Joint labeling of multiple regions of interest (ROIS) by enhanced auto context models

Minjeong Kim, Guorong Wu, Yanrong Guo, Dinggang Shen

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

1 Citation (Scopus)

Abstract

Accurate segmentation of a set of regions of interest (ROIs) in the brain images is a key step in many neuroscience studies. Due to the complexity of image patterns, many learning-based segmentation methods have been proposed, including auto context model (ACM) that can capture highlevel contextual information for guiding segmentation. However, since current ACM can only handle one ROI at a time, neighboring ROIs have to be labeled separately with different ACMs that are trained independently without communicating each other. To address this, we enhance the current single-ROI learning ACM to multi-ROI learning ACM for joint labeling of multiple neighboring ROIs (called eACM). First, we extend current independently-trained single-ROI ACMs to a set of jointly-trained cross-ROI ACMs, by simultaneous training of ACMs for all spatially-connected ROIs to let them to share their respective intermediate outputs for coordinated labeling of each image point. Then, the context features in each ACM can capture the cross-ROI dependence information from the outputs of other ACMs that are designed for neighboring ROIs. Second, we upgrade the output labeling map of each ACM with the multi-scale representation, thus both local and global context information can be effectively used to increase the robustness in characterizing geometric relationship among neighboring ROIs. Third, we integrate ACM into a multi-atlases segmentation paradigm, for encompassing high variations among subjects. Experiments on Loni LPBA40 dataset show much better performance by our eACM, compared to the conventional ACM.

Original languageEnglish
Title of host publicationProceedings - International Symposium on Biomedical Imaging
PublisherIEEE Computer Society
Pages1560-1563
Number of pages4
Volume2015-July
ISBN (Print)9781479923748
DOIs
Publication statusPublished - 2015 Jul 21
Externally publishedYes
Event12th IEEE International Symposium on Biomedical Imaging, ISBI 2015 - Brooklyn, United States
Duration: 2015 Apr 162015 Apr 19

Other

Other12th IEEE International Symposium on Biomedical Imaging, ISBI 2015
CountryUnited States
CityBrooklyn
Period15/4/1615/4/19

Fingerprint

Labeling
Joints
Learning
Atlases
Neurosciences
Brain
Datasets
Experiments

Keywords

  • Auto context model (ACM)
  • Labeling

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Kim, M., Wu, G., Guo, Y., & Shen, D. (2015). Joint labeling of multiple regions of interest (ROIS) by enhanced auto context models. In Proceedings - International Symposium on Biomedical Imaging (Vol. 2015-July, pp. 1560-1563). [7164176] IEEE Computer Society. https://doi.org/10.1109/ISBI.2015.7164176

Joint labeling of multiple regions of interest (ROIS) by enhanced auto context models. / Kim, Minjeong; Wu, Guorong; Guo, Yanrong; Shen, Dinggang.

Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July IEEE Computer Society, 2015. p. 1560-1563 7164176.

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

Kim, M, Wu, G, Guo, Y & Shen, D 2015, Joint labeling of multiple regions of interest (ROIS) by enhanced auto context models. in Proceedings - International Symposium on Biomedical Imaging. vol. 2015-July, 7164176, IEEE Computer Society, pp. 1560-1563, 12th IEEE International Symposium on Biomedical Imaging, ISBI 2015, Brooklyn, United States, 15/4/16. https://doi.org/10.1109/ISBI.2015.7164176
Kim M, Wu G, Guo Y, Shen D. Joint labeling of multiple regions of interest (ROIS) by enhanced auto context models. In Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July. IEEE Computer Society. 2015. p. 1560-1563. 7164176 https://doi.org/10.1109/ISBI.2015.7164176
Kim, Minjeong ; Wu, Guorong ; Guo, Yanrong ; Shen, Dinggang. / Joint labeling of multiple regions of interest (ROIS) by enhanced auto context models. Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July IEEE Computer Society, 2015. pp. 1560-1563
@inproceedings{4db31db2feb240b0a83d0afefbe7cccb,
title = "Joint labeling of multiple regions of interest (ROIS) by enhanced auto context models",
abstract = "Accurate segmentation of a set of regions of interest (ROIs) in the brain images is a key step in many neuroscience studies. Due to the complexity of image patterns, many learning-based segmentation methods have been proposed, including auto context model (ACM) that can capture highlevel contextual information for guiding segmentation. However, since current ACM can only handle one ROI at a time, neighboring ROIs have to be labeled separately with different ACMs that are trained independently without communicating each other. To address this, we enhance the current single-ROI learning ACM to multi-ROI learning ACM for joint labeling of multiple neighboring ROIs (called eACM). First, we extend current independently-trained single-ROI ACMs to a set of jointly-trained cross-ROI ACMs, by simultaneous training of ACMs for all spatially-connected ROIs to let them to share their respective intermediate outputs for coordinated labeling of each image point. Then, the context features in each ACM can capture the cross-ROI dependence information from the outputs of other ACMs that are designed for neighboring ROIs. Second, we upgrade the output labeling map of each ACM with the multi-scale representation, thus both local and global context information can be effectively used to increase the robustness in characterizing geometric relationship among neighboring ROIs. Third, we integrate ACM into a multi-atlases segmentation paradigm, for encompassing high variations among subjects. Experiments on Loni LPBA40 dataset show much better performance by our eACM, compared to the conventional ACM.",
keywords = "Auto context model (ACM), Labeling",
author = "Minjeong Kim and Guorong Wu and Yanrong Guo and Dinggang Shen",
year = "2015",
month = "7",
day = "21",
doi = "10.1109/ISBI.2015.7164176",
language = "English",
isbn = "9781479923748",
volume = "2015-July",
pages = "1560--1563",
booktitle = "Proceedings - International Symposium on Biomedical Imaging",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Joint labeling of multiple regions of interest (ROIS) by enhanced auto context models

AU - Kim, Minjeong

AU - Wu, Guorong

AU - Guo, Yanrong

AU - Shen, Dinggang

PY - 2015/7/21

Y1 - 2015/7/21

N2 - Accurate segmentation of a set of regions of interest (ROIs) in the brain images is a key step in many neuroscience studies. Due to the complexity of image patterns, many learning-based segmentation methods have been proposed, including auto context model (ACM) that can capture highlevel contextual information for guiding segmentation. However, since current ACM can only handle one ROI at a time, neighboring ROIs have to be labeled separately with different ACMs that are trained independently without communicating each other. To address this, we enhance the current single-ROI learning ACM to multi-ROI learning ACM for joint labeling of multiple neighboring ROIs (called eACM). First, we extend current independently-trained single-ROI ACMs to a set of jointly-trained cross-ROI ACMs, by simultaneous training of ACMs for all spatially-connected ROIs to let them to share their respective intermediate outputs for coordinated labeling of each image point. Then, the context features in each ACM can capture the cross-ROI dependence information from the outputs of other ACMs that are designed for neighboring ROIs. Second, we upgrade the output labeling map of each ACM with the multi-scale representation, thus both local and global context information can be effectively used to increase the robustness in characterizing geometric relationship among neighboring ROIs. Third, we integrate ACM into a multi-atlases segmentation paradigm, for encompassing high variations among subjects. Experiments on Loni LPBA40 dataset show much better performance by our eACM, compared to the conventional ACM.

AB - Accurate segmentation of a set of regions of interest (ROIs) in the brain images is a key step in many neuroscience studies. Due to the complexity of image patterns, many learning-based segmentation methods have been proposed, including auto context model (ACM) that can capture highlevel contextual information for guiding segmentation. However, since current ACM can only handle one ROI at a time, neighboring ROIs have to be labeled separately with different ACMs that are trained independently without communicating each other. To address this, we enhance the current single-ROI learning ACM to multi-ROI learning ACM for joint labeling of multiple neighboring ROIs (called eACM). First, we extend current independently-trained single-ROI ACMs to a set of jointly-trained cross-ROI ACMs, by simultaneous training of ACMs for all spatially-connected ROIs to let them to share their respective intermediate outputs for coordinated labeling of each image point. Then, the context features in each ACM can capture the cross-ROI dependence information from the outputs of other ACMs that are designed for neighboring ROIs. Second, we upgrade the output labeling map of each ACM with the multi-scale representation, thus both local and global context information can be effectively used to increase the robustness in characterizing geometric relationship among neighboring ROIs. Third, we integrate ACM into a multi-atlases segmentation paradigm, for encompassing high variations among subjects. Experiments on Loni LPBA40 dataset show much better performance by our eACM, compared to the conventional ACM.

KW - Auto context model (ACM)

KW - Labeling

UR - http://www.scopus.com/inward/record.url?scp=84944315889&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944315889&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2015.7164176

DO - 10.1109/ISBI.2015.7164176

M3 - Conference contribution

AN - SCOPUS:84944315889

SN - 9781479923748

VL - 2015-July

SP - 1560

EP - 1563

BT - Proceedings - International Symposium on Biomedical Imaging

PB - IEEE Computer Society

ER -