Ismail Ben Ayed

Multiregion level-set partitioning of synthetic aperture radar images

The purpose of this study is to investigate synthetic aperture radar (SAR) image segmentation into a given but arbitrary number of gamma homogeneous regions via active contours and level sets. The segmentation of SAR images is a difficult problem due to the presence of speckle which can be modeled as strong, multiplicative noise. The proposed algorithm consists of evolving simple closed planar curves within an explicit correspondence between the interiors of curves and regions of segmentation to minimize a criterion containing a term of conformity of data to a speckle model of noise and a term of regularization. Results are shown on both synthetic and real images.

Multiregion Image Segmentation by Parametric Kernel Graph Cuts

The purpose of this study is to investigate multiregion graph cut image partitioning via kernel mapping of the image data. The image data is transformed implicitly by a kernel function so that the piecewise constant model of the graph cut formulation becomes applicable. The objective function contains an original data term to evaluate the deviation of the transformed data, within each segmentation region, from the piecewise constant model, and a smoothness, boundary preserving regularization term. The method affords an effective alternative to complex modeling of the original image data while taking advantage of the computational benefits of graph cuts. Using a common kernel function, energy minimization typically consists of iterating image partitioning by graph cut iterations and evaluations of region parameters via fixed point computation. A quantitative and comparative performance assessment is carried out over a large number of experiments using synthetic grey level data as well as natural images from the Berkeley database. The effectiveness of the method is also demonstrated through a set of experiments with real images of a variety of types such as medical, synthetic aperture radar, and motion maps.

Variational and Level Set Methods in Image Segmentation

Image segmentation consists of dividing an image domain into disjoint regions according to a characterization of the image within or in-between the regions. Therefore, segmenting an image is to divide its domain into relevant components. The efficient solution of the key problems in image segmentation promises to enable a rich array of useful applications. The current major application areas include robotics, medical image analysis, remote sensing, scene understanding, and image database retrieval. The subject of this book is image segmentation by variational methods with a focus on formulations which use closed regular plane curves to define the segmentation regions and on a level set implementation of the corresponding active curve evolution algorithms. Each method is developed from an objective functional which embeds constraints on both the image domain partition of the segmentation and the image data within or in-between the partition regions. The necessary conditions to optimize the objective functional are then derived and solved numerically. The book covers, within the active curve and level set formalism, the basic two-region segmentation methods, multiregion extensions, region merging, image modeling, and motion based segmentation. To treat various important classes of images, modeling investigates several parametric distributions such as the Gaussian, Gamma, Weibull, and Wishart. It also investigates non-parametric models. In motion segmentation, both optical flow and the movement of real three-dimensional objects are studied.

Unsupervised Variational Image Segmentation/Classification Using a Weibull Observation Model

Studies have shown that the Weibull distribution can model accurately a wide variety of images. Its parameters index a family of distributions which includes the exponential and approximations of the Gaussian and the Raleigh models widely used in image segmentation. This study investigates the Weibull distribution in unsupervised image segmentation and classification by a variational method. The data term of the segmentation functional measures the conformity of the image intensity in each region to a Weibull distribution whose parameters are determined jointly with the segmentation. Minimization of the functional is implemented by active curves via level sets and consists of iterations of two consecutive steps: curve evolution via Euler-Lagrange descent equations and evaluation of the Weibull distribution parameters. Experiments with synthetic and real images are described which verify the validity of method and its implementation

Graph cuts with invariant object-interaction priors: application to intervertebral disc segmentation

This study investigates novel object-interaction priors for graph cut image segmentation with application to intervertebral disc delineation in magnetic resonance (MR) lumbar spine images. The algorithm optimizes an original cost function which constrains the solution with learned prior knowledge about the geometric interactions between different objects in the image. Based on a global measure of similarity between distributions, the proposed priors are intrinsically invariant with respect to translation and rotation. We further introduce a scale variable from which we derive an original fixed-point equation (FPE), thereby achieving scale-invariance with only few fast computations. The proposed priors relax the need of costly pose estimation (or registration) procedures and large training sets (we used a single subject for training), and can tolerate shape deformations, unlike template-based priors. Our formulation leads to an NP-hard problem which does not afford a form directly amenable to graph cut optimization. We proceeded to a relaxation of the problem via an auxiliary function, thereby obtaining a nearly real-time solution with few graph cuts. Quantitative evaluations over 60 intervertebral discs acquired from 10 subjects demonstrated that the proposed algorithm yields a high correlation with independent manual segmentations by an expert. We further demonstrate experimentally the invariance of the proposed geometric attributes. This supports the fact that a single subject is sufficient for training our algorithm, and confirms the relevance of the proposed priors to disc segmentation.

Left Ventricle Segmentation via Graph Cut Distribution Matching

We present a discrete kernel density matching energy for segmenting the left ventricle cavity in cardiac magnetic resonance sequences. The energy and its graph cut optimization based on an original first-order approximation of the Bhattacharyya measure have not been proposed previously, and yield competitive results in nearly real-time. The algorithm seeks a region within each frame by optimization of two priors, one geometric (distance-based) and the other photometric, each measuring a distribution similarity between the region and a model learned from the first frame. Based on global rather than pixelwise information, the proposed algorithm does not require complex training and optimization with respect to geometric transformations. Unlike related active contour methods, it does not compute iterative updates of computationally expensive kernel densities. Furthermore, the proposed first-order analysis can be used for other intractable energies and, therefore, can lead to segmentation algorithms which share the flexibility of active contours and computational advantages of graph cuts. Quantitative evaluations over 2280 images acquired from 20 subjects demonstrated that the results correlate well with independent manual segmentations by an expert.

Left ventricle segmentation in MRI via convex relaxed distribution matching.

A fundamental step in the diagnosis of cardiovascular diseases, automatic left ventricle (LV) segmentation in cardiac magnetic resonance images (MRIs) is still acknowledged to be a difficult problem. Most of the existing algorithms require either extensive training or intensive user inputs. This study investigates fast detection of the left ventricle (LV) endo- and epicardium surfaces in cardiac MRI via convex relaxation and distribution matching. The algorithm requires a single subject for training and a very simple user input, which amounts to a single point (mouse click) per target region (cavity or myocardium). It seeks cavity and myocardium regions within each 3D phase by optimizing two functionals, each containing two distribution-matching constraints: (1) a distance-based shape prior and (2) an intensity prior. Based on a global measure of similarity between distributions, the shape prior is intrinsically invariant with respect to translation and rotation. We further introduce a scale variable from which we derive a fixed-point equation (FPE), thereby achieving scale-invariance with only few fast computations. The proposed algorithm relaxes the need for costly pose estimation (or registration) procedures and large training sets, and can tolerate shape deformations, unlike template (or atlas) based priors. Our formulation leads to a challenging problem, which is not directly amenable to convex-optimization techniques. For each functional, we split the problem into a sequence of sub-problems, each of which can be solved exactly and globally via a convex relaxation and the augmented Lagrangian method. Unlike related graph-cut approaches, the proposed convex-relaxation solution can be parallelized to reduce substantially the computational time for 3D domains (or higher), extends directly to high dimensions, and does not have the grid-bias problem. Our parallelized implementation on a graphics processing unit (GPU) demonstrates that the proposed algorithm requires about 3.87 s for a typical cardiac MRI volume, a speed-up of about five times compared to a standard implementation. We report a performance evaluation over 400 volumes acquired from 20 subjects, which shows that the obtained 3D surfaces correlate with independent manual delineations. We further demonstrate experimentally that (1) the performance of the algorithm is not significantly affected by the choice of the training subject and (2) the shape description we use does not change significantly from one subject to another. These results support the fact that a single subject is sufficient for training the proposed algorithm.

Max-flow segmentation of the left ventricle by recovering subject-specific distributions via a bound of the Bhattacharyya measure

This study investigates fast detection of the left ventricle (LV) endo- and epicardium boundaries in a cardiac magnetic resonance (MR) sequence following the optimization of two original discrete cost functions, each containing global intensity and geometry constraints based on the Bhattacharyya similarity. The cost functions and the corresponding max-flow optimization built upon an original bound of the Bhattacharyya measure yield competitive results in nearly real-time. Within each frame, the algorithm seeks the LV cavity and myocardium regions consistent with subject-specific model distributions learned from the first frame in the sequence. Based on global rather than pixel-wise information, the proposed formulation relaxes the need of a large training set and optimization with respect to geometric transformations. Different from related active contour methods, it does not require a large number of iterative updates of the segmentation and the corresponding computationally onerous kernel density estimates (KDEs). The algorithm requires very few iterations and KDEs to converge. Furthermore, the proposed bound can be used for several other applications and, therefore, can lead to segmentation algorithms which share the flexibility of active contours and computational advantages of max-flow optimization. Quantitative evaluations over 2280 images acquired from 20 subjects demonstrated that the results correlate well with independent manual segmentations by an expert. Moreover, comparisons with a related recent active contour method showed that the proposed framework brings significant improvements in regard to accuracy and computational efficiency.

Graph cut segmentation with a global constraint: Recovering region distribution via a bound of the Bhattacharyya measure

This study investigates an efficient algorithm for image segmentation with a global constraint based on the Bhattacharyya measure. The problem consists of finding a region consistent with an image distribution learned a priori. We derive an original upper bound of the Bhattacharyya measure by introducing an auxiliary labeling. From this upper bound, we reformulate the problem as an optimization of an auxiliary function by graph cuts. Then, we demonstrate that the proposed procedure converges and give a statistical interpretation of the upper bound. The algorithm requires very few iterations to converge, and finds nearly global optima. Quantitative evaluations and comparisons with state-of-the-art methods on the Microsoft GrabCut segmentation database demonstrated that the proposed algorithm brings improvements in regard to segmentation accuracy, computational efficiency, and optimality. We further demonstrate the flexibility of the algorithm in object tracking.

A Statistical Overlap Prior for Variational Image Segmentation

This study investigates variational image segmentation with an original data term, referred to as statistical overlap prior, which measures the conformity of overlap between the nonparametric distributions of image data within the segmentation regions to a learned statistical description. This leads to image segmentation and distribution tracking algorithms that relax the assumption of minimal overlap and, as such, are more widely applicable than existing algorithms. We propose to minimize active curve functionals containing the proposed overlap prior, compute the corresponding Euler-Lagrange curve evolution equations, and give an interpretation of how the overlap prior controls such evolution. We model the overlap, measured via the Bhattacharyya coefficient, with a Gaussian prior whose parameters are estimated from a set of relevant training images. Quantitative and comparative performance evaluations of the proposed algorithms over several experiments demonstrate the positive effects of the overlap prior in regard to segmentation accuracy and convergence speed.