Skull stripping based on region growing for magnetic resonance brain images

Jong Geun Park, Chul Hee Lee

Research output: Contribution to journalArticle

81 Citations (Scopus)

Abstract

In this paper, we propose a new skull stripping method for T1-weighted magnetic resonance (MR) brain images. Skull stripping has played an important role in neuroimage research because it is a basic preliminary step in many clinical applications. The process of skull stripping can be challenging due to the complexity of the human brain, variable parameters of MR scanners, individual characteristics, etc. In this paper, we aim to develop a computationally efficient and robust method. In the proposed algorithm, after eliminating the background voxels with histogram analysis, two seed regions of the brain and non-brain regions were automatically identified using a mask produced by morphological operations. Then we expanded these seed regions with a 2D region growing algorithm based on general brain anatomy information. The proposed algorithm was validated using 56 volumes of human brain data and simulated phantom data with manually segmented masks. It was compared with two popular automated skull stripping methods: the brain surface extractor (BSE) and the brain extraction tool (BET). The experimental results showed that the proposed algorithm produced accurate and stable results against data sets acquired from various MR scanners and effectively addressed difficult problems such as low contrast and large anatomical connections between the brain and surrounding tissues. The proposed method was also robust against noise, RF, and intensity inhomogeneities.

Original languageEnglish
Pages (from-to)1394-1407
Number of pages14
JournalNeuroImage
Volume47
Issue number4
DOIs
Publication statusPublished - 2009 Oct 1

Fingerprint

Skull
Magnetic Resonance Spectroscopy
Brain
Masks
Seeds
Noise
Anatomy
Research

All Science Journal Classification (ASJC) codes

  • Cognitive Neuroscience
  • Neurology

Cite this

@article{dea9a67d210c4ac8b970f10a9bdc925e,
title = "Skull stripping based on region growing for magnetic resonance brain images",
abstract = "In this paper, we propose a new skull stripping method for T1-weighted magnetic resonance (MR) brain images. Skull stripping has played an important role in neuroimage research because it is a basic preliminary step in many clinical applications. The process of skull stripping can be challenging due to the complexity of the human brain, variable parameters of MR scanners, individual characteristics, etc. In this paper, we aim to develop a computationally efficient and robust method. In the proposed algorithm, after eliminating the background voxels with histogram analysis, two seed regions of the brain and non-brain regions were automatically identified using a mask produced by morphological operations. Then we expanded these seed regions with a 2D region growing algorithm based on general brain anatomy information. The proposed algorithm was validated using 56 volumes of human brain data and simulated phantom data with manually segmented masks. It was compared with two popular automated skull stripping methods: the brain surface extractor (BSE) and the brain extraction tool (BET). The experimental results showed that the proposed algorithm produced accurate and stable results against data sets acquired from various MR scanners and effectively addressed difficult problems such as low contrast and large anatomical connections between the brain and surrounding tissues. The proposed method was also robust against noise, RF, and intensity inhomogeneities.",
author = "Park, {Jong Geun} and Lee, {Chul Hee}",
year = "2009",
month = "10",
day = "1",
doi = "10.1016/j.neuroimage.2009.04.047",
language = "English",
volume = "47",
pages = "1394--1407",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "4",

}

Skull stripping based on region growing for magnetic resonance brain images. / Park, Jong Geun; Lee, Chul Hee.

In: NeuroImage, Vol. 47, No. 4, 01.10.2009, p. 1394-1407.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Skull stripping based on region growing for magnetic resonance brain images

AU - Park, Jong Geun

AU - Lee, Chul Hee

PY - 2009/10/1

Y1 - 2009/10/1

N2 - In this paper, we propose a new skull stripping method for T1-weighted magnetic resonance (MR) brain images. Skull stripping has played an important role in neuroimage research because it is a basic preliminary step in many clinical applications. The process of skull stripping can be challenging due to the complexity of the human brain, variable parameters of MR scanners, individual characteristics, etc. In this paper, we aim to develop a computationally efficient and robust method. In the proposed algorithm, after eliminating the background voxels with histogram analysis, two seed regions of the brain and non-brain regions were automatically identified using a mask produced by morphological operations. Then we expanded these seed regions with a 2D region growing algorithm based on general brain anatomy information. The proposed algorithm was validated using 56 volumes of human brain data and simulated phantom data with manually segmented masks. It was compared with two popular automated skull stripping methods: the brain surface extractor (BSE) and the brain extraction tool (BET). The experimental results showed that the proposed algorithm produced accurate and stable results against data sets acquired from various MR scanners and effectively addressed difficult problems such as low contrast and large anatomical connections between the brain and surrounding tissues. The proposed method was also robust against noise, RF, and intensity inhomogeneities.

AB - In this paper, we propose a new skull stripping method for T1-weighted magnetic resonance (MR) brain images. Skull stripping has played an important role in neuroimage research because it is a basic preliminary step in many clinical applications. The process of skull stripping can be challenging due to the complexity of the human brain, variable parameters of MR scanners, individual characteristics, etc. In this paper, we aim to develop a computationally efficient and robust method. In the proposed algorithm, after eliminating the background voxels with histogram analysis, two seed regions of the brain and non-brain regions were automatically identified using a mask produced by morphological operations. Then we expanded these seed regions with a 2D region growing algorithm based on general brain anatomy information. The proposed algorithm was validated using 56 volumes of human brain data and simulated phantom data with manually segmented masks. It was compared with two popular automated skull stripping methods: the brain surface extractor (BSE) and the brain extraction tool (BET). The experimental results showed that the proposed algorithm produced accurate and stable results against data sets acquired from various MR scanners and effectively addressed difficult problems such as low contrast and large anatomical connections between the brain and surrounding tissues. The proposed method was also robust against noise, RF, and intensity inhomogeneities.

UR - http://www.scopus.com/inward/record.url?scp=67651020814&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67651020814&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2009.04.047

DO - 10.1016/j.neuroimage.2009.04.047

M3 - Article

VL - 47

SP - 1394

EP - 1407

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 4

ER -