Learning-based meta-algorithm for MRI brain extraction.

Feng Shi, L. Wang, John H. Gilmore, Weili Lin, Dinggang Shen

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Multiple-segmentation-and-fusion method has been widely used for brain extraction, tissue segmentation, and region of interest (ROI) localization. However, such studies are hindered in practice by their computational complexity, mainly coming from the steps of template selection and template-to-subject nonlinear registration. In this study, we address these two issues and propose a novel learning-based meta-algorithm for MRI brain extraction. Specifically, we first use exemplars to represent the entire template library, and assign the most similar exemplar to the test subject. Second, a meta-algorithm combining two existing brain extraction algorithms (BET and BSE) is proposed to conduct multiple extractions directly on test subject. Effective parameter settings for the meta-algorithm are learned from the training data and propagated to subject through exemplars. We further develop a level-set based fusion method to combine multiple candidate extractions together with a closed smooth surface, for obtaining the final result. Experimental results show that, with only a small portion of subjects for training, the proposed method is able to produce more accurate and robust brain extraction results, at Jaccard Index of 0.956 +/- 0.010 on total 340 subjects under 6-fold cross validation, compared to those by the BET and BSE even using their best parameter combinations.

Original languageEnglish
Title of host publicationMedical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
Pages313-321
Number of pages9
Volume14
EditionPt 3
Publication statusPublished - 2011 Dec 1

Fingerprint

Learning
Brain
Libraries

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Shi, F., Wang, L., Gilmore, J. H., Lin, W., & Shen, D. (2011). Learning-based meta-algorithm for MRI brain extraction. In Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention (Pt 3 ed., Vol. 14, pp. 313-321)

Learning-based meta-algorithm for MRI brain extraction. / Shi, Feng; Wang, L.; Gilmore, John H.; Lin, Weili; Shen, Dinggang.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 14 Pt 3. ed. 2011. p. 313-321.

Research output: Chapter in Book/Report/Conference proceedingChapter

Shi, F, Wang, L, Gilmore, JH, Lin, W & Shen, D 2011, Learning-based meta-algorithm for MRI brain extraction. in Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Pt 3 edn, vol. 14, pp. 313-321.
Shi F, Wang L, Gilmore JH, Lin W, Shen D. Learning-based meta-algorithm for MRI brain extraction. In Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Pt 3 ed. Vol. 14. 2011. p. 313-321
Shi, Feng ; Wang, L. ; Gilmore, John H. ; Lin, Weili ; Shen, Dinggang. / Learning-based meta-algorithm for MRI brain extraction. Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 14 Pt 3. ed. 2011. pp. 313-321
@inbook{e1e296b433fe4047b6e2d71be2e59e65,
title = "Learning-based meta-algorithm for MRI brain extraction.",
abstract = "Multiple-segmentation-and-fusion method has been widely used for brain extraction, tissue segmentation, and region of interest (ROI) localization. However, such studies are hindered in practice by their computational complexity, mainly coming from the steps of template selection and template-to-subject nonlinear registration. In this study, we address these two issues and propose a novel learning-based meta-algorithm for MRI brain extraction. Specifically, we first use exemplars to represent the entire template library, and assign the most similar exemplar to the test subject. Second, a meta-algorithm combining two existing brain extraction algorithms (BET and BSE) is proposed to conduct multiple extractions directly on test subject. Effective parameter settings for the meta-algorithm are learned from the training data and propagated to subject through exemplars. We further develop a level-set based fusion method to combine multiple candidate extractions together with a closed smooth surface, for obtaining the final result. Experimental results show that, with only a small portion of subjects for training, the proposed method is able to produce more accurate and robust brain extraction results, at Jaccard Index of 0.956 +/- 0.010 on total 340 subjects under 6-fold cross validation, compared to those by the BET and BSE even using their best parameter combinations.",
author = "Feng Shi and L. Wang and Gilmore, {John H.} and Weili Lin and Dinggang Shen",
year = "2011",
month = "12",
day = "1",
language = "English",
volume = "14",
pages = "313--321",
booktitle = "Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention",
edition = "Pt 3",

}

TY - CHAP

T1 - Learning-based meta-algorithm for MRI brain extraction.

AU - Shi, Feng

AU - Wang, L.

AU - Gilmore, John H.

AU - Lin, Weili

AU - Shen, Dinggang

PY - 2011/12/1

Y1 - 2011/12/1

N2 - Multiple-segmentation-and-fusion method has been widely used for brain extraction, tissue segmentation, and region of interest (ROI) localization. However, such studies are hindered in practice by their computational complexity, mainly coming from the steps of template selection and template-to-subject nonlinear registration. In this study, we address these two issues and propose a novel learning-based meta-algorithm for MRI brain extraction. Specifically, we first use exemplars to represent the entire template library, and assign the most similar exemplar to the test subject. Second, a meta-algorithm combining two existing brain extraction algorithms (BET and BSE) is proposed to conduct multiple extractions directly on test subject. Effective parameter settings for the meta-algorithm are learned from the training data and propagated to subject through exemplars. We further develop a level-set based fusion method to combine multiple candidate extractions together with a closed smooth surface, for obtaining the final result. Experimental results show that, with only a small portion of subjects for training, the proposed method is able to produce more accurate and robust brain extraction results, at Jaccard Index of 0.956 +/- 0.010 on total 340 subjects under 6-fold cross validation, compared to those by the BET and BSE even using their best parameter combinations.

AB - Multiple-segmentation-and-fusion method has been widely used for brain extraction, tissue segmentation, and region of interest (ROI) localization. However, such studies are hindered in practice by their computational complexity, mainly coming from the steps of template selection and template-to-subject nonlinear registration. In this study, we address these two issues and propose a novel learning-based meta-algorithm for MRI brain extraction. Specifically, we first use exemplars to represent the entire template library, and assign the most similar exemplar to the test subject. Second, a meta-algorithm combining two existing brain extraction algorithms (BET and BSE) is proposed to conduct multiple extractions directly on test subject. Effective parameter settings for the meta-algorithm are learned from the training data and propagated to subject through exemplars. We further develop a level-set based fusion method to combine multiple candidate extractions together with a closed smooth surface, for obtaining the final result. Experimental results show that, with only a small portion of subjects for training, the proposed method is able to produce more accurate and robust brain extraction results, at Jaccard Index of 0.956 +/- 0.010 on total 340 subjects under 6-fold cross validation, compared to those by the BET and BSE even using their best parameter combinations.

UR - http://www.scopus.com/inward/record.url?scp=82255181704&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=82255181704&partnerID=8YFLogxK

M3 - Chapter

C2 - 22003714

VL - 14

SP - 313

EP - 321

BT - Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention

ER -