Abstract
In this paper we present an accurate template-based technique for automatic detection of fiducial markers in 3D brain images so that fully automatic landmark-based co-registration can be implemented In our approach, we performed edge detection on a sequence of fiducial images in their location order. We then examined the resulting edge sequence to see if it matches a predefined template. In our tests, our approach detected successfully 429 out of 430 fiducial markers that can be recognized by human eyes. Thus, our template-based technique can eliminate the procedure of waiting for users to manually pick fiducial landmarks in images in landmark-based image-registrations.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 47-49 |
| Number of pages | 3 |
| Journal | International Journal of Computer Assisted Radiology and Surgery |
| Volume | 1 |
| Issue number | SUPPL. 7 |
| State | Published - Jun 2006 |
| Externally published | Yes |
Keywords
- Co-registration
- Computer assisted surgery
- Fiducial detection
- Image processing
- Neurosurgery
ASJC Scopus subject areas
- Surgery
- Biomedical Engineering
- Radiology Nuclear Medicine and imaging
- Computer Vision and Pattern Recognition
- Health Informatics
- Computer Science Applications
- Computer Graphics and Computer-Aided Design