Loading...

Intra-Operative Registration of Non-Rigid Tissue for Image-Guided Surgery

Amiri, Hakimeh | 2012

641 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 43935 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Kasaei, Shohreh
  7. Abstract:
  8. Image Registration is a fundamental task in numerous applications in medical image processing and is defined as the process of determining the correspondence of between images collected at different times or using different imaging modalities. This correspondence can be used for aligning images so that the pair can be directly compared, combined or analyzed. Image-guided surgery systems use registration for establishing an accurate relation between preoperative and intraoperative image space. There have been several methods for rigid registration which are not easily applicable for soft tissues. Indeed, nonrigid deformation of soft tissues will endanger the accuracy of rigid methods, so it is vital to use nonrigid registration. There have been several methods proposed according to dimensionality of problem, application and modalities involved. B-spline registration method is one of the most important nonrigid registration methods. This algorithm uses optimization procedure to find optimal parameters of a b-spline transformation which registers images with minimum cost. Classic (local) or Metaheuristic (global) methods can be used for cost function optimization. Classical methods may easily trap in local minima and need cost function derivations. Since analytic derivative of some cost function is difficult to obtain, metaheuristic optimization methods such as particle swarm optimization and genetic algorithm are preferred. In this research, a nonrigid b-spline registration method with multilevel approach has been proposed that benefits from a novel hybrid particle swarm optimization methodwith Multiresolution approach. This novel optimization method uses a classical optimization method for the highest level of Gaussian resolution pyramid and particle swarm optimization for other pyramid levels. Our proposed optimization method achieves 14.4% increase in accuracy compared with other classic optimization methods
  9. Keywords:
  10. B-Spline ; Particles Swarm Optimization (PSO) ; Imaging Modality ; Multiresolution ; Non-Rigid Registration

 Digital Object List

 Bookmark

No TOC