Sharif Digital Repository

Defining a suitable similarity measure is a crucial step in (medical) image registration tasks. A common problem with frequently used intensity-based image registration algorithms is that they assume intensities of different pixels are independent of each other that could lead to low registration performance especially in the presence of spatially-varying intensity distortions, because they ignore the complex interactions between the pixel intensities. Motivated by this problem, in this paper we present a novel similarity measure which takes into account nonstationarity of the pixels intensity and complex spatially varying intensity distortions in mono-modal settings. Experimental results on... 

The configuration of landmarks is an important issue in minimizing the target registration error (TRE). In this paper the effect of different landmark configurations on the accuracy of pedicle screw placement during image guided spine surgery (IGSS) is investigated. Since the spine is deformed in intra-operative conditions compared to the preoperative situation, an accurate alignment of each vertebra is crucial to compensate for the deformation. CT compatible markers are placed over anatomical landmarks which are feasible and routinely used in surgical procedures. The TRE is obtained directly for the markers which are placed on the right and left pedicle of the vertebra. The estimated TRE... 

The registration of images is a fundamental task in numerous applications in medical image processing. In this paper, a novel registration technique is proposed which combines landmark and intensity based approaches. In this framework, the free form deformation (FFD) is used as transformation which is the key point of our algorithm. Landmarks with FFD transformation define the guidance surface which increases robustness of intensity based registration to bias field (bias noise). In fact, the performance of registration is improved by matching both landmark and intensity information. The experimental results show that the proposed method is more accurate than only intensity based method... 

Spatially-varying intensity noise is a common source of distortion in medical images and is often associated with reduced accuracy in medical image registration. In this paper, we propose two multi-resolution image registration algorithms based on Empirical Mode Decomposition (EMD) that are robust against additive spatially-varying noise. EMD is a multi-resolution tool that decomposes a signal into several principle patterns and residual components. Our first proposed algorithm (LR-EMD) is based on the registration of EMD feature maps from both floating and reference images in various resolutions. In the second algorithm (AFR-EMD), we first extract a single average feature map based on EMD... 

A new method for image registration has been previously proposed by the authors, which the registration is based on physical forces. The registration parameters are translation and rotation. This method assumes images like charged materials that attract each other. In this case, one of the images moves in the same direction as the applied force while the other one is still. The movement of the image continues until the resultant force becomes zero. This approach estimates the registration parameters simultaneously and leading to a better optimized set of registration parameters. The registration error for this method is 1 to 3 pixels. In this paper we aim to develop this method for the... 

In this article, we look at early, recent, and state-of-the-art methods for registration of medical images using a range of high-performance computing (HPC) architectures including symmetric multiprocessing (SMP), massively multiprocessing (MMP), and architectures with distributed memory (DM), and nonuniform memory access (NUMA). The article is designed to be self-sufficient. We will take the time to define and describe concepts of interest, albeit briefly, in the context of image registration and HPC. We provide an overview of the registration problem and its main components in the section "Registration." Our main focus will be HPC-related aspects, and we will highlight relevant issues as... 

Point Set Registration (PSR) of anatomic parts is used in different fields such as Patient Specific Implant (PSI) design in Computer Assisted Surgery (CAS) procedure. We designed a modified rigid PSR method based on student's-t mixture model. The proposed method is compared with Coherent Point Drift (CPD) registration method. Higher convergence speed and the lower error value are the advantages of the suggested algorithm in compare with CPD. In our method, the number of iterations decreases by about 69%, and the final error improvement was about 7% in comparison with CPD. The robustness of the proposed algorithm makes it beneficial to be used in the procedure of designing PSI in both... 

Surface registration is a necessary step and widely used in medical image-aided surgery. It's relevance to medical imaging is that there is much useful anatomical information in the form of collected surface points which originate from complimentary modalities. In this study, the kinematic relations between two point clouds with different coordinate definitions have been generated. Using Influence Method of surface modeling for extracting point clouds functions, the transformation matrix would be resulted. The proposed method was applied for an experimental femur data points(651 points) using the MRI images. These data points were transformed in a 30 degrees flexion of knee. This... 

Similarity measure is an important block in image registration. Most traditional intensity-based similarity measures (e.g., sum-of-squared-difference, correlation coefficient, and mutual information) assume a stationary image and pixel-by-pixel independence. These similarity measures ignore the correlation between pixel intensities; hence, perfect image registration cannot be achieved, especially in the presence of spatially varying intensity distortions. Here, we assume that spatially varying intensity distortion (such as bias field) is a low-rank matrix. Based on this assumption, we formulate the image registration problem as a nonlinear and low-rank matrix decomposition (NLLRMD).... 

A rotated general regression neural network is presented as an enhancement to the general regression neural network. A variable kernel estimate for multivariate densities is considered. A coordinate transformation is adopted which circumvent the difficulty of predicting multimodal distribution with large variance differences between modes which is associated with the general regression neural network. The proposed technique trains the network in a way that the variance differences between modes is kept small and in the same order. Further, the technique reduces the number of indispensable training parameters to two parameters and lowers the load of the computation as well as the time for... 

Detection of changes in remotely sensed geographic images is required for a variety of applications including natural disasters. Change detection is an important process utilized for updating the geographic information system (GIS) data, monitoring natural resources and urban developments. It provides quantitative analysis of the spatial distribution of the area of interest. Different types of change detection techniques include: Multi-date visual composite (multitemporal composite), image differencing, post-classification, etc. In this work, we propose a change detection algorithm based on multiresolution analysis and motion estimation. We use multispectral satellite imagery and apply the... 

Similarity measure is an important key in image registration. Most traditional intensity-based similarity measures (e.g. sum-of-squared-differences, correlation coefficient, mutual information and correlation ratio) assume a stationary image and pixel-by-pixel independence. These similarity measures ignore the correlation among pixel intensities; hence, a perfect image registration cannot be achieved especially in the presence of spatially varying intensity distortions and outlier objects that appear in one image but not in the other. It is supposed here that non-stationary intensity distortion (such as bias field) has a sparse representation in the transformation domain. Based on this... 

Purpose: The accuracy of pedicle screw placement during image-guided spine surgery (IGSS) can be characterized by estimating the target registration error (TRE). The major factors that influence TRE were identified, minimized, and verified with in vitro experiments. Materials and methods: Computed-tomography- compatible markers are placed over anatomical landmarks of lumbar vertebral segments in locations that are feasible and routinely used in surgical procedures. TRE was determined directly for markers placed on the pedicles of vertebra segments. First, optimum selections of landmarks are proposed for different landmarks according to the minimum achievable TRE values in different... 

Existing algorithms based on scale invariant feature transform (SIFT) and Harris corners such as edge-driven dual-bootstrap iterative closest point and Harris-partial intensity invariant feature descriptor (PIIFD) respectivley have been shown to be robust in registering multimodal retinal images. However, they fail to register color retinal images with other modalities in the presence of large content or scale changes. Moreover, the approaches need preprocessing operations such as image resizing to do well. This restricts the application of image registration for further analysis such as change detection and image fusion. Motivated by the need for efficient registration of multimodal retinal... 

Elimination of motion artifact in breast MR images is a significant issue in pre-processing step before utilizing images for diagnostic applications. Breast MR Images are affected by slow varying intensity distortions as a result of contrast agent enhancement. Thus a nonrigid registration algorithm considering this effect is needed. Traditional similarity measures such as sum of squared differences and cross correlation, ignore the mentioned distortion. Therefore, efficient registration is not obtained. Residual complexity is a similarity measure that considers spatially varying intensity distortions by maximizing sparseness of the residual image. In this research, the results obtained by... 

Recognition and correction of inhomogeneous displacement caused by patient's movement has been recently discussed as an interesting topic in medical image processing. Considering consistency in general structure of the image during distortion, histogram could be employed as a fast implementation method in feature domain. Accordingly, attribute vectors could be defined for each pixel based on spatial features to find corresponding points in two images. Consequently a point-based and non-rigid transformation approach will be designed. A B-spline image registration has been applied to match those pairs with a defined smoothness factor. This algorithm is a step-by-step registration process... 

In feature-based image registration, feature selection and reduction methods play an important role in decreasing computational burden of these operations. In this paper, a new approach is introduced to reduce the dimension of extracted feature vectors of MR images. This approach is based on the selection of the maximum and minimum responses of the alpha stable filter for the MR images over the extracted features with different orientation in frequency domain. This algorithm selects the rotation invariant features which are suitable for image registration purposes. It has been shown that these features could efficiently describe the image elements. The discriminating ability of the features...