Rigid Medical Image Registration Research Articles

Non-rigid Multi-Modal Medical Image Registration Based on Improved Maximum Mutual Information PV Image Interpolation Method.

With the continuous improvement of medical imaging equipment, CT, MRI and PET images can obtain accurate anatomical information of the same patient site. However, due to the fuzziness of medical image physiological evaluation and the unhealthy understanding of objects, the registration effect of many methods is not ideal. Therefore, based on the medical image registration model of Partial Volume (PV) image interpolation method and rigid medical image registration method, this paper established the non-rigid registration model of maximum mutual information Novel Partial Volume (NPV) image interpolation method. The proposed NPV interpolation method uses the Davidon-Fletcher-Powell algorithm (DFP) algorithm optimization method to solve the transformation parameter matrix and realize the accurate transformation of the floating image. In addition, the cubic B-spline is used as the kernel function to improve the image interpolation, which effectively improves the accuracy of the registration image. Finally, the proposed NPV method is compared with the PV interpolation method through the human brain CT-MRI-PET image to obtain a clear CT-MRI-PET image. The results show that the proposed NPV method has higher accuracy, better robustness, and easier realization. The model should also have guiding significance in face recognition and fingerprint recognition.

End to End Unsupervised Rigid Medical Image Registration by Using Convolutional Neural Networks.

In this paper, we focus on the issue of rigid medical image registration using deep learning. Under ultrasound, the moving of some organs, e.g., liver and kidney, can be modeled as rigid motion. Therefore, when the ultrasound probe keeps stationary, the registration between frames can be modeled as rigid registration. We propose an unsupervised method with Convolutional Neural Networks. The network estimates from the input image pair the transform parameters first then the moving image is wrapped using the parameters. The loss is calculated between the registered image and the fixed image. Experiments on ultrasound data of kidney and liver verified that the method is capable of achieve higher accuracy compared with traditional methods and is much faster.

Cross‐cumulative residual entropy‐based medical image registration via hybrid differential search algorithm

AbstractImage registration is the process of overlaying images of the same scene taken at different times by different sensors from different viewpoints. The cross‐cumulative residual entropy (CCRE)‐based medical image registration could achieve a high precision and a strong robustness performance. However, the optimization problem formulated by CCRE consists of some local extrema, especially for noise images. In order to address these difficulties, this article proposes a new optimization algorithm named hybrid differential search algorithm (HDSA) to optimize CCRE. As HDSA consists of simple control parameters, it is independent of the initial searching point. In addition, HDSA ameliorated the search method and the iterative conditions. As a result, the optimization process is more stable and efficient. Image registration experiments of HDSA are performed and compared with the conventional differential search algorithm (DSA) and adaptive differential evolution with optional external archive (JADE). The results show that HDSA does not only overcome the difficulties of sticking in the local extrema but also enhances the precision of registration. It is effective, robust, and fast for both the single‐mode rigid medical image registration and the multispectral‐mode rigid medical image registration.

Rigid Medical Image Registration Using Learning-Based Interest Points and Features

Rigid Medical Image Registration Using Learning-Based Interest Points and Features

Rigid Medical Image Registration Based on Genetic Algorithms and Mutual Information

With the variety of medical imaging equipment’s application in the medical process,medical image registration becomes particularly important in the field of medical image processing,which has important clinical diagnostic and therapeutic value. This article describes the matrix conversion method of the rigid registration model, the basic concepts and principles of the mutual information algorithm ,the basic idea of genetic algorithms and algorithm’s flow , and the application of the improved genetic algorithms in practice. The rigid registration of two CT brain bones images uses mutual information as a similarity measure, genetic algorithm as the search strategy and matlab as programming environment. Using the three-point crossover technique to exchange the three parameters in the rigid transformation repeectively to produce new individuals, the genetic algorithm’s local search ability enhanced and the prematurity phenomenon can be reduced through the depth study of the basic genetic algorithm. The experiments show that the registration has high stability and accuracy.

Improved nearest neighbor interpolators based on confidence region in medical image registration

In order to reduce artifacts in match metric and improve the registration speed in medical image registration, three types of improved nearest neighbor (NN) interpolators based on confidence region (CR) are studied. These improved NN interpolators include: (1) NN based on deterministic confidence region (DCR), DCRNN; (2) NN based on stochastic confidence region (SCR), SCRNN; (3) NN based on confidence region integrating deterministic information and stochastic information (DSCR), DSCRNN. The values of normalized mutual information (NMI) are deterministic and accurate at any grid translation position when any improved NN interpolator is used. The smoothness of the NMI curves is compared by applying DCRNN, SCRNN, and DSCRNN interpolators to rigid medical image registration with different numbers of intensity bins and random variables. The results of tests show that the new DSCRNN interpolator outperforms DCRNN and SCRNN in curve smoothness and anti-micro-fluctuation, and outperforms the conditional NN, PVI and LI interpolators in convergence performance and noise immunity.

Rigid registration of medical images using 1D and 2D binary projections.

Image registration is a necessary procedure in everyday clinical practice. Several techniques for rigid and non-rigid registration have been developed and tested and the state-of-the-art is evolving from the research setting to incorporate image registration techniques into clinically useful tools. In this paper, we develop a novel rigid medical image registration technique which incorporates binary projections. This technique is tested and compared to the standard mutual information (MI) methods. Results show that the method is significantly more accurate and robust compared to MI methods. The accuracy is well below 0.5° and 0.5mm. This method introduces two more improvements over MI methods: (1)for 2D registration with the use of 1D binary projections, we use minimal interpolation; and (2) for 3D registration with the use of 2D binary projections the method converges to stable final positions, independent of the initial misregistration.

Rigid medical image registration using PCA neural network

Medical image registration plays an important role in clinical diagnosis and therapy planning. This paper proposes an automatic method to register computed tomography (CT) and magnetic resonance (MR) brain images by using first principal directions of feature images. In this method, principal component analysis (PCA) neural network is used to calculate the first principal directions from feature images, then the registration is accomplished by simply aligning feature images’ first principal directions and centroids. Simulations for MR–MR (MR and MR images) registration and CT–MR (CT and MR images) registration are carried out to illustrate the method.

RIGID MEDICAL IMAGE REGISTRATION AND ITS ASSOCIATION WITH MUTUAL INFORMATION

Image registration plays a crucial role in the computer vision and medical imaging field where it is used to develop a spatial mapping between different sets of data. These transformations can range from simple rigid registrations to complex nonrigid deformations. Mutual information (MI) is a popular entropy-based similarity measure which has recently experienced a prolific expansion in a number of image registration applications. Stemming from information theory, this measure generally outperforms most other intensity-based measures in multimodal applications as it only assumes a statistical dependence between images. This paper provides a thorough introduction to the MI measure and its use in rigid medical image registration. A look at the extensions proposed to the original measure will also be provided. These were developed to improve the robustness of the measure and to avoid certain cases when maximizing MI does not lead to the correct spatial alignment.