Conference proceeding
Tensor scale-based image registration
Proceedings of SPIE, Vol.5032(1), pp.314-324
Medical Imaging 2003: Image Processing
05/16/2003
DOI: 10.1117/12.481433
Abstract
Tangible solutions to image registration are paramount in longitudinal as well as multi-modal medical imaging studies. In this paper, we introduce tensor scale - a recently developed local morphometric parameter - in rigid image registration. A tensor scale-based registration method incorporates local structure size, orientation and anisotropy into the matching criterion, and therefore, allows efficient multi-modal image registration and holds potential to overcome the effects of intensity inhomogeneity in MRI. Two classes of two-dimensional image registration methods are proposed - (1) that computes angular shift between two images by correlating their tensor scale orientation histogram, and (2) that registers two images by maximizing the similarity of tensor scale features. Results of applications of the proposed methods on proton density and T2-weighted MR brain images of (1) the same slice of the same subject, and (2) different slices of the same subject are presented. The basic superiority of tensor scale-based registration over intensity-based registration is that it may allow the use of local Gestalts formed by the intensity patterns over the image instead of simply considering intensities as isolated events at the pixel level. This would be helpful in dealing with the effects of intensity inhomogeneity and noise in MRI.
Details
- Title: Subtitle
- Tensor scale-based image registration
- Creators
- Punam K Saha - Univ. of Pennsylvania (USA)Hui Zhang - University of PennsylvaniaJayaram K Udupa - Univ. of Pennsylvania (USA)James C Gee - Univ. of Pennsylvania (USA)
- Resource Type
- Conference proceeding
- Publication Details
- Proceedings of SPIE, Vol.5032(1), pp.314-324
- Conference
- Medical Imaging 2003: Image Processing
- DOI
- 10.1117/12.481433
- ISSN
- 0277-786X
- Language
- English
- Date published
- 05/16/2003
- Academic Unit
- Radiology; Electrical and Computer Engineering
- Record Identifier
- 9984051707402771
Metrics
12 Record Views