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 language | English |
|---|---|
| Title of host publication | Communications in Computer and Information Science |
| Publisher | Springer Verlag |
| Pages | 240-248 |
| Number of pages | 9 |
| Volume | 546 |
| ISBN (Print) | 9783662485576 |
| DOIs | |
| Publication status | Published - 2015 |
| Externally published | Yes |
| Event | 1st Chinese Conference on Computer Vision, CCCV 2015 - Xian, China Duration: 2015 Sep 18 → 2015 Sep 20 |
Publication series
| Name | Communications in Computer and Information Science |
|---|---|
| Volume | 546 |
| ISSN (Print) | 18650929 |
Other
| Other | 1st Chinese Conference on Computer Vision, CCCV 2015 |
|---|---|
| Country | China |
| City | Xian |
| Period | 15/9/18 → 15/9/20 |
Fingerprint
ASJC Scopus subject areas
- Computer Science(all)
Cite this
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 proceeding › Conference contribution
}
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 -