Desired Object Boundary Research Articles

Local image fitting-based active contour for vector-valued images

<span>Variational active contour seeks to segment or extract desired object boundaries for further analysis. The model can be divided into global segmentation and selective segmentation. Selective segmentation, which focuses on segmenting a particular object, is preferable to the global model. Recently, a number of selective segmentation models have been developed to precisely extract an object on grayscale images. Nevertheless, if the input image is vector-valued (colour), these models merely convert it to a grayscale image, resulting in data loss owing to the reduction in image dimension. Furthermore, they may have poor segmentation performance due to the intensity inhomogeneous images. Therefore, a new model on variational selective active contour for segmenting vector-valued images has been proposed that incorporates the concepts of local image fitting and distance-based fitting terms into a variational minimization energy functional. Moreover, a Gaussian function was used as a regularizer to replace the computationally expensive Total Variation term. Then, the proposed model’s Euler Lagrange equation has been provided to solve the model. When segmenting an object in inhomogeneous intensity images, the result of the proposed model was about 30% more accurate based on the Jaccard value and about 3 times faster than other existing methods.</span>

Automated segmentation and area estimation of neural foramina with boundary regression model

Accurate segmentation and area estimation of neural foramina from both CT and MR images are essential to clinical diagnosis of neural foramina stenosis. Existing clinical routine, relying on physician's purely manual segmentation, becomes very tedious, laborious, and inefficient. Automated segmentation is highly desirable but faces big challenges from diverse boundary, local weak/no boundary, and intra/inter-modality intensity inhomogeneity. In this paper, a novel boundary regression segmentation framework is proposed for fully automated and multi-modal segmentation of neural foramina. It creatively formulates the segmentation task as a boundary regression problem which models a highly nonlinear mapping function from substantially diverse neural foramina images directly to desired object boundaries. By leveraging a seamless combination of multiple output support vector regression (MSVR) and multiple kernel learning (MKL), the proposed framework enables the domain knowledge learning in a holistic fashion which successfully handles the extreme diversity posing a tremendous challenge to conventional segmentation methods. The performance evaluation was conducted on a dataset including 912 MR images and 306 CT images collected from 152 subjects. Experimental results show that the proposed automated segmentation framework is highly consistent with physician with average DSI (dice similarity index) as high as 0.9005 (CT), 0.8984 (MR), 0.8935 (MR+CT) and BD (boundary distance) as low as 0.6393mm (CT), 0.6586mm (MR), 0.6881mm (MR+CT). Based on this accurate automated segmentation, the estimated areas, highly correlated to their independent ground truth, have been achieved with correlation coefficient: 0.9154 (CT) and 0.8789 (MR). Hence, the proposed approach enables an efficient, accurate and convenient tool for clinical diagnosis of neural foramina stenosis.

A robust statistics driven volume-scalable active contour for segmenting anatomical structures in volumetric medical images with complex conditions.

BackgroundAccurate segmentation of anatomical structures in medical images is a critical step in the development of computer assisted intervention systems. However, complex image conditions, such as intensity inhomogeneity, noise and weak object boundary, often cause considerable difficulties in medical image segmentation. To cope with these difficulties, we propose a novel robust statistics driven volume-scalable active contour framework, to extract desired object boundary from magnetic resonance (MR) and computed tomography (CT) imagery in 3D.MethodsWe define an energy functional in terms of the initial seeded labels and two fitting functions that are derived from object local robust statistics features. This energy is then incorporated into a level set scheme which drives the active contour evolving and converging at the desired position of the object boundary. Due to the local robust statistics and the volume scaling function in the energy fitting term, the object features in local volumes are learned adaptively to guide the motion of the contours, which thereby guarantees the capability of our method to cope with intensity inhomogeneity, noise and weak boundary. In addition, the initialization of active contour is simplified by select several seeds in the object and/or background to eliminate the sensitivity to initialization.ResultsThe proposed method was applied to extensive public available volumetric medical images with challenging image conditions. The segmentation results of various anatomical structures, such as white matter (WM), atrium, caudate nucleus and brain tumor, were evaluated quantitatively by comparing with the corresponding ground truths. It was found that the proposed method achieves consistent and coherent segmentation accuracy of 0.9246 ± 0.0068 for WM, 0.9043 ± 0.0131 for liver tumors, 0.8725 ± 0.0374 for caudate nucleus, 0.8802 ± 0.0595 for brain tumors, etc., measured by Dice similarity coefficients value for the overlap between the algorithm one and the ground truth. Further comparative experimental results showed desirable performances of the proposed method over several well-known segmentation methods in terms of accuracy and robustness.ConclusionWe proposed an approach to accurate segment volumetric medical images with complex conditions. The accuracy of segmentation, robustness to noise and contour initialization were validated on the basis of extensive MR and CT volumes.

Active contour model and nonlinear shape priors with application to left ventricle segmentation in cardiac MR images

This paper presents a new active contour model for left ventricle segmentation in cardiac magnetic resonance (MR) images. In this study, the shape prior is coupled with intensity information in the proposed energy functional which includes a data term and a shape term. The data term, inspired from a region-based active contour model, is used to guide the motion of the initial curve to desired object boundaries. Meanwhile, the shape term is utilized to constrain the evolving contour with respect to the reference shape, which helps the model deal with images in the presence of background clutter and object occlusion. Especially, in the paper, to reconstruct the shape prior, we utilize the kernel principal component analysis (KPCA) that allows the obtained prior shape to be faithful to the shape of the desired object. In addition, the pose variations between the shapes are handled by employing shape normalization procedure instead of solving a set of Euler–Lagrange equations as in conventional approaches. The proposed model is first presented as a two-phase level set formulation and then extended to a multi-phase formulation. Comparative experiments on a set of cardiac MR images show the advantages of the proposed model.

Active Contour Models for Manifold Valued Image Segmentation

Image segmentation is the process of partitioning an image into different regions or groups based on some characteristics like color, texture, motion, or shape etc. Active contours are a popular variational method for object segmentation in images, in which the user initializes a contour which evolves in order to optimize an objective function designed such that the desired object boundary is the optimal solution. Recently, imaging modalities that produce Manifold-valued images are frequently used, for example, DT-MRI images, vector fields. The traditional active contour model does not work on such images. In this paper, we generalize the active contour model to work on Manifold-valued images. As expected, our algorithm detects regions with similar Manifold values in the image. Our algorithm also produces expected results on usual gray-scale images, since these are nothing but trivial examples of Manifold-valued images. As another application of our general active contour model, we perform texture segmentation on gray-scale images by first creating an appropriate Manifold-valued image. We demonstrate segmentation results for manifold-valued images and texture images.

Regression Segmentation for <formula formulatype="inline"><tex Notation="TeX">$M^{3}$</tex></formula> Spinal Images

Clinical routine often requires to analyze spinal images of multiple anatomic structures in multiple anatomic planes from multiple imaging modalities (M(3)). Unfortunately, existing methods for segmenting spinal images are still limited to one specific structure, in one specific plane or from one specific modality (S(3)). In this paper, we propose a novel approach, Regression Segmentation, that is for the first time able to segment M(3) spinal images in one single unified framework. This approach formulates the segmentation task innovatively as a boundary regression problem: modeling a highly nonlinear mapping function from substantially diverse M(3) images directly to desired object boundaries. Leveraging the advancement of sparse kernel machines, regression segmentation is fulfilled by a multi-dimensional support vector regressor (MSVR) which operates in an implicit, high dimensional feature space where M(3) diversity and specificity can be systematically categorized, extracted, and handled. The proposed regression segmentation approach was thoroughly tested on images from 113 clinical subjects including both disc and vertebral structures, in both sagittal and axial planes, and from both MRI and CT modalities. The overall result reaches a high dice similarity index (DSI) 0.912 and a low boundary distance (BD) 0.928 mm. With our unified and expendable framework, an efficient clinical tool for M(3) spinal image segmentation can be easily achieved, and will substantially benefit the diagnosis and treatment of spinal diseases.

Improved Snake for Breast Tumor Image Segmentation Using Prior Shape Constraint

The accuracy of breast tumor image segmentation plays a crucial role in the radiotherapy treatment planning, which directly affects the effectiveness of patients treatment. Snake can dynamically track the desired object boundaries from an initial contour, however, its sensitivity and narrow capture range of initial contour has limited its utility. When Snake is directly applied to segment breast tumor image, it often produces improper result due to the closeness of intensity variations within both tumor area and non-tumor areas. Therefore, an improved Snake segmentation method based on the prior shape constraint is proposed to solve the problems caused by fuzzy boundaries and similar gray levels of tumor and non-tumor areas. Firstly, tumor lesion via partitioned images is extracted according to the gray and shape characteristics. Then morphological filter is utilized to enhance the lesion. Simultaneously, the average shape is obtained by establishing a prior shape model with Point Distribution Model (PDM). Finally, superposition of the deformable shape is derived by adjusting parameters with the mean shape upon real tumor boundaries in a new image. Snake is then employed to merge the real target contours. Experiments show that this method has higher accuracy and stronger robustness to noise. Moreover, perfect segmentation results are also attained in special cases where breast tumor and chest wall image intensity values are relatively close.

Use of biometric thermal factors for identification in access systems

The article considers the preconditions for use of the biometric identification and authentication methods based on the features of a human thermogram. The article presents the method of solution of the problem of recognition of a human face contour thermogram, which can improve the quality of functioning of the information security system and provide high factors of FAR and FRR. The method consists in the fact that initially for all image pixels the squared norm of gradient of change of their brightness was calculated. Then on a new black and white monochrome matrix by black colour on a white background all elements are set off, whose values of the norm of the gradient are over a threshold value. As outlines of objects in a monochrome matrix, we take coherent configurations of elements in black. Further, the coefficient is determined and the threshold value of squared norm of gradient is calculated. It is necessary to take into account that the values are higher than the overall average levels of non-zero changes in rows and columns, respectively, and among the connected configurations of elements in black on the monochrome matrix, the configurations, in which the number of input elements is less than a certain value, are rejected. For remaining configurations the average degree of neighborhood is calculated, i.e. the result of division of the sum of all elements of the configuration of neighboring elements into the sum of the elements in the configuration. At the same time, the configurations in which the average degree of neighborhood is less than three are rejected, and the remaining ones are accepted as the desired object boundaries.

Adaptive B-Snake model using shape and appearance information for object segmentation

A novel adaptive B-Spline deformable model is presented in this paper for object segmentation. Comparing with other B-Spline models, the proposed model has the following advantages. First, a fully automatic and affine-invariant strategy is proposed for landmark point assignment. Second, contrary to other B-Spline models that rely on predetermined number of control points, an automatic scheme for control point insertion is designed to enhance the adaptivity and the flexibility of B-Spline model for segmenting shapes with high complexity. Thirdly, a statistical framework is embedded for modeling the shape distribution and appearance characteristics of landmark points in the training samples. Fine deformation can be achieved through the minimum mean square error approach that allows the model to accurately adapt to the desired object boundaries in the image. Experiments on medical image segmentation are carried out to validate the performance, and comparison has been made with respect to the traditional Snake and ASM. It turns out that the proposed adaptive B-Spline model can attain more accurate object segmentation. Copyright © 2010 John Wiley & Sons, Ltd.

Gradient vector flow active contours with prior directional information

Active contours, or snakes, have been widely used in image processing and computer vision for image segmentation and object tracking. However, they usually have poor performance in segmenting images with complex object shape and complex background, and also in dealing with the issue of weak-edge-leakage. To guide the front of active contour toward the desired object boundary and prevent it from moving over the weak edges with strong neighbors, we present a novel external force field, referred to as gradient and direction vector flow (G&DVF), which integrates the gradient vector flow (GVF) and the prior directional information provided by a user. The proposed method is sufficiently general and simple to implement. The experiments conducted on image segmentation demonstrate that the proposed method is insensitive to image clutters/noise and capable of driving the fronts of active contours to conform to complex shapes and addressing the issue of weak-edge-leakage in some cases.

Fuzzy Energy-Based Active Contours

This paper presents a novel fast model for active contours to detect objects in an image, based on techniques of curve evolution. The proposed model can detect objects whose boundaries are not necessarily defined by gradient, based on the minimization of a fuzzy energy, which can be seen as a particular case of a minimal partition problem. This fuzzy energy is used as the model motivation power evolving the active contour, which will stop on the desired object boundary. However, the stopping term does not depend on the gradient of the image, as most of the classical active contours, but instead is related to the image color and spatial segments. The fuzziness of the energy provides a balanced technique with a strong ability to reject "weak" local minima. Moreover, this approach converges to the desired object boundary very fast, since it does not solve the Euler-Lagrange equations of the underlying problem, but, instead, calculates the fuzzy energy alterations directly. The theoretical properties and various experiments presented demonstrate that the proposed fuzzy energy-based active contour is better and more robust than classical snake methods based on the gradient or other kind of energies.

Live-wire-based image segmentation with embedded edge confidence

Live-wire-based image segmentation allows the user to select piece-wise globally optimal contour segments corresponding to a desired object boundary. However, the boundary extracted by live wire tends to deviate from the object boundary if other boundaries with strong gradient features are situated near a desirable object boundary. We present a new live-wire method based on the concept of embedded edge confidence to improve segmentation performance. Experimental results on medical images demonstrate the effectiveness of the proposed method.

Optimizing the Level Set Algorithm for Detecting Object Edges in MR and CT Images

Specifying the boundary of tissues or an organ is one of the most frequently required tasks for a radiologist. It is a first step for further processing, such as comparing two serial images in time, volume measurements. In the present work, we use genetic algorithms (GA) and where necessary apply a ldquodynamic genetic algorithmrdquo (dGA) procedure, which (we believe) is a unique application, to assess different values for finding an optimal set of parameters that characterize the level set method, a geometric active contour, for use as a boundary detection method. Four quantitative measures are used in calculating geometric differences between the object boundaries, as determined by the level set method, and the desired object boundaries. A semi-automated method is also developed to find the desired boundary for the object. A two-step method requires the user to manipulate the object boundaries obtained by applying an edge detection method based on the Canny filter. By setting the level set method parameters using the output of the GA we obtain accurate boundaries of organs automatically and rapidly.

Anisotropic Diffusion of Halting Speed Fields in Geometric Active Contour Model

Geometrical active contours (GAC) are used extensively in computer vision and image analysis, particularly to locate object boundaries. However, GAC-based segmentations have the drawbacks of long evolving time and boundary leaking. Because halting speed fields (HSF) in GAC models are typically not smooth enough in homogenous region, they are not able to make the active contour quickly move towards the desired object boundaries. On the other hand, the HSF don’t really vanish along the object boundaries, thus the curve propagating can not stop on the object boundaries and continuously move into the object boundaries (boundary leaking). In this paper, an anisotropic diffusion model is therefore presented and then applied to the HSF in GAC model. This GAC-based segmentation with the diffused HSF can overcome the two drawbacks above. Experimental results on a synthetic image and two real world images show the improvements in terms of reducing both the segmentation time and boundary leaking, in comparison of GAC model with the original HSF.

Separability-Based Intelligent Scissors for Interactive Image Segmentation

Intelligent scissors is an interactive image segmentation algorithm which allows a user to select piece-wise globally optimal contour segment corresponding to a desired object boundary. However, the intelligent scissors is too sensitive to a noise and texture patterns in an image since it utilizes the gradient information concerning the pixel intensities. This paper describes a new intelligent scissors based on the concept of the separability in order to improve the object boundary extraction performance. The effectiveness of the proposed method has been confirmed by some experiments for actual images acquired by an ordinary digital camera.

Feature optimization via simulated search for model-based heart segmentation

Medical images contain numerous different structures and organs. When segmenting a complex organ such as the heart, it is a typical problem of deformable models and related techniques that the image features defining the wanted object boundaries are not discriminative enough to distinguish between borders of different sub-organs. As a result, the model is often locally attracted by some wrong structures. We present a method to automatically learn from a representative set of 3D images which features are most appropriate at each position of the surface of the deformable model. The basic idea is to simulate the boundary detection for the given 3D images and to select those features that minimize the distance between the detected position and the desired object boundary. In addition, we present examples for heart segmentation showing that attraction by false edges is almost completely eliminated.

A hybrid boundary detection algorithm based on watershed and snake

Watersheds and snakes are used extensively in image processing, particularly in locating object boundaries. Both of them have their own advantages and limitations. Watersheds can provide accurate and closed contours with single pixel width. The main problem with watersheds is over-segmentation. Snakes, or active contour, can locate desired object boundaries automatically and dynamically from an initial contour, but the narrow capture range of initial contour has limited their utility. This paper presents a hybrid boundary detection algorithm to incorporate the advantages of both watersheds and snakes. An initial contour is firstly transformed into the maximum watershed contour it contains. The later are then input to the snake model and begins its evolvement to the interested object boundary. In our experiments, we compared this hybrid algorithm with traditional snake and gradient vector flow (GVF) snake. The results show that the hybrid scheme has larger capture range, faster calculation and robustness to noise.

FACE: fast active-contour curvature-based evolution

This paper presents an active contour model for fast object segmentation called FACE. A novel energy term that takes into account the computational complexity of the active contour is introduced together with related constraints and minimization procedure. The described process is based on the regularization and optimization of the active contour control points position. The trade-off between computational complexity and final contour accuracy is based on curvature estimation. The result is a fast active contour convergence towards desired object boundaries. This method can be combined with most of the other active contour approaches presented in literature, thanks to the independence between the computational minimization process and the classical active contour minimization process. The object segmentation procedure can be automatic or semiautomatic depending on the original image complexity. Several tests and experiments have been realized. Results show improvements in terms of computational time reduction when compared with other similar active contour models.