Interactive registration and segmentation for multi-atlas-based labeling of brain MR image

Qian Wang, Guorong Wu, Min Jeong Kim, Lichi Zhang, Dinggang Shen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In the conventional multi-atlas-based labeling methods, atlases are registered with each unlabeled image, which is then segmented by fusing the labels of all registered atlases. The registration is typically ignorant about the segmentation while the segmentation of each individual unlabeled image is independently considered, both of which potentially undermine the accuracy in labeling. In this work, we propose the interactive registration-segmentation scheme for multi-atlas- based labeling of brain MR images. First, we learn the distribution of all images (including atlases and unlabeled images) and register them to their common space in the groupwise manner. Then, we segment all unlabeled images simultaneously, by fusing the labels of the registered atlases in the common space as well as the tentative segmentation of the unlabeled images. Next, the (tentative) labeling feeds back to refine the registration, thus all images are more accurately aligned within the common space. The improved registration further boosts the accuracy to determine the segmentation of the unlabeled images. According to our experimental results, the iterative optimization to the interactive registration-segmentation scheme can improve the performances of the multi-atlas-based labeling significantly.

Original languageEnglish
Title of host publicationCommunications in Computer and Information Science
PublisherSpringer Verlag
Pages240-248
Number of pages9
Volume546
ISBN (Print)9783662485576
DOIs
Publication statusPublished - 2015
Externally publishedYes
Event1st Chinese Conference on Computer Vision, CCCV 2015 - Xian, China
Duration: 2015 Sep 182015 Sep 20

Publication series

NameCommunications in Computer and Information Science
Volume546
ISSN (Print)18650929

Other

Other1st Chinese Conference on Computer Vision, CCCV 2015
CountryChina
CityXian
Period15/9/1815/9/20

Fingerprint

Labeling
Brain
Labels

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Wang, Q., Wu, G., Kim, M. J., Zhang, L., & Shen, D. (2015). Interactive registration and segmentation for multi-atlas-based labeling of brain MR image. In Communications in Computer and Information Science (Vol. 546, pp. 240-248). (Communications in Computer and Information Science; Vol. 546). Springer Verlag. https://doi.org/10.1007/978-3-662-48558-3_24

Interactive registration and segmentation for multi-atlas-based labeling of brain MR image. / Wang, Qian; Wu, Guorong; Kim, Min Jeong; Zhang, Lichi; Shen, Dinggang.

Communications in Computer and Information Science. Vol. 546 Springer Verlag, 2015. p. 240-248 (Communications in Computer and Information Science; Vol. 546).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, Q, Wu, G, Kim, MJ, Zhang, L & Shen, D 2015, Interactive registration and segmentation for multi-atlas-based labeling of brain MR image. in Communications in Computer and Information Science. vol. 546, Communications in Computer and Information Science, vol. 546, Springer Verlag, pp. 240-248, 1st Chinese Conference on Computer Vision, CCCV 2015, Xian, China, 15/9/18. https://doi.org/10.1007/978-3-662-48558-3_24
Wang Q, Wu G, Kim MJ, Zhang L, Shen D. Interactive registration and segmentation for multi-atlas-based labeling of brain MR image. In Communications in Computer and Information Science. Vol. 546. Springer Verlag. 2015. p. 240-248. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-662-48558-3_24
Wang, Qian ; Wu, Guorong ; Kim, Min Jeong ; Zhang, Lichi ; Shen, Dinggang. / Interactive registration and segmentation for multi-atlas-based labeling of brain MR image. Communications in Computer and Information Science. Vol. 546 Springer Verlag, 2015. pp. 240-248 (Communications in Computer and Information Science).
@inproceedings{5972ebf973794b88a31514badcd1c47e,
title = "Interactive registration and segmentation for multi-atlas-based labeling of brain MR image",
abstract = "In the conventional multi-atlas-based labeling methods, atlases are registered with each unlabeled image, which is then segmented by fusing the labels of all registered atlases. The registration is typically ignorant about the segmentation while the segmentation of each individual unlabeled image is independently considered, both of which potentially undermine the accuracy in labeling. In this work, we propose the interactive registration-segmentation scheme for multi-atlas- based labeling of brain MR images. First, we learn the distribution of all images (including atlases and unlabeled images) and register them to their common space in the groupwise manner. Then, we segment all unlabeled images simultaneously, by fusing the labels of the registered atlases in the common space as well as the tentative segmentation of the unlabeled images. Next, the (tentative) labeling feeds back to refine the registration, thus all images are more accurately aligned within the common space. The improved registration further boosts the accuracy to determine the segmentation of the unlabeled images. According to our experimental results, the iterative optimization to the interactive registration-segmentation scheme can improve the performances of the multi-atlas-based labeling significantly.",
author = "Qian Wang and Guorong Wu and Kim, {Min Jeong} and Lichi Zhang and Dinggang Shen",
year = "2015",
doi = "10.1007/978-3-662-48558-3_24",
language = "English",
isbn = "9783662485576",
volume = "546",
series = "Communications in Computer and Information Science",
publisher = "Springer Verlag",
pages = "240--248",
booktitle = "Communications in Computer and Information Science",

}

TY - GEN

T1 - Interactive registration and segmentation for multi-atlas-based labeling of brain MR image

AU - Wang, Qian

AU - Wu, Guorong

AU - Kim, Min Jeong

AU - Zhang, Lichi

AU - Shen, Dinggang

PY - 2015

Y1 - 2015

N2 - In the conventional multi-atlas-based labeling methods, atlases are registered with each unlabeled image, which is then segmented by fusing the labels of all registered atlases. The registration is typically ignorant about the segmentation while the segmentation of each individual unlabeled image is independently considered, both of which potentially undermine the accuracy in labeling. In this work, we propose the interactive registration-segmentation scheme for multi-atlas- based labeling of brain MR images. First, we learn the distribution of all images (including atlases and unlabeled images) and register them to their common space in the groupwise manner. Then, we segment all unlabeled images simultaneously, by fusing the labels of the registered atlases in the common space as well as the tentative segmentation of the unlabeled images. Next, the (tentative) labeling feeds back to refine the registration, thus all images are more accurately aligned within the common space. The improved registration further boosts the accuracy to determine the segmentation of the unlabeled images. According to our experimental results, the iterative optimization to the interactive registration-segmentation scheme can improve the performances of the multi-atlas-based labeling significantly.

AB - In the conventional multi-atlas-based labeling methods, atlases are registered with each unlabeled image, which is then segmented by fusing the labels of all registered atlases. The registration is typically ignorant about the segmentation while the segmentation of each individual unlabeled image is independently considered, both of which potentially undermine the accuracy in labeling. In this work, we propose the interactive registration-segmentation scheme for multi-atlas- based labeling of brain MR images. First, we learn the distribution of all images (including atlases and unlabeled images) and register them to their common space in the groupwise manner. Then, we segment all unlabeled images simultaneously, by fusing the labels of the registered atlases in the common space as well as the tentative segmentation of the unlabeled images. Next, the (tentative) labeling feeds back to refine the registration, thus all images are more accurately aligned within the common space. The improved registration further boosts the accuracy to determine the segmentation of the unlabeled images. According to our experimental results, the iterative optimization to the interactive registration-segmentation scheme can improve the performances of the multi-atlas-based labeling significantly.

UR - http://www.scopus.com/inward/record.url?scp=84951282632&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84951282632&partnerID=8YFLogxK

U2 - 10.1007/978-3-662-48558-3_24

DO - 10.1007/978-3-662-48558-3_24

M3 - Conference contribution

AN - SCOPUS:84951282632

SN - 9783662485576

VL - 546

T3 - Communications in Computer and Information Science

SP - 240

EP - 248

BT - Communications in Computer and Information Science

PB - Springer Verlag

ER -