A robust level set method based on local statistical information for noisy image segmentation

The paper presents an improved local region-based active contour model for image segmentation, which is robust to noise. A data fitting energy functional is defined in terms of curves and the energy terms which are based on the differences between the local average intensity and the global intensity means. Then the energy is incorporated into a level set variational formulation, from which a curve evolution equation is derived for energy minimization. And then the level set function is regularized by Gaussian filter to keep smooth and eliminate the re-initialization. By using the local statistical information, the proposed model can handle with noisy images. The proposed model is first presented as a two-phase level set formulation and then extended to a multi-phase one. Experimental results show desirable performances of the proposed model for both noisy synthetic and real images, especially with high level noise.     

基于混合能量模型水平集的合成孔径声纳图像分割方法

本文讨论了合成孔径声纳图像分割问题。首先介绍了Chan-Vese模型水平集方法,针对该模型存在的边界定位和重复初始化等问题,提出了一种改进的水平集方法。该方法的能量模型由区域信息项、边界信息项和距离约束函数构成的内部能量项三部分混合形成,既兼顾了全局优化特性和局部定位精度,又避免了水平集函数重复初始化,提高了运算效率。实验结果表明,该模型对于噪声干扰严重、边缘模糊的合成孔径声纳图像分割效果良好。     

Adaptive segmentation of magnetic resonance images with intensity inhomogeneity using level set method

It is a big challenge to segment magnetic resonance (MR) images with intensity inhomogeneity. The widely used segmentation algorithms are region based, which mostly rely on the intensity homogeneity, and could bring inaccurate results. In this paper, we propose a novel region-based active contour model in a variational level set formulation. Based on the fact that intensities in a relatively small local region are separable, a local intensity clustering criterion function is defined. Then, the local function is integrated around the neighborhood center to formulate a global intensity criterion function, which defines the energy term to drive the evolution of the active contour locally. Simultaneously, an intensity fitting term that drives the motion of the active contour globally is added to the energy. In order to segment the image fast and accurately, we utilize a coefficient to make the segmentation adaptive. Finally, the energy is incorporated into a level set formulation with a level set regularization term, and the energy minimization is conducted by a level set evolution process. Experiments on synthetic and real MR images show the effectiveness of our method.     

基于局部和全局信息的自适应水平集图像分割

针对仅采用局部或全局信息无法快速准确分割灰度不均匀图像的问题,提出了一种基于局部和全局信息的自适应水平集图像分割模型。首先,利用图像局部信息和全局信息建立局部能量项和全局能量项,并且利用演化曲线轮廓内外小邻域的灰度均值差作为自变量,建立了权重函数模型,实现了局部能量项和全局能量项之间权重的自适应调整,提高了模型分割灰度不均匀图像的效率和准确性。其次,提出了一种新的能量惩罚项,避免了水平集函数的重新初始化,增强了数值计算的稳定性。最后,为验证模型的优越性,将模型与CV模型、LBF模型和LGIF模型进行了对比,并通过分割时间、迭代次数以及相似度等指标对分割结果进行了客观、定量分析。最终结果表明:该模型不但对初始轮廓具有较高鲁棒性,而且对灰度不均匀图像具有较高的分割准确性与分割效率。     

Automatic segmentation of brain MRI in high-dimensional local and non-local feature space based on sparse representation

Automatic extraction of the varying regions of magnetic resonance images is required as a prior step in a diagnostic intelligent system. The sparsest representation and high-dimensional feature are provided based on learned dictionary. The classification is done by employing the technique that computes the reconstruction error locally and non-locally of each pixel. The acquired results from the real and simulated images are superior to the best MRI segmentation method with regard to the stability advantages. In addition, it is segmented exactly through a formula taken from the distance and sparse factors. Also, it is done automatically taking sparse factor in unsupervised clustering methods whose results have been improved.     

Image-guided regularization level set evolution for MR image segmentation and bias field correction

Magnetic resonance (MR) image segmentation is a crucial step in surgical and treatment planning. In this paper, we propose a level-set-based segmentation method for MR images with intensity inhomogeneous problem. To tackle the initialization sensitivity problem, we propose a new image-guided regularization to restrict the level set function. The maximum a posteriori inference is adopted to unify segmentation and bias field correction within a single framework. Under this framework, both the contour prior and the bias field prior are fully used. As a result, the image intensity inhomogeneity can be well solved. Extensive experiments are provided to evaluate the proposed method, showing significant improvements in both segmentation and bias field correction accuracies as compared with other state-of-the-art approaches.     

基于C-V模型的改进快速水平集图像分割法

针对水平集方法计算复杂度高,无法满足实时系统要求的缺陷,提出一种改进的快速水平集算法。该算法对快速水平集算法进行简化,采用单链表表示轮廓曲线。利用C-V模型的二值拟合项来设计曲线演化的速度函数,保留了C-V模型的全局优化特性。还给出了一个基于单链表中轮廓点个数变化的水平集演化终止准则。该算法不仅明显提高了分割速度,且对噪声图像也能实现高效的分割。     

Multicontext wavelet-based thresholding segmentation of brain tissues in magnetic resonance images

A novel segmentation method based on wavelet transform is presented for gray matter, white matter and cerebrospinal fluid in thin-sliced single-channel brain magnetic resonance (MR) scans. On the basis of the local image model, multicontext wavelet-based thresholding segmentation (MCWT) is proposed to classify 2D MR data into tissues automatically. In MCWT, the wavelet multiscale transform of local image gray histogram is done, and the gray threshold is gradually revealed from large-scale to small-scale coefficients. Image segmentation is independently performed in each local image to calculate the degree of membership of a pixel to each tissue class. Finally, a strategy is adopted to integrate the intersected outcomes from different local images. The result of the experiment indicates that MCWT outperforms other traditional segmentation methods in classifying brain MR images.     

Automatic segmentation for brain MR images via a convex optimized segmentation and bias field correction coupled model

Accurate segmentation of magnetic resonance (MR) images remains challenging mainly due to the intensity inhomogeneity, which is also commonly known as bias field. Recently active contour models with geometric information constraint have been applied, however, most of them deal with the bias field by using a necessary pre-processing step before segmentation of MR data. This paper presents a novel automatic variational method, which can segment brain MR images meanwhile correcting the bias field when segmenting images with high intensity inhomogeneities. We first define a function for clustering the image pixels in a smaller neighborhood. The cluster centers in this objective function have a multiplicative factor that estimates the bias within the neighborhood. In order to reduce the effect of the noise, the local intensity variations are described by the Gaussian distributions with different means and variances. Then, the objective functions are integrated over the entire domain. In order to obtain the global optimal and make the results independent of the initialization of the algorithm, we reconstructed the energy function to be convex and calculated it by using the Split Bregman theory. A salient advantage of our method is that its result is independent of initialization, which allows robust and fully automated application. Our method is able to estimate the bias of quite general profiles, even in 7T MR images. Moreover, our model can also distinguish regions with similar intensity distribution with different variances. The proposed method has been rigorously validated with images acquired on variety of imaging modalities with promising results.     

结合光源分割和线性图像深度估计的夜间图像去雾

夜间有雾图像通常具有对比度低、光照不均匀、颜色偏移以及噪声较多等现象,这些退化现象使得夜间图像去雾具有极大的挑战性。针对夜间图像存在的退化问题,本文提出了一种能够在夜间图像中有效去雾并提高图像质量的方法。首先,将图像分解成光晕层和有雾层,并对有雾层进行颜色校正。其次,通过一种新提出的带有伽马变换的图像光源分割方法来分割光源,并设置分割阈值作为像素点属于光源区域的概率值。然后,将得到的概率值与最大反射先验相结合来估计光源和非光源区域的大气光值。最后,根据图像深度与亮度、饱和度以及梯度之间的关系建立线性模型,进一步估计透射率的值。实验得到的分割阈值为0.07,线性深度估计参数分别为1.026 7、-0.596 6、0.673 5、0.004 135。实验结果表明本文方法在夜间图像去雾、消除光晕、减少噪声,以及提高可视度方面取得良好的效果。     

Accurate segmentation of leukocyte in blood cell images using Atanassov's intuitionistic fuzzy and interval Type II fuzzy set theory

In this paper automatic leukocyte segmentation in pathological blood cell images is proposed using intuitionistic fuzzy and interval Type II fuzzy set theory. This is done to count different types of leukocytes for disease detection. Also, the segmentation should be accurate so that the shape of the leukocytes is preserved. So, intuitionistic fuzzy set and interval Type II fuzzy set that consider either more number of uncertainties or a different type of uncertainty as compared to fuzzy set theory are used in this work. As the images are considered fuzzy due to imprecise gray levels, advanced fuzzy set theories may be expected to give better result. A modified Cauchy distribution is used to find the membership function. In intuitionistic fuzzy method, non-membership values are obtained using Yager's intuitionistic fuzzy generator. Optimal threshold is obtained by minimizing intuitionistic fuzzy divergence. In interval type II fuzzy set, a new membership function is generated that takes into account the two levels in Type II fuzzy set using probabilistic T co norm. Optimal threshold is selected by minimizing a proposed Type II fuzzy divergence. Though fuzzy techniques were applied earlier but these methods failed to threshold multiple leukocytes in images. Experimental results show that both interval Type II fuzzy and intuitionistic fuzzy methods perform better than the existing non-fuzzy/fuzzy methods but interval Type II fuzzy thresholding method performs little bit better than intuitionistic fuzzy method. Segmented leukocytes in the proposed interval Type II fuzzy method are observed to be distinct and clear.     

Effect of a uniform magnetic field on dielectric two-phase bubbly flows using the level set method

In this study, the behavior of a single bubble in a dielectric viscous fluid under a uniform magnetic field has been simulated numerically using the Level Set method in two-phase bubbly flow. The two-phase bubbly flow was considered to be laminar and homogeneous. Deformation of the bubble was considered to be due to buoyancy and magnetic forces induced from the external applied magnetic field. A computer code was developed to solve the problem using the flow field, the interface of two phases, and the magnetic field. The Finite Volume method was applied using the SIMPLE algorithm to discretize the governing equations. Using this algorithm enables us to calculate the pressure parameter, which has been eliminated by previous researchers because of the complexity of the two-phase flow. The finite difference method was used to solve the magnetic field equation. The results outlined in the present study agree well with the existing experimental data and numerical results. These results show that the magnetic field affects and controls the shape, size, velocity, and location of the bubble.     

A nonlinear PDE model for reconstructing a regular surface from sampled data using a level set formulation on triangular meshes

In this paper, we propose a nonlinear PDE model for reconstructing a regular surface from sampled data. At first, we show the existence and the uniqueness of a viscosity solution to this problem. Then we propose a numerical scheme for solving the nonlinear level set equation on unstructured triangulations adapted to the data sample. We show the consistency of this scheme. In addition, we show how to compute nodewise first and second order derivatives. Some application examples of curve or surface construction are provided to illustrate the potential and to demonstrate the accuracy of this method.     

Hybrid segmentation of left ventricle in cardiac MRI using gaussian-mixture model and region restricted dynamic programming

Segmentation of the left ventricle from cardiac magnetic resonance images (MRI) is very important to quantitatively analyze global and regional cardiac function. The aim of this study is to develop a novel and robust algorithm which can improve the accuracy of automatic left ventricle segmentation on short-axis cardiac MRI. The database used in this study consists of three data sets obtained from the Sunnybrook Health Sciences Centre. Each data set contains 15 cases (4 ischemic heart failures, 4 non-ischemic heart failures, 4 left ventricle (LV) hypertrophies and 3 normal cases). Three key techniques are developed in this segmentation algorithm: (1) ray scanning approach is designed for segmentation of images with left ventricular outflow tract (LVOT), (2) a region restricted technique is employed for epicardial contour extraction, and (3) an edge map with non-maxima gradient suppression approach is put forward to improve the dynamic programming to derive the epicardial boundary. The validation experiments were performed on a pool of data sets of 45 cases. For both endo- and epi-cardial contours of our results, percentage of good contours is about 91%, the average perpendicular distance is about 2 mm. The overlapping dice metric is about 0.92. The regression and determination coefficient between the experts and our proposed method on the ejection fraction (EF) is 1.01 and 0.9375, respectively; they are 0.9 and 0.8245 for LV mass. The proposed segmentation method shows the better performance and is very promising in improving the accuracy of computer-aided diagnosis systems in cardiovascular diseases.     

PDE-based spatial smoothing: a practical demonstration of impacts on MRI brain extraction, tissue segmentation and registration

Spatial smoothing is typically used to denoise magnetic resonance imaging (MRI) data. Gaussian smoothing kernels, associated with heat equations or isotropic diffusion (ISD), are widely adopted for this purpose because of their easy implementation and efficient computation, but despite these advantages, Gaussian smoothing kernels blur the edges, curvature and texture of images. To overcome these issues, researchers have proposed anisotropic diffusion (ASD) and non-local means [i.e., diffusion (NLD)] kernels. However, these new filtering paradigms are rarely applied to MRI analyses. In the current study, using real degraded MRI data, we demonstrated the effect of denoising using ISD, ASD and NLD kernels. Furthermore, we evaluated their impact on three common preprocessing steps of MRI data analysis: brain extraction, segmentation and registration. Results suggest that NLD-based spatial smoothing is most effective at improving the quality of MRI data preprocessing and thus should become the new standard method of smoothing in MRI data processing.     

Quantitative analysis of arterial spin labeling FMRI data using a general linear model

Arterial spin labeling techniques can yield quantitative measures of perfusion by fitting a kinetic model to difference images (tagged-control). Because of the noisy nature of the difference images investigators typically average a large number of tagged versus control difference measurements over long periods of time. This averaging requires that the perfusion signal be at a steady state and not at the transitions between active and baseline states in order to quantitatively estimate activation induced perfusion. This can be an impediment for functional magnetic resonance imaging task experiments. In this work, we introduce a general linear model (GLM) that specifies Blood Oxygenation Level Dependent (BOLD) effects and arterial spin labeling modulation effects and translate them into meaningful, quantitative measures of perfusion by using standard tracer kinetic models. We show that there is a strong association between the perfusion values using our GLM method and the traditional subtraction method, but that our GLM method is more robust to noise.     

Breakdown voltage model and structure realization of a thin silicon layer with linear variable doping on a silicon on insulator high voltage device with multiple step field plates

Based on the theoretical and experimental investigation of a thin silicon layer(TSL) with linear variable doping(LVD) and further research on the TSL LVD with a multiple step field plate(MSFP),a breakdown voltage(BV) model is proposed and experimentally verified in this paper.With the two-dimensional Poisson equation of the silicon on insulator(SOI) device,the lateral electric field in drift region of the thin silicon layer is assumed to be constant.For the SOI device with LVD in the thin silicon layer,the dependence of the BV on impurity concentration under the drain is investigated by an enhanced dielectric layer field(ENDIF),from which the reduced surface field(RESURF) condition is deduced.The drain in the centre of the device has a good self-isolation effect,but the problem of the high voltage interconnection(HVI) line will become serious.The two step field plates including the source field plate and gate field plate can be adopted to shield the HVI adverse effect on the device.Based on this model,the TSL LVD SOI n-channel lateral double-diffused MOSFET(nLDMOS) with MSFP is realized.The experimental breakdown voltage(BV) and specific on-resistance(R on,sp) of the TSL LVD SOI device are 694 V and 21.3 ·mm 2 with a drift region length of 60 μm,buried oxide layer of 3 μm,and silicon layer of 0.15 μm,respectively.     

The measurement of R2, and R2′ in HIV-infected patients using the prime sequence as a measure of brain iron deposition

Brain iron deposition was assessed at 1.5 T in the caudate nucleus, globus pallidus and frontal and parietooccipital white matter in 28 human immunodeficiency virus (HIV)-infected patients and 15 control subjects with a new Partially Refocussed Interleaved Multi-Echo sequence by measuring 1/T₂, 1/T₂^* and 1/T2′ (i.e., R₂, and R₂′). There were significant differences in the R₂ and of the caudate nucleus (p < 0.0001 and p < 0.05) and the R₂, and R₂′ of the globus pallidus (p < 0.001, p < 0.005 and p < 0.05) in HIV-infected patients compared to control subjects. There was a trend for higher values of R₂, and R₂′ in the globus pallidus and caudate nucleus in HIV-infected patients with later stage HIV disease. These results suggest that there is greater iron deposition in the basal ganglia of HIV-infected patients compared with control subjects, with a predilection for the globus pallidus. The relationship between iron deposition in the brain and various parameters of severity of HIV infection remains uncertain.     

Hyperpolarized He diffusion MRI and histology of secreted frizzled related protein-1 (SFRP1) deficient lungs in a Murine model

Secreted frizzled related protein-1 (SFRP1) plays a key role in many diverse processes, including embryogenesis, tissue repair, bone formation, and tumor genesis. Previous studies have shown the effects of the SFRP1 gene on lung development using the SFRP1 knockout mouse model via histological and physiological studies. In this study, the feasibility of ADC (acquired via HP ³He) to detect altered lung structure in the SFRP1 knockout (SFRP1^−/−) mice was investigated, and compared to analysis by histology. This study consisted of two groups, the wild-type (WT) mice and the knockout (KO) mice with n = 6 mice for each group. ³He ADC MRI and histology were performed on all of the animals. The global L_m values of WT and KO mice were 35.0 ± 0.8 μm and 38.4 ± 3.8 μm, respectively, which translated to an increase of 9.58% in the L_m of KO mice. The mean global ADCs for the WT and KO mice were 0.12 ± 0.01 cm²/s and 0.13 ± 0.01 cm²/s, respectively, which equated to a relative increase of 8.0% in the KO mice compared to the WT mice. In the sub-analysis of the anterior, medial and posterior lung regions, L_m increased by 10.50%, 6.66% and 11.84% in the KO mice, respectively, whereas the differences in ADC between the two groups in the anterior, medial, and posterior regions were 7.3%, 8.3%, and 4.6%, respectively. These results suggest that HP MRI measurements can be used as a suitable substitute for histology to obtain valuable information about lung geometry non-invasively. This technique is also advantageous as regional measurements can be performed, which can identify lung destruction more precisely. Most importantly, this approach extends far beyond the specific pathology analyzed in this study, as it can be applied to many other pathological conditions in the lung tissue, as well to many other embryonic studies.