Investigation of Intensity Correction in the Context\udof Image RegistrationReport as inadecuate






Author: Piotr Urban

Source: https://core.ac.uk/

An image registration algorithm with intensity correction was developed. A particular goal was to apply intensity correction instead of using multimodal similarity measures. ud The algorithm utilises common Levenberg-Marquardt optimisation. The author has chosen two dimensional affine and one dimensional B-Spline model as spatial transformation, as well as intensity correction models specific to CT images. They are global non-linear mapping and smooth local affine correction. The algorithm was tested experimentally using a wide class of simulated images and a limited class of medical images. ud Affine registration works properly even for deformations which exceed typical deformation encountered in medical practice. B-Spline registration works properly for small deformations and requires further development to increase capture range. ud The idea of separating intensity correction mapping from similarity measure is shown to ha...


Teaser



Investigation of Intensity Correction in the Context of Image Registration by Piotr Urban A thesis submitted in partial fulfilment for the requirements of the degree of Master of Philosophy at the University of Central Lancashire University of Central Lancashire, Preston UK School of Computing Engineering and Physical Sciences Applied Digital Signal and Image Processing Research Centre The research was part of Metrology Guided Radiation Therapy project which was funded by Engineering and Physical Science Research Council June 2010 Contents 1 Introduction 1.1 Background . 1.2 Image registration . 1.2.1 Single and multi-modal images 1.2.2 Examples of image registration 1.3 Similarity measure and intensity mapping 1.4 Aims of the research . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 Investigation of image registration 2.1 Intensity and landmark based registration 2.2 Definitions 2.2.1 Image and grid . 2.2.2 Interpolation 2.2.3 Spatial transformation with reverse mapping 2.2.4 Image registration and similarity measure 2.3 Parametric registration . 2.3.1 General algorithm . 2.3.2 Multi-resolution 2.3.3 Deformation models 2.3.4 Affine transformation . 2.3.5 B-Spline transformation 2.3.6 Similarity measure . 2.3.7 Image registration and optimisation . 2.4 Affine 2-d registration . 2.4.1 The algorithm implemented 2.4.2 Experimental results 2.4.3 Concluding remarks 2.5 Nonrigid B-Spline 1-d registration 2.5.1 The algorithm implemented 2.5.2 Experimental results 2.5.3 Concluding remarks 2.6 Summary 1 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 9 10 10 10 ....





Related documents