An integrated geometrical and stochastic approach for accurate infant brain extraction

A. Alansary; A. Soliman; M. Nitzken; F. Khalifa; A. Elnakib; M. Mostapha; M. F. Casanova; A. El-Baz

doi:10.1109/ICIP.2014.7025719

An integrated geometrical and stochastic approach for accurate infant brain extraction

A. Alansary, A. Soliman, M. Nitzken, F. Khalifa, A. Elnakib, M. Mostapha, M. F. Casanova, A. El-Baz

School of Engineering (Behrend)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Scopus citations

Abstract

This paper presents a novel approach for extracting the brain from 3D T1-weighted MR images. The proposed approach combines a stochastic two-level Markov-Gibbs random field (MGRF) image model with a geometric model that parcels the brain into a set of nested iso-surfaces using a fast marching level setmethod. The classification of each brain voxel found on the iso-surfaces is performed based on the first-order (a linear combination of discrete gaussian (LCDG) model) and second-order (an MGRF model with analytically estimated parameters) visual appearance features of the brain structures. Our approach is tested on 280 infant 3D MR brain scans and evaluated on 9 data sets using the Dice coefficient, the 95-percentile modified Hausdorff distance, and absolute brain volume difference. Experimental results showed that the fusion of the stochastic and geometric models of brain MRI data has led to more accurate brain extraction, when compared with other widely-used brain extraction tools, such as BET, BET2, and brain surface extractor (BSE).

Original language	English (US)
Title of host publication	2014 IEEE International Conference on Image Processing, ICIP 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3542-3546
Number of pages	5
ISBN (Electronic)	9781479957514
DOIs	https://doi.org/10.1109/ICIP.2014.7025719
State	Published - Jan 28 2014

Publication series

Name	2014 IEEE International Conference on Image Processing, ICIP 2014

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition

Access to Document

10.1109/ICIP.2014.7025719

Cite this

Alansary, A., Soliman, A., Nitzken, M., Khalifa, F., Elnakib, A., Mostapha, M., Casanova, M. F., & El-Baz, A. (2014). An integrated geometrical and stochastic approach for accurate infant brain extraction. In 2014 IEEE International Conference on Image Processing, ICIP 2014 (pp. 3542-3546). Article 7025719 (2014 IEEE International Conference on Image Processing, ICIP 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIP.2014.7025719

@inproceedings{2fe73559904e4dc09e2b46e5318525e9,

title = "An integrated geometrical and stochastic approach for accurate infant brain extraction",

abstract = "This paper presents a novel approach for extracting the brain from 3D T1-weighted MR images. The proposed approach combines a stochastic two-level Markov-Gibbs random field (MGRF) image model with a geometric model that parcels the brain into a set of nested iso-surfaces using a fast marching level setmethod. The classification of each brain voxel found on the iso-surfaces is performed based on the first-order (a linear combination of discrete gaussian (LCDG) model) and second-order (an MGRF model with analytically estimated parameters) visual appearance features of the brain structures. Our approach is tested on 280 infant 3D MR brain scans and evaluated on 9 data sets using the Dice coefficient, the 95-percentile modified Hausdorff distance, and absolute brain volume difference. Experimental results showed that the fusion of the stochastic and geometric models of brain MRI data has led to more accurate brain extraction, when compared with other widely-used brain extraction tools, such as BET, BET2, and brain surface extractor (BSE).",

author = "A. Alansary and A. Soliman and M. Nitzken and F. Khalifa and A. Elnakib and M. Mostapha and Casanova, {M. F.} and A. El-Baz",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.",

year = "2014",

month = jan,

day = "28",

doi = "10.1109/ICIP.2014.7025719",

language = "English (US)",

series = "2014 IEEE International Conference on Image Processing, ICIP 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "3542--3546",

booktitle = "2014 IEEE International Conference on Image Processing, ICIP 2014",

address = "United States",

}

Alansary, A, Soliman, A, Nitzken, M, Khalifa, F, Elnakib, A, Mostapha, M, Casanova, MF & El-Baz, A 2014, An integrated geometrical and stochastic approach for accurate infant brain extraction. in 2014 IEEE International Conference on Image Processing, ICIP 2014., 7025719, 2014 IEEE International Conference on Image Processing, ICIP 2014, Institute of Electrical and Electronics Engineers Inc., pp. 3542-3546. https://doi.org/10.1109/ICIP.2014.7025719

An integrated geometrical and stochastic approach for accurate infant brain extraction. / Alansary, A.; Soliman, A.; Nitzken, M. et al.
2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 3542-3546 7025719 (2014 IEEE International Conference on Image Processing, ICIP 2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - An integrated geometrical and stochastic approach for accurate infant brain extraction

AU - Alansary, A.

AU - Soliman, A.

AU - Nitzken, M.

AU - Khalifa, F.

AU - Elnakib, A.

AU - Mostapha, M.

AU - Casanova, M. F.

AU - El-Baz, A.

PY - 2014/1/28

Y1 - 2014/1/28

N2 - This paper presents a novel approach for extracting the brain from 3D T1-weighted MR images. The proposed approach combines a stochastic two-level Markov-Gibbs random field (MGRF) image model with a geometric model that parcels the brain into a set of nested iso-surfaces using a fast marching level setmethod. The classification of each brain voxel found on the iso-surfaces is performed based on the first-order (a linear combination of discrete gaussian (LCDG) model) and second-order (an MGRF model with analytically estimated parameters) visual appearance features of the brain structures. Our approach is tested on 280 infant 3D MR brain scans and evaluated on 9 data sets using the Dice coefficient, the 95-percentile modified Hausdorff distance, and absolute brain volume difference. Experimental results showed that the fusion of the stochastic and geometric models of brain MRI data has led to more accurate brain extraction, when compared with other widely-used brain extraction tools, such as BET, BET2, and brain surface extractor (BSE).

AB - This paper presents a novel approach for extracting the brain from 3D T1-weighted MR images. The proposed approach combines a stochastic two-level Markov-Gibbs random field (MGRF) image model with a geometric model that parcels the brain into a set of nested iso-surfaces using a fast marching level setmethod. The classification of each brain voxel found on the iso-surfaces is performed based on the first-order (a linear combination of discrete gaussian (LCDG) model) and second-order (an MGRF model with analytically estimated parameters) visual appearance features of the brain structures. Our approach is tested on 280 infant 3D MR brain scans and evaluated on 9 data sets using the Dice coefficient, the 95-percentile modified Hausdorff distance, and absolute brain volume difference. Experimental results showed that the fusion of the stochastic and geometric models of brain MRI data has led to more accurate brain extraction, when compared with other widely-used brain extraction tools, such as BET, BET2, and brain surface extractor (BSE).

UR - http://www.scopus.com/inward/record.url?scp=84949928575&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949928575&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2014.7025719

DO - 10.1109/ICIP.2014.7025719

M3 - Conference contribution

AN - SCOPUS:84949928575

T3 - 2014 IEEE International Conference on Image Processing, ICIP 2014

SP - 3542

EP - 3546

BT - 2014 IEEE International Conference on Image Processing, ICIP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Alansary A, Soliman A, Nitzken M, Khalifa F, Elnakib A, Mostapha M et al. An integrated geometrical and stochastic approach for accurate infant brain extraction. In 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 3542-3546. 7025719. (2014 IEEE International Conference on Image Processing, ICIP 2014). doi: 10.1109/ICIP.2014.7025719

An integrated geometrical and stochastic approach for accurate infant brain extraction

Abstract

Publication series

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Cite this