Back to Search
Start Over
Intensity-based Image Registration with a Guaranteed One-to-one Point Match
- Source :
- Methods of Information in Medicine. 43:327-330
- Publication Year :
- 2004
- Publisher :
- Georg Thieme Verlag KG, 2004.
-
Abstract
- Summary Objectives: In this paper, we propose a novel registration technique, which combines the concepts of landmark and automatic, non-rigid intensity-based approaches. A general framework, which might be used for many different registration problems is presented. The novel approach enables the incorporation of different distance measures as well as different smoothers. Methods: The proposed scheme minimizes a regular-ized distance measure subject to some interpolation constraints. The desired deformation is computed iteratively using an Euler-scheme for the first variation of the chosen objective functional. Results: A fast and robust numerical scheme for the computation of the wanted minimizer is developed, implemented, and applied to various registration tasks. This includes the registration of pre- and post-intervention images of the human eye. Conclusions: A novel framework for a parameter-free, non-rigid registration scheme which allows for the additional incorporation of user-defined landmarks is proposed. It enhances the reliability of conventional approaches considerably and thereby their acceptability by practitioners in a clinical environment.
- Subjects :
- Mathematical optimization
Computation
Reliability (computer networking)
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Image registration
Health Informatics
Image processing
Distance measures
Health Information Management
Image Interpretation, Computer-Assisted
Humans
Computer vision
Medical Informatics Applications
Fluorescein Angiography
Elastic matching
Mathematics
Advanced and Specialized Nursing
Landmark
business.industry
Models, Theoretical
Radiographic Image Enhancement
Subtraction Technique
Artificial intelligence
business
Algorithms
Interpolation
Subjects
Details
- ISSN :
- 2511705X and 00261270
- Volume :
- 43
- Database :
- OpenAIRE
- Journal :
- Methods of Information in Medicine
- Accession number :
- edsair.doi.dedup.....612c877b727eeee943e9edad7efb6ca4