A Novel Technique for Prealignment in Multimodality Medical Image Registration. (22nd May 2014)

• Record Type: Journal Article
• Authors: Zhou, Wu; Zhang, Lijuan; Xie, Yaoqin; Liang, Changhong
• Other Names: Liu An Academic Editor.
• Is Part Of: BioMed research international. Volume 2014(2014)
• Publication Date: 2014-05-22
• Subjects: Medicine -- Periodicals; Biology -- Periodicals; Biotechnology -- Periodicals; Life sciences -- Periodicals; 610.5
• DOI: 10.1155/2014/726852
• Languages: English
• ISSNs: 2314-6133

Abstract

Abstract : Image pair is often aligned initially based on a rigid or affine transformation before a deformable registration method is applied in medical image registration. Inappropriate initial registration may compromise the registration speed or impede the convergence of the optimization algorithm. In this work, a novel technique was proposed for prealignment in both monomodality and multimodality image registration based on statistical correlation of gradient information. A simple and robust algorithm was proposed to determine the rotational differences between two images based on orientation histogram matching accumulated from local orientation of each pixel without any feature extraction. Experimental results showed that it was effective to acquire the orientation angle between two unregistered images with advantages over the existed method based on edge-map in multimodalities. Applying the orientation detection into the registration of CT/MR, T1/T2 MRI, and monomadality images with respect to rigid and nonrigid deformation improved the chances of finding the global optimization of the registration and reduced the search space of optimization.