Vascular active contour for vessel tree segmentation

In this paper, a novel active contour model is proposed for vessel tree segmentation. First, we introduce a region competition-based active contour model exploiting the gaussian mixture model, which mainly segments thick vessels. Second, we define a vascular vector field to evolve the active contour along its center line into the thin and weak vessels. The vector field is derived from the eigenanalysis of the Hessian matrix of the image intensity in a multiscale framework. Finally, a dual curvature strategy, which uses a vesselness measure-dependent function selecting between a minimal principal curvature and a mean curvature criterion, is added to smoothen the surface of the vessel without changing its shape. The developed model is used to extract the liver and lung vessel tree as well as the coronary artery from high-resolution volumetric computed tomography images. Comparisons are made with several classical active contour models and manual extraction. The experiments show that our model is more accurate and robust than these classical models and is, therefore, more suited for automatic vessel tree extraction.     

Towards multi-stage texture-based active contour image segmentation

In this paper, we present a three-stage approach to incorporation of texture analysis into a two-dimensional active contour segmentation framework. This approach allows to utilise texture information alongside other image features. The proposed method starts with an initial unsupervised feature computation and selection, then moves to a fast contour evolution process and ends with a final refinement stage. The algorithm is designed to be general in its nature and not restricted to any particular texture feature extraction method. In this paper, the initial stage generates a set of feature maps consisting of grey-level co-occurrence matrix and Gabor features. The implementation makes an extensive use of hardware acceleration for efficient calculation of a relatively large number of features. The performance of the method was tested on various synthetic and natural images and compared with results of other algorithms.     

Region-based active contour driven by global intensity fitting energy

In this paper, we present a novel region-based active contour model based on global intensity fitting energy in a variational level set framework. Meanwhile, an internal energy term is introduced, and it forces the level set function to be close to a signed distance function. Image global information utilized efficiently makes the proposed model insensitive to noise, and the introduced penalty term can avoid the costly re-initialization for the evolving level set function, which not only speeds up the contour evolvement, but also improves accuracy of the final contour. Comparisons with other classical region-based models, such as Chan-Vese model and Region-Scalable Fitting (RSF) model, show the advantages of our model in terms of efficiency and accuracy. Moreover, the model is robust to noise.     

STACS: new active contour scheme for cardiac MR image segmentation

The paper presents a novel stochastic active contour scheme (STACS) for automatic image segmentation designed to overcome some of the unique challenges in cardiac MR images such as problems with low contrast, papillary muscles, and turbulent blood flow. STACS minimizes an energy functional that combines stochastic region-based and edge-based information with shape priors of the heart and local properties of the contour. The minimization algorithm solves, by the level set method, the Euler-Lagrange equation that describes the contour evolution. STACS includes an annealing schedule that balances dynamically the weight of the different terms in the energy functional. Three particularly attractive features of STACS are: 1) ability to segment images with low texture contrast by modeling stochastically the image textures; 2) robustness to initial contour and noise because of the utilization of both edge and region-based information; 3) ability to segment the heart from the chest wall and the undesired papillary muscles due to inclusion of heart shape priors. Application of STACS to a set of 48 real cardiac MR images shows that it can successfully segment the heart from its surroundings such as the chest wall and the heart structures (the left and right ventricles and the epicardium.) We compare STACS' automatically generated contours with manually-traced contours, or the "gold standard," using both area and edge similarity measures. This assessment demonstrates very good and consistent segmentation performance of STACS.     

基于相位一致性改进的活动轮廓分割模型

为了实现甲状腺超声图像中结节组织的快速准确分割,克服图像灰度分布不均匀和边缘模糊对分割结果造成的影响,采用了基于相位一致性改进的活动轮廓分割模型。首先,利用相位一致性边缘检测原理构造一种新的速度函数,不仅弥补了梯度算子边缘检测中由于滤波处理造成边缘损坏的缺陷,而且可以灵活地控制曲线演化速率;然后,将该速度函数乘入到无边缘主动轮廓模型的能量项中,避免了线性组合中的权重分配问题,同时具有全局分割能力。通过理论分析和实验验证,改进模型的相对差异度均小于1%,运行时间均低于对比模型。结果表明,新模型实现了灰度分布不均匀图像的精确分割,同时分割效率也有所提高。     

High speed VLSI architecture for improved region based active contour segmentation technique

Active contour segmentation is an important stage in image analysis applications. In this article, an improved region based active contour segmentation is proposed. The proposed active contour model speeds up the contour convergence by up to 40% while maintaining the advantages of a local region based active contour model by reducing the number of iterations. Moreover, we propose a low-complexity pipelined VLSI architecture for improved region based active contour model targeting FPGA and 90 nm ASIC platforms. The proposed pipelined design offers an increased speed of operation. Its complexity is independent of the size of image.     

Fully automatic luminal contour segmentation in intracoronary ultrasound imaging--a statistical approach

In this paper, a fully automatic method for luminal contour segmentation in intracoronary ultrasound imaging is introduced. Its principle is based on a contour with a priori properties that evolves according to the statistics of the ultrasound texture brightness, which is generally Rayleigh distributed. The main interest of the technique is its fully automatic character. This is insured by an initial contour that is not set by the user, like in classical snake-based algorithms, but estimated and, thus, adapted to each image. Its estimation combines two pieces of information extracted from the a posteriori probability function of the contour position: the function maximum location (or maximum a posteriori estimator) and the first zero-crossing of its derivative. Then, starting from the initial contour, a region of interest is automatically selected and the process iterated until the contour evolution can be ignored. In vivo coronary images from 15 patients, acquired with the 20-MHz central frequency Jomed Invision ultrasound scanner, were segmented with the developed method. Automatic contours were compared to those manually drawn by two physicians in terms of mean absolute difference. The results demonstrate that the error between automatic contours and the average of manual ones is of small amplitude, and only very slightly higher (0.099 +/- 0.032 mm) than the interexpert error (0.097 +/- 0.027 mm).     

一种血管约束的局部活动轮廓模型

活动轮廓作为一种重要的图像分割工具,近几年来在理论和应用方面都有很大的发展。然而,现有轮廓模型在处理灰度均匀性较差的图像时,通常存在较高的分割误差,并且对初始轮廓曲线位置敏感。为此,本文提出一种基于血管特征约束的活动轮廓模型,该模型首先使用局部相位（Local Phase）的血管增强算法对图像进行增强处理以生成一种不同于图像灰度的血管特征信息,然后将血管信息和图像灰度以线性加权的形式引入到局部二值拟合（Local Binary Fitting,LBF）能量泛函中,指导图像血管分割。基于视网膜血管图像数据（Digital Retinal Images for Vessel Extraction,DRIV）的实验显示：该模型能成功地从灰度分布不均匀和弱边界轮廓的视网膜图像中提取血管,分割灵敏度和准确性分别达到74.43%和93.67%,同时对初始轮廓曲线位置的敏感性大为降低。由上述可知,该模型具有高分割准确性和低初始位置敏感性。     

基于改进主动轮廓模型的图像分割算法

针对C-V模型对灰度不均匀的图像分割效果不理想的情况,提出一种改进的C-V模型.该模型在C-V模型的基础上,引入非加权的邻域平均和局部窗口方差概念,加快并精确了C-V模型的演化效果,同时在C-V模型的能量函数中加入惩罚项,使得C-V模型在演化过程中无须重新初始化,进一步提高了分割速度.仿真实验结果表明改进的C-V模型较原模型对灰度不均匀图像分割具有较好的分割效果.     

Image segmentation using fuzzy energy-based active contour with shape prior

This paper presents a fuzzy energy-based active contour model with shape prior for image segmentation. The paper proposes a fuzzy energy functional including a data term and a shape prior term. The data term, inspired from the region-based active contour approach proposed by Chan and Vese, evolves the contour relied on image information. The shape term inspired from Chan and Zhu’s work, defined as the distance between the evolving shape and a reference one, constrains the evolving contour with respect to the reference shape. To align the shapes, we exploit the shape normalization procedure which takes into account the affine transformation. In addition, to minimize the energy functional, we utilize a direct method to calculate the energy alterations. The proposed model therefore can deal with images with background clutter and object occlusion, improves the computational speed, and avoids difficulties associated with time step selection issue in gradient descent-based approaches.     

A fuzzy energy-based active contour model with adaptive contrast constraint for local segmentation

Image segmentation is to divide an image into different parts or extract some interested objects. Active contour model and fuzzy clustering are two widely used segmentation methods, which have been integrated into an effective model in recent years. Local segmentation is often needful in medical image processing. In view of local segmentation on inhomogeneous images, a new average fuzzy energy-based active contour model is proposed in this paper, in which the total fuzzy energy integrates the approximate weighted average and arithmetic average variances of the image. And an adaptive contrast constraint condition is introduced to prevent the curve from falling into local minimum, which further improves the robustness of the segmentation model to initial contour. Experimental results on synthetic and medical images demonstrate that the proposed model has considerable improvements in terms of segmentation accuracy and robustness compared to several existing local segmentation models.     

Moving object segmentation and detection for monocular robot based on active contour model

A novel geodesic active contour model based on optical flow information is proposed to segment and detect the moving object for monocular robots. More specifically, an active contour is formulated using the level set method, which eliminates the need of re-initialisation. The developed scheme alleviates the effect of optical flow noise, increasing the robustness of the detection of moving objects. Experimental results show that this algorithm can successfully track a moving target, e.g. a human being.     

Coupling of radial-basis network and active contour model for multispectral brain MRI segmentation

Magnetic resonance (MR) has been accepted as the reference image study in the clinical environment. The development of new sequences has allowed obtaining diverse images with high clinical importance and whose interpretation requires their joint analysis (multispectral MRI). Recent approaches to segment MRI point toward the definition of hybrid models, where the advantages of region and contour-based methods can be exploited to look for the integration or fusion of information, thus enhancing the performance of the individual approaches. Following this perspective, a hybrid model for multispectral brain MRI segmentation is presented. The model couples a segmenter, based on a radial basis network (RBFNNcc), and an active contour model, based on a cubic spline active contour (CSAC) interpolation. Both static and dynamic coupling of RBFNNcc and CSAC are proposed; the RBFNNcc stage provides an initial contour to the CSAC; the initial contour is optimally sampled with respect to its curvature variations; multispectral information and a restriction term are included into the CSAC energy equation. Segmentations were compared to a reference stack, indicating high-quality performance as measured by Tanimoto indexes of 0.74 +/- 0.08.     

Zernike moment and local distribution fitting fuzzy energy-based active contours for image segmentation

This paper presents a new region-based active contour model for extracting the object boundaries in an image, based on techniques of curve evolution. The proposed model introduces an energy functional that involves intensity distributions in local image regions and fuzzy membership functions. The local image intensity distribution information used to guide the motion of the contour, in the paper, is derived by Hueckel operator in the neighborhood of each image point. The parameters of Hueckel operator are estimated by a set of orthogonal Zernike moments before curve evolution. Meanwhile, the fuzzy membership functions are used to measure the association degree of each image pixel to the region outside and inside the contour. To minimize the energy functional, instead of solving the Euler–Lagrange equation of the underlying problem, the paper employs a direct method to compute the energy alterations. As a result, the model can deal with images with intensity inhomogeneity. In addition, the model effectively alleviates the sensitivity to contour initialization. Moreover, the model reduces computational cost, avoids problems associated with choosing time steps as well as allows fast convergence to the segmentation solutions. Experimental results on synthetic, real images and comparisons with other models show the desired performances of the proposed model.     

图像边缘提取的区域联合分割与主动轮廓模型

在目标的识别与跟踪处理中,目标图像的边缘提取是一项关键技术。采用边缘区域分割和主动轮廓C-V模型算法,而C-V模型更适用于水下的球体、椭球体边缘检测,具有提取的边缘连续的优点。当然,在处理不同的实际问题时,针对环境条件和要求的不同,可以选择适合的算子进行图像边缘提取。     

Integrating machine learning with region-based active contour models in medical image segmentation

Region-based active contour models are effective in segmenting images with poorly defined boundaries but often fail when applied to images containing intensity inhomogeneity. The traditional models utilize pixel intensity and are very sensitive to parameter tuning. On the other hand, machine learning algorithms are highly effective in handling inhomogeneities but often result in noise from misclassified pixels. In addition, there is no objective function. We propose a framework which integrates machine learning with a region-based active contour model. Classification probability scores from machine learning algorithm, which are regularized using a non-linear function, are used to replace the pixel intensity values during energy minimization. In our experiments, we integrate the k-nearest neighbours and the support vector machine with the Chan-Vese method and compare the results obtained with the traditional methods of Chan-Vese and Li et al. The proposed framework gives better accuracy and less sensitive to parameter tuning.     

Unsupervised segmentation based on robust estimation and color active contour models.

One of the most commonly used clinical tests performed today is the routine evaluation of peripheral blood smears. In this paper, we investigate the design, development, and implementation of a robust color gradient vector flow (GVF) active contour model for performing segmentation, using a database of 1791 imaged cells. The algorithms developed for this research operate in Luv color space, and introduce a color gradient and L2E robust estimation into the traditional GVF snake. The accuracy of the new model was compared with the segmentation results using a mean-shift approach, the traditional color GVF snake, and several other commonly used segmentation strategies. The unsupervised robust color snake with L2E robust estimation was shown to provide results which were superior to the other unsupervised approaches, and was comparable with supervised segmentation, as judged by a panel of human experts.     

A hybrid active contour model based on global and local information for medical image segmentation

Multidimensional Systems and Signal Processing - For segmenting medical images with abundant noise, blurry boundaries, and intensity heterogeneities effectively, a hybrid active contour model that...