A 3D geometric deformable model for tubular structure segmentation
Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45) › 32_Refereed conference paper (with host publication) › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 10th International Multimedia Modelling Conference, MMM 2004 |
| Pages | 174-180 |
| Publication status | Published - 2004 |
Conference
| Title | Proceedings - 10th International Multimedia Modelling Conference, MMM 2004 |
|---|---|
| Place | Australia |
| City | Brisbana |
| Period | 5 - 7 January 2004 |
Link(s)
Abstract
A relational-tubular (ReTu) deformable model for segmenting the tubular branches of the network structure objects from media images is discussed. The deformation process is formulated as a two stage procedure such as tubular medial axis deformation and tubular surface deformation. To extract the robust data features from the volume with a complex map, a data term energy based on the mass and density of the volumetric data existed in the model cross-section is adopted. It is observed that the energy term that described the spatial relationship between vessels could be extended to the open problem of seperating arteries and veins from the TOF data.
Citation Format(s)
A 3D geometric deformable model for tubular structure segmentation. / Feng, Jun; Ip, Horace H.S.; Cheng, Shuk H.
Proceedings - 10th International Multimedia Modelling Conference, MMM 2004. 2004. p. 174-180.
Proceedings - 10th International Multimedia Modelling Conference, MMM 2004. 2004. p. 174-180.
Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45) › 32_Refereed conference paper (with host publication) › peer-review
