Abstract
A template-based and semi-automatic volumetrics system-Brain Vol is build to divide the any given patient brain to neo-cortical and sub-cortical regions. The standard region is given as standard ROI drawn on a standard brain volume. After normalization between the standard MR image and the patient MR image, the sub-cortical ROIs' boundary are refined based on gray matter. The neo-cortical ROIs are refined by sulcus information that is semi-automatically marked on the patient brain. Then the segmentation is applied to 4D PET image of same patient for calculation of TAC (Time Activity Curve) by co-registration between MR and PET.
Original language | English (US) |
---|---|
Pages (from-to) | 1734-1741 |
Number of pages | 8 |
Journal | Proceedings of SPIE - The International Society for Optical Engineering |
Volume | 4684 III |
DOIs | |
State | Published - 2002 |
Externally published | Yes |
Keywords
- Automatic segmentation
- MRI
- PET
- Registration
- Volumetrics
ASJC Scopus subject areas
- Electronic, Optical and Magnetic Materials
- Condensed Matter Physics
- Computer Science Applications
- Applied Mathematics
- Electrical and Electronic Engineering