means clustering algorithm and the Gaussian mixture model coupled with the expectation-maximization algorithm for white matter extraction. To evaluate performance, a quantitative analysis was conducted using the dice similarity index, false-positive dice, and false-negative dice for comparison with manually obtained segmentation results produced by anatomy experts. Results indicate that the proposed algorithm is capable of accurate segmentation and substantial agreement with the gold standard.",
keywords = "Brain tissue, Chinese visible human (CVH), Segmentation, Visible human project (VHP), White matter",
author = "Min Li and Zheng, {Xiao Lin} and Luo, {Hong Yan} and Richard Castillo and Zhang, {Shao Xiang} and Tan, {Li Wen} and Edward Castillo and Thomas Guerrero",
year = "2014",
doi = "10.5405/jmbe.1336",
language = "English (US)",
volume = "34",
pages = "178--187",
journal = "Journal of Medical and Biological Engineering",
issn = "1609-0985",
publisher = "Biomedical Engineering Society",
number = "2",

}

TY - JOUR

T1 - Automated segmentation of brain tissue and white matter in cryosection images from Chinese visible human dataset

AU - Li, Min

AU - Zheng, Xiao Lin

AU - Luo, Hong Yan

AU - Castillo, Richard

AU - Zhang, Shao Xiang

AU - Tan, Li Wen

AU - Castillo, Edward

AU - Guerrero, Thomas

PY - 2014

Y1 - 2014

N2 - Cryosection images contain fairly rich and original details of the brain anatomy. Accurate and fast segmentation of cryosection images is of great significance for research of the human brain and development of the Visible Human Project. However, most automated approaches in the literature are designed for magnetic resonance imaging or computed tomography data, and they may not be suitable for cryosection images. Cryosection image segmentation is often realized manually or semi-automatically in practice. The present study proposes an automated algorithm for cryosection image segmentation of brain tissue and white matter and evaluates its accuracy using the Chinese Visible Human (CVH) dataset. This method combines a mathematical morphological approach to delineate brain tissue and k-means clustering to uniquely identify white matter. Firstly, the region of brain tissue is detected coarsely using connected component labeling combined with morphological reconstruction. Then, morphological operations are used for final boundary determination to complete the segmentation of brain tissue. Finally, k-means clustering is employed to extract white matter based on segmented brain tissue. The algorithm was applied to the CVH dataset to automatically extract the entire brain tissue and white matter in the cerebrum, cerebellum, and brain stem. Additionally, the proposed mathematical morphological approach is compared with the region growing method and the threshold morphological method for brain segmentation, and the k-means clustering method is compared with the fuzzy c-means clustering algorithm and the Gaussian mixture model coupled with the expectation-maximization algorithm for white matter extraction. To evaluate performance, a quantitative analysis was conducted using the dice similarity index, false-positive dice, and false-negative dice for comparison with manually obtained segmentation results produced by anatomy experts. Results indicate that the proposed algorithm is capable of accurate segmentation and substantial agreement with the gold standard.

AB - Cryosection images contain fairly rich and original details of the brain anatomy. Accurate and fast segmentation of cryosection images is of great significance for research of the human brain and development of the Visible Human Project. However, most automated approaches in the literature are designed for magnetic resonance imaging or computed tomography data, and they may not be suitable for cryosection images. Cryosection image segmentation is often realized manually or semi-automatically in practice. The present study proposes an automated algorithm for cryosection image segmentation of brain tissue and white matter and evaluates its accuracy using the Chinese Visible Human (CVH) dataset. This method combines a mathematical morphological approach to delineate brain tissue and k-means clustering to uniquely identify white matter. Firstly, the region of brain tissue is detected coarsely using connected component labeling combined with morphological reconstruction. Then, morphological operations are used for final boundary determination to complete the segmentation of brain tissue. Finally, k-means clustering is employed to extract white matter based on segmented brain tissue. The algorithm was applied to the CVH dataset to automatically extract the entire brain tissue and white matter in the cerebrum, cerebellum, and brain stem. Additionally, the proposed mathematical morphological approach is compared with the region growing method and the threshold morphological method for brain segmentation, and the k-means clustering method is compared with the fuzzy c-means clustering algorithm and the Gaussian mixture model coupled with the expectation-maximization algorithm for white matter extraction. To evaluate performance, a quantitative analysis was conducted using the dice similarity index, false-positive dice, and false-negative dice for comparison with manually obtained segmentation results produced by anatomy experts. Results indicate that the proposed algorithm is capable of accurate segmentation and substantial agreement with the gold standard.

KW - Brain tissue

KW - Chinese visible human (CVH)

KW - Segmentation

KW - Visible human project (VHP)

KW - White matter

UR - http://www.scopus.com/inward/record.url?scp=84902143037&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902143037&partnerID=8YFLogxK

U2 - 10.5405/jmbe.1336

DO - 10.5405/jmbe.1336

M3 - Article

VL - 34

SP - 178

EP - 187

JO - Journal of Medical and Biological Engineering

JF - Journal of Medical and Biological Engineering

SN - 1609-0985

IS - 2

ER -