Multiresolution elastic medical image registration in standard intensity scale

Ulas Bagci, Li Bai

2008 IEEE 16th Signal Processing, Communication and Applications Conference (SIU 2008)

Abstract

Medical image registration is a difficult problem. Not only a registration algorithm needs to capture both large and small scale image deformations, it also has to deal with global and local image intensity variations. In this paper we describe a new multiresolution elastic image registration method that challenges these difficulties in image registration. To capture large and small scale image deformations, we use both global and local affine transformation algorithms. To address global and local image intensity variations, we apply an image intensity standardization algorithm to correct image intensity variations. This transforms image intensities into a standard intensity scale, which allows highly accurate registration of medical images.

Abstract source

This 2008 conference paper by Ulas Bagci and Li Bai presents an elastic image-registration method combining intensity standardization with a coarse-to-fine, multiresolution approach.

Summary

The paper addresses medical image registration under spatial deformation and image-intensity variation. Its method standardizes image intensities and then uses global affine alignment followed by locally affine, smooth elastic registration in a coarse-to-fine image pyramid. The authors report evaluations on two-dimensional images with synthetic affine and nonlinear deformations, using mean squared intensity differences and visual checkerboard inspection. These experiments do not establish clinical performance or prospective validation.

Cite this work

Ulas Bagci, Li Bai (2008). Multiresolution elastic medical image registration in standard intensity scale. 2008 IEEE 16th Signal Processing, Communication and Applications Conference (SIU 2008) https://doi.org/10.1109/SIU.2008.4632564

BibTeX