scholarly journals IMAGE REGISTRATION BASED ON MAXIMIZATION OF GRADIENT CODE MUTUAL INFORMATION

2011 ◽  
Vol 24 (1) ◽  
pp. 1 ◽  
Author(s):  
Xiaoxiang Wang ◽  
Jie Tian
Keyword(s):  
Image Registration ◽  
Mutual Information ◽  
Search Space ◽  
Image Resolution ◽  
Hill Climbing ◽  
Global Maximum ◽  
Registration Method ◽  
Pixel Intensity ◽  
Biological Images ◽  
Reference Images

Herein one proposes a mutual information-based registration method using pixel gradient information rather than pixel intensity information. Special care is paid to finding the global maximum of the registration function. In particular, one uses simulated annealing method speeded up by including a statistical analysis to reduce the next search space across the cooling schedule. An additional speed up is obtained by combining this numerical strategy with hill-climbing method. Experimental results obtained on a limited database of biological images illustrate that the proposed method for image registration is relatively fast, and performs well as the overlap between the floating and reference images is decreased and/or the image resolution is coarsened.

scholarly journals Automatic PET-CT Image Registration Method Based on Mutual Information and Genetic Algorithms

2012 ◽  
Vol 2012 ◽  
pp. 1-12 ◽  
Author(s):  
Martina Marinelli ◽  
Vincenzo Positano ◽  
Francesco Tucci ◽  
Danilo Neglia ◽  
Luigi Landini
Keyword(s):  
Mutual Information ◽  
Optimization Method ◽  
Global Maximum ◽  
Similarity Function ◽  
Spatial Transformation ◽  
Registration Method ◽  
Registration Algorithm ◽  
Positron Emission ◽  
Pet Ct ◽  
Artery Disease

Hybrid PET/CT scanners can simultaneously visualize coronary artery disease as revealed by computed tomography (CT) and myocardial perfusion as measured by positron emission tomography (PET). Manual registration is usually required in clinical practice to compensate spatial mismatch between datasets. In this paper, we present a registration algorithm that is able to automatically align PET/CT cardiac images. The algorithm bases on mutual information (MI) as registration metric and on genetic algorithm as optimization method. A multiresolution approach was used to optimize the processing time. The algorithm was tested on computerized models of volumetric PET/CT cardiac data and on real PET/CT datasets. The proposed automatic registration algorithm smoothes the pattern of the MI and allows it to reach the global maximum of the similarity function. The implemented method also allows the definition of the correct spatial transformation that matches both synthetic and real PET and CT volumetric datasets.

scholarly journals A Novel Technique for Prealignment in Multimodality Medical Image Registration

2014 ◽  
Vol 2014 ◽  
pp. 1-16 ◽  
Author(s):  
Wu Zhou ◽  
Lijuan Zhang ◽  
Yaoqin Xie ◽  
Changhong Liang
Keyword(s):  
Image Registration ◽  
Medical Image ◽  
Orientation Angle ◽  
Search Space ◽  
Statistical Correlation ◽  
Medical Image Registration ◽  
Registration Method ◽  
Novel Technique ◽  
Orientation Histogram ◽  
Multimodality Image

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.

scholarly journals A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance

2011 ◽  
Author(s):  
Yifei Lou ◽  
Xun Jia ◽  
Xuejun Gu ◽  
Allen Tannenbaum
Keyword(s):  
Image Registration ◽  
Mutual Information ◽  
Input Data ◽  
Fluid Model ◽  
Source Code ◽  
Deformable Image Registration ◽  
Bhattacharyya Distance ◽  
Output Data ◽  
Registration Method ◽  
Viscous Fluid Model

This paper describes a multimodal deformable image registration method on the GPU. It is a CUDA-based implementation of a paper by E. D’Agostino et. al, ‘’A viscous fluid model for multimodal non-rigid image registration using mutual information’’. In addition, we incorporate an alternative metric as opposed to mutual information, called Bhattacharyya Distance, in the recent work of Lou and Tannenbaum. This paper is accompanied with the source code, input data, parameters and output data that the authors used for validating the algorithm.

Use of Information Discrepancy Measure to Register Medical Images

2011 ◽  
Vol 50-51 ◽  
pp. 790-793
Author(s):  
Shao Yan Sun ◽  
Lei Chen
Keyword(s):  
Image Registration ◽  
Mutual Information ◽  
Medical Image ◽  
Numerical Experiments ◽  
Three Dimensional ◽  
Registration Accuracy ◽  
Registration Method ◽  
Mathematical Properties ◽  
Discrepancy Measure ◽  
Multiple Sequences

Function of Degree of Disagreement (FDOD), a new measure of information discrepancy, quantifies the discrepancy of multiple sequences. This function has some peculiar mathematical properties, such as symmetry, boundedness and monotonicity. In this contribution, we first introduce the FDOD function to solve the three-dimensional (3-D) medical image registration problem. Numerical experiments illustrate that the new registration method based on the FDOD function can obtain subvoxel registration accuracy, and it is a competitive method with the mutual information based method.

scholarly journals A Medical Image Registration Method Based on Progressive Images

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Qian Zheng ◽  
Qiang Wang ◽  
Xiaojuan Ba ◽  
Shan Liu ◽  
Jiaofen Nan ◽  
...  
Keyword(s):  
Image Registration ◽  
Mutual Information ◽  
Medical Image ◽  
Medical Image Analysis ◽  
Reference Image ◽  
Medical Image Registration ◽  
Registration Method ◽  
Multimodal Registration ◽  
Coarse Registration ◽  
Registration Result

Background. Medical image registration is an essential task for medical image analysis in various applications. In this work, we develop a coarse-to-fine medical image registration method based on progressive images and SURF algorithm (PI-SURF) for higher registration accuracy. Methods. As a first step, the reference image and the floating image are fused to generate multiple progressive images. Thereafter, the floating image and progressive image are registered to get the coarse registration result based on the SURF algorithm. For further improvement, the coarse registration result and the reference image are registered to perform fine image registration. The appropriate progressive image has been investigated by experiments. The mutual information (MI), normal mutual information (NMI), normalized correlation coefficient (NCC), and mean square difference (MSD) similarity metrics are used to demonstrate the potential of the PI-SURF method. Results. For the unimodal and multimodal registration, the PI-SURF method achieves the best results compared with the mutual information method, Demons method, Demons+B-spline method, and SURF method. The MI, NMI, and NCC of PI-SURF are improved by 15.5%, 1.31%, and 7.3%, respectively, while MSD decreased by 13.2% for the multimodal registration compared with the optimal result of the state-of-the-art methods. Conclusions. The extensive experiments show that the proposed PI-SURF method achieves higher quality of registration.

Sign in / Sign up

Export Citation Format

Share Document