Non-rigid multimodal image registration based on local variability measures and optical flow
- Additional Document Info
- View All
In this paper, we present a novel methodology for multimodal non-rigid medical image registration. The proposed approach is based on combining an optical flow technique with a pixel intensity transformation by using a local variability measure, such as statistical variance or Shannon entropy. The methodology is basically composed by three steps: first, we approximate the global deformation using a rigid registration based on a global optimization technique, called particle filtering; second, we transform both target and source images into a new intensity space where they can be compared; and third, we obtain the optical flow between them by using the Horn and Shuck algorithm in an iterative scales-space framework. After these steps, the non-rigid registration is made up by adding the resulting vector fields, computed by the rigid registration, and the optical flow. The proposed algorithm was tested using a synthetic intensity mapping and non-rigid deformation of MRI images. Preliminary results show that the methodology seems to be a good alternative for non-rigid multimodal registration, obtaining an average error of less than two pixels in the estimation of the deformation vector field. © 2012 IEEE.
multimodal images; Non-rigid image registration; optimization Average errors; Deformation vectors; Global deformations; Global optimization techniques; Intensity mapping; Medical image registration; MRI Image; Multi-modal; Multi-modal image; Multimodal image registration; Multimodal registration; Non-rigid; Non-rigid deformation; Nonrigid image registration; Nonrigid registration; Novel methodology; Optical flow techniques; Particle Filtering; Pixel intensities; Rigid registration; Shannon entropy; Source images; Statistical variance; Variability measures; Vector fields; Algorithms; Deformation; Global optimization; Iterative methods; Optical flows; Optimization; Pixels; Image registration; algorithm; article; female; human; image enhancement; male; methodology; nuclear magnetic resonance imaging; theoretical model; Algorithms; Female; Humans; Image Enhancement; Magnetic Resonance Imaging; Male; Models, Theoretical
Digital Object Identifier (DOI)
Additional Document Info