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 language | English |
|---|---|
| Title of host publication | Proceedings - International Symposium on Biomedical Imaging |
| Publisher | IEEE Computer Society |
| Pages | 1560-1563 |
| Number of pages | 4 |
| Volume | 2015-July |
| ISBN (Print) | 9781479923748 |
| DOIs | |
| Publication status | Published - 2015 Jul 21 |
| Externally published | Yes |
| Event | 12th IEEE International Symposium on Biomedical Imaging, ISBI 2015 - Brooklyn, United States Duration: 2015 Apr 16 → 2015 Apr 19 |
Other
| Other | 12th IEEE International Symposium on Biomedical Imaging, ISBI 2015 |
|---|---|
| Country | United States |
| City | Brooklyn |
| Period | 15/4/16 → 15/4/19 |
Fingerprint
Keywords
- Auto context model (ACM)
- Labeling
ASJC Scopus subject areas
- Biomedical Engineering
- Radiology Nuclear Medicine and imaging
Cite this
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 proceeding › Conference contribution
}
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 -