Abstract
Object boundary extraction is an important task in brain image analysis. Acquiring detailed 3D representations of the brain structures could improve the detection rate of diseases at earlier stages. Deformable model based segmentation methods have been widely used with considerable success. Recently, 3D Active Volume Model (AVM) was proposed, which incorporates both gradient and region information for robustness. However, the segmentation performance of this model depends on the position, size and shape of the initialization, especially for data with complex texture. Furthermore, there is no shape prior information integrated. In this paper, we present an approach combining AVM and Active Shape Model (ASM). Our method uses shape information from training data to constrain the deformation of AVM. Experiments have been made on the segmentation of complex structures of the rodent brain from MR images, and the proposed method performed better than the original AVM.
| Original language | English (US) |
|---|---|
| Title of host publication | 2011 8th IEEE International Symposium on Biomedical Imaging |
| Subtitle of host publication | From Nano to Macro, ISBI'11 |
| Pages | 433-436 |
| Number of pages | 4 |
| DOIs | |
| State | Published - Nov 2 2011 |
| Event | 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 - Chicago, IL, United States Duration: Mar 30 2011 → Apr 2 2011 |
Publication series
| Name | Proceedings - International Symposium on Biomedical Imaging |
|---|---|
| ISSN (Print) | 1945-7928 |
| ISSN (Electronic) | 1945-8452 |
Other
| Other | 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 |
|---|---|
| Country | United States |
| City | Chicago, IL |
| Period | 3/30/11 → 4/2/11 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Biomedical Engineering
- Radiology Nuclear Medicine and imaging
Cite this
}
3D segmentation of rodent brain structures using Active Volume Model with shape priors. / Zhang, Shaoting; Huang, Junzhou; Uzunbas, Mustafa; Shen, Tian; Delis, Foteini; Huang, Sharon Xiaolei; Volkow, Nora; Thanos, Panayotis; Metaxas, Dimitris.
2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11. 2011. p. 433-436 5872439 (Proceedings - International Symposium on Biomedical Imaging).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - 3D segmentation of rodent brain structures using Active Volume Model with shape priors
AU - Zhang, Shaoting
AU - Huang, Junzhou
AU - Uzunbas, Mustafa
AU - Shen, Tian
AU - Delis, Foteini
AU - Huang, Sharon Xiaolei
AU - Volkow, Nora
AU - Thanos, Panayotis
AU - Metaxas, Dimitris
PY - 2011/11/2
Y1 - 2011/11/2
N2 - Object boundary extraction is an important task in brain image analysis. Acquiring detailed 3D representations of the brain structures could improve the detection rate of diseases at earlier stages. Deformable model based segmentation methods have been widely used with considerable success. Recently, 3D Active Volume Model (AVM) was proposed, which incorporates both gradient and region information for robustness. However, the segmentation performance of this model depends on the position, size and shape of the initialization, especially for data with complex texture. Furthermore, there is no shape prior information integrated. In this paper, we present an approach combining AVM and Active Shape Model (ASM). Our method uses shape information from training data to constrain the deformation of AVM. Experiments have been made on the segmentation of complex structures of the rodent brain from MR images, and the proposed method performed better than the original AVM.
AB - Object boundary extraction is an important task in brain image analysis. Acquiring detailed 3D representations of the brain structures could improve the detection rate of diseases at earlier stages. Deformable model based segmentation methods have been widely used with considerable success. Recently, 3D Active Volume Model (AVM) was proposed, which incorporates both gradient and region information for robustness. However, the segmentation performance of this model depends on the position, size and shape of the initialization, especially for data with complex texture. Furthermore, there is no shape prior information integrated. In this paper, we present an approach combining AVM and Active Shape Model (ASM). Our method uses shape information from training data to constrain the deformation of AVM. Experiments have been made on the segmentation of complex structures of the rodent brain from MR images, and the proposed method performed better than the original AVM.
UR - http://www.scopus.com/inward/record.url?scp=80055059194&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80055059194&partnerID=8YFLogxK
U2 - 10.1109/ISBI.2011.5872439
DO - 10.1109/ISBI.2011.5872439
M3 - Conference contribution
SN - 9781424441280
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 433
EP - 436
BT - 2011 8th IEEE International Symposium on Biomedical Imaging
ER -