Geodesic Active Regions Research Articles

Skull Segmentation and Reconstruction From Newborn CT Images Using Coupled Level Sets.

This study presents a new approach for segmentation and reconstruction of newborn's skull including bones, fontanels, and sutures from computed tomography (CT) images. The segmentation approach relies on propagation of a pair of interacting smooth surfaces based on geodesic active regions. These surfaces evolve in opposite directions; the exterior surface moves inward while the interior one moves in outward direction. The moving surfaces are forced to stop when arriving at the outer or the inner surface of the cranial bones using edge information. Since fontanels and sutures are not directly detectable in CT images, this method imposes specific propagation constraints for coupled interfaces to prevent the moving surfaces from intersecting each other and penetrating into the opposite region. Finally, an algorithm for level set initialization is introduced which enforces the evolving surfaces to conform to the shape of the head. The proposed method was evaluated using 18 neonatal CT images. The segmentation results achieved by the suggested method have been compared with manual segmentations by two different raters, performed to establish a reliable reference. The comparison of the two segmentation results using the Dice similarity coefficient and modified Hausdorff distance shows that the proposed approach provides satisfactory results.

Partitioned edge‐function‐scaled region‐based active contour (p‐ESRAC): Automated liver segmentation in multiphase contrast‐enhanced MRI

In multiphase contrast-enhanced magnetic resonance imaging (CE-MRI), liver segmentation is an important preprocessing step for the computer-aided evaluation of liver disease. However, because of the liver's irregular shape, proximity to surrounding organs, and large intensity variation, and peripheral contrast enhancement in the kidney, liver segmentation has been very challenging. This paper presents a novel hybrid active contour model and overall procedures that are specific to liver segmentation. The authors introduced an edge-function-scaled (weighted) region-based active contour model (ESRAC) and utilization of registered, multiphase sequences to address leakage-to-kidney and oversegmentation problems. The model incorporated weighted regional information with a compactly supported edge map, computed from a combination of images obtained during arterial and delayed phases, and it was coupled with a geodesic edge term. To cope with signal-inhomogeneity on MRI, all of the axial slices were partitioned into eight sectors with an angular span of 45°, centered on the inferior vena cava, each in the superior and inferior regions and the regional information regarding ESRAC was computed for each partition, henceforth the so-called partitioned ESRAC (p-ESRAC). Initialization of the active contour was performed by thresholding with a range of [200, +∞) and simple morphological operation during the delayed phase. At the end, to fill the holes in the segmented images caused by high gradients around the vasculature, noise, or outstanding texture features, iterative morphological operations were performed until convergence. The authors compared the segmentation accuracy of p-ESRAC to that with geodesic active contour, region-based active contour, geodesic active region, and localized region-based active contour using quantitative and visual assessments. In three-dimensional experimental studies conducted on 30 subjects (14 normal or benign cases and 16 malignant cases), compared with other active contours, p-ESRAC achieved the highest dice similarity coefficients of 93.9 ± 1.6% (normal) and 91.6 ± 2.2% (malignant), respectively. In addition, p-ESRAC resulted in the lowest false positive rates of 4.5 ± 3.2% (normal) and 7.9 ± 3.0% (malignant), demonstrating it to be the most effective in reducing oversegmentation. The partition scheme improved segmentation accuracy by 5.4 ± 9.2% (normal) and 22.2 ± 27.6% (malignant) of the true segmentation that was missed by ESRAC. Visual assessment confirmed that p-ESRAC prevented leakage of the segmentation results of the liver into the kidney. A novel active-contour model was developed, allowing for accurate liver segmentation on multiphase CE-MRI, with conditions that include signal inhomogeneity and weak boundary conditions. Such a technique could be useful for applications that involve computer-aided diagnosis of liver disease.

Initial condition for efficient mapping of level set algorithms on many-core architectures

In this paper, we investigated the effect of adding more small curves to the initial condition which determines the required number of iterations of a fast level set (LS) evolution. As a result, we discovered two new theorems and developed a proof on the worst case of the required number of iterations. Furthermore, we found that these kinds of initial conditions fit well to many-core architectures. To show this, we have included two case studies which are presented on different platforms. One runs on a graphical processing unit (GPU) and the other is executed on a cellular nonlinear network universal machine (CNN-UM). With the new initial conditions, the steady-state solutions of the LS are reached in less than eight iterations depending on the granularity of the initial condition. These dense iterations can be calculated very quickly on many-core platforms according to the two case studies. In the case of the proposed dense initial condition on GPU, there is a significant speedup compared to the sparse initial condition in all cases since our dense initial condition together with the algorithm utilizes the properties of the underlying architecture. Therefore, greater performance gain can be achieved (up to 18 times speedup compared to the sparse initial condition on GPU). Additionally, we have validated our concept against numerically approximated LS evolution of standard flows (mean curvature, Chan-Vese, geodesic active regions). The dice indexes between the fast LS evolutions and the evolutions of the numerically approximated partial differential equations are in the range of 0.99±0.003.

Automated segmentation of cerebral vasculature with aneurysms in 3DRA and TOF‐MRA using geodesic active regions: An evaluation study

To evaluate the suitability of an improved version of an automatic segmentation method based on geodesic active regions (GAR) for segmenting cerebral vasculature with aneurysms from 3D x-ray reconstruction angiography (3DRA) and time of flight magnetic resonance angiography (TOF-MRA) images available in the clinical routine. Three aspects of the GAR method have been improved: execution time, robustness to variability in imaging protocols, and robustness to variability in image spatial resolutions. The improved GAR was retrospectively evaluated on images from patients containing intracranial aneurysms in the area of the Circle of Willis and imaged with two modalities: 3DRA and TOF-MRA. Images were obtained from two clinical centers, each using different imaging equipment. Evaluation included qualitative and quantitative analyses of the segmentation results on 20 images from 10 patients. The gold standard was built from 660 cross-sections (33 per image) of vessels and aneurysms, manually measured by interventional neuroradiologists. GAR has also been compared to an interactive segmentation method: isointensity surface extraction (ISE). In addition, since patients had been imaged with the two modalities, we performed an intermodality agreement analysis with respect to both the manual measurements and each of the two segmentation methods. Both GAR and ISE differed from the gold standard within acceptable limits compared to the imaging resolution. GAR (ISE) had an average accuracy of 0.20 (0.24) mm for 3DRA and 0.27 (0.30) mm for TOF-MRA, and had a repeatability of 0.05 (0.20) mm. Compared to ISE, GAR had a lower qualitative error in the vessel region and a lower quantitative error in the aneurysm region. The repeatability of GAR was superior to manual measurements and ISE. The intermodality agreement was similar between GAR and the manual measurements. The improved GAR method outperformed ISE qualitatively as well as quantitatively and is suitable for segmenting 3DRA and TOF-MRA images from clinical routine.

Gaussian mixtures on tensor fields for segmentation: Applications to medical imaging

Abstract In this paper, we introduce a new approach for tensor field segmentation based on the definition of mixtures of Gaussians on tensors as a statistical model. Working over the well-known Geodesic Active Regions segmentation framework, this scheme presents several interesting advantages. First, it yields a more flexible model than the use of a single Gaussian distribution, which enables the method to better adapt to the complexity of the data. Second, it can work directly on tensor-valued images or, through a parallel scheme that processes independently the intensity and the local structure tensor, on scalar textured images. Two different applications have been considered to show the suitability of the proposed method for medical imaging segmentation. First, we address DT-MRI segmentation on a dataset of 32 volumes, showing a successful segmentation of the corpus callosum and favourable comparisons with related approaches in the literature. Second, the segmentation of bones from hand radiographs is studied, and a complete automatic–semiautomatic approach has been developed that makes use of anatomical prior knowledge to produce accurate segmentation results.

Texture Analysis and Segmentation Using Modulation Features, Generative Models, and Weighted Curve Evolution

In this work we approach the analysis and segmentation of natural textured images by combining ideas from image analysis and probabilistic modeling. We rely on AM-FM texture models and specifically on the Dominant Component Analysis (DCA) paradigm for feature extraction. This method provides a low-dimensional, dense and smooth descriptor, capturing essential aspects of texture, namely scale, orientation, and contrast. Our contributions are at three levels of the texture analysis and segmentation problems: First, at the feature extraction stage we propose a Regularized Demodulation Algorithm that provides more robust texture features and explore the merits of modifying the channel selection criterion of DCA. Second, we propose a probabilistic interpretation of DCA and Gabor filtering in general, in terms of Local Generative Models. Extending this point of view to edge detection facilitates the estimation of posterior probabilities for the edge and texture classes. Third, we propose the Weighted Curve Evolution scheme that enhances the Region Competition/ Geodesic Active Regions methods by allowing for the locally adaptive fusion of heterogeneous cues. Our segmentation results are evaluated on the Berkeley Segmentation Benchmark, and compare favorably to current state-of-the-art methods.

Unifying Statistical Classification and Geodesic Active Regions for Segmentation of Cardiac MRI

This paper presents a segmentation method that extends geodesic active region methods by the incorporation of a statistical classifier trained using feature selection. The classifier provides class probability maps based on class representative local features, and the geodesic active region formulation enables the partitioning of the image according to the region information. We demonstrate automatic segmentation results of the myocardium in cardiac late gadolinium-enhanced magnetic resonance imaging (CE-MRI) data using coupled level set curve evolutions, in which the classifier is incorporated both from a region term and from a shape term from particle filtering. The results show potential for clinical studies of scar tissue in late CE-MRI data.

Unsupervised Texture Segmentation via Applying Geodesic Active Regions to Gaborian Feature Space

In this paper, we propose a novel variational method for unsupervised texture segmentation. We use a Gabor filter bank to extract texture features. Some of the filtered channels form a multidimensional Gaborian feature space. To avoid deforming contours directly in a vector-valued space we use a Gaussian mixture model to describe the statistical distribution of this space and get the boundary and region probabilities. Then a framework of geodesic active regions is applied based on them. In the end, experimental results are presented, and show that this method can obtain satisfied boundaries between different texture regions. Keywords—Texture segmentation, Gabor filter, snakes, Geodesic active regions

Non-parametric geodesic active regions: Method and evaluation for cerebral aneurysms segmentation in 3DRA and CTA

Segmentation of vascular structures is a difficult and challenging task. In this article, we present an algorithm devised for the segmentation of such structures. Our technique consists in a geometric deformable model with associated energy functional that incorporates high-order multiscale features in a non-parametric statistical framework. Although the proposed segmentation method is generic, it has been applied to the segmentation of cerebral aneurysms in 3DRA and CTA. An evaluation study over 10 clinical datasets indicate that the segmentations obtained by our method present a high overlap index with respect to the ground-truth (91.13% and 73.31%, respectively) and that the mean error distance from the surface to the ground truth is close to the in-plane resolution (0.40 and 0.38 mm, respectively). Besides, our technique favorably compares to other alternative techniques based on deformable models, namely parametric geodesic active regions and active contours without edges.

Unsupervised Texture Segmentation Based on Geodesic Active Regions

This paper proposes an algorithm based on curve evolution for unsupervised texture segmentation. A multidimensional feature space is achieved by using a Gabor filter bank to extract texture features. To avoid deforming contours directly in a vector-valued space, a Gaussian mixture model (GMM) is used to describe the statistical distribution of the space and get the boundary and region probabilities. Then a framework of geodesic active regions is applied based on them to get final results. In the end, the experimental results demonstrate that this method can obtain satisfied boundaries between different texture regions.

Segmentation d'images ultrasonores par les régions actives géodésiques

This work is devoted to the segmentation of thrombosis in vivo venous ultrasound image. The evaluation of thrombosis size is of a big interest for the diagnosis of cardiovascular diseases. In this paper a new segmentation method for ultrasound images is developed, employing a geodesic active region model. This approach takes account both of boundary and region information using their statistical properties. The region information is approached with grey level distribution model and the estimation of the boundaries is based on the evolution of an initial curve using a level set method. The developed algorithm is tested on real B-mode ultrasound images, in vivo thrombus vein echotomographic images, to isolate the thrombus. The obtained experimental results have confirmed the ability of this approach to bound effectively the thrombus, and they pointed out also that the proposed method is adapted for ultrasound image segmentation.

Geodesic active regions and level set methods for motion estimation and tracking

Motion analysis in computer vision is a well-studied problem with numerous applications. In particular, the tasks of optical flow estimation and tracking are of increasing interest. In this paper, we propose a level set approach to address both aspects of motion analysis. Our approach relies on the propagation of smooth interfaces to perform tracking while using an incremental estimation of the motion models. Implicit representations are used to represent moving objects, and capture their motion parameters. Information from different sources like a boundary attraction term, a background subtraction component and a visual consistency constraint are considered. The Euler–Lagrange equations within a gradient descent method lead to a flow that deforms a set of initial curve towards the object boundaries as well an incremental robust estimator of their apparent motion. Partial extension of the proposed framework to address dense motion estimation and the case of moving observer is also presented. Promising results demonstrate the performance of the method.

Geodesic Active Regions: A New Framework to Deal with Frame Partition Problems in Computer Vision

This paper presents a novel variational framework for dealing with frame partition problems in computer vision by the propagation of curves. This framework integrates boundary- and region-based frame partition modules under a curve-based objective function, which aims at finding a set of minimal length curves that preserve three main properties: (i) they are regular and smooth, (ii) they are attracted by the boundary points (boundary-based information), (iii) and they create a partition that is optimal according to the expected region properties of the different hypotheses (region-based information). The defined objective function is minimized using a gradient descent method. According to the obtained motion equations, the set of initial curves is propagated toward the best partition under the influence of boundary- and region-based forces, and is constrained by a regularity force. The changes of topology are naturally handled thanks to the level set implementation. Furthermore, a coupled multiphase propagation that imposes the idea of mutually exclusive propagating curves and increases the robustness as well as the convergence rate is proposed. The proposed framework has been validated using three important applications in computer vision, the tasks of image and supervised texture segmentation in low-level vision and the task of motion estimation and tracking in motion analysis.

Geodesic Active Regions and Level Set Methods for Supervised Texture Segmentation

This paper presents a novel variational framework to deal with frame partition problems in Computer Vision. This framework exploits boundary and region-based segmentation modules under a curve-based optimization objective function. The task of supervised texture segmentation is considered to demonstrate the potentials of the proposed framework. The textured feature space is generated by filtering the given textured images using isotropic and anisotropic filters, and analyzing their responses as multi-component conditional probability density functions. The texture segmentation is obtained by unifying region and boundary-based information as an improved Geodesic Active Contour Model. The defined objective function is minimized using a gradient-descent method where a level set approach is used to implement the obtained PDE. According to this PDE, the curve propagation towards the final solution is guided by boundary and region-based segmentation forces, and is constrained by a regularity force. The level set implementation is performed using a fast front propagation algorithm where topological changes are naturally handled. The performance of our method is demonstrated on a variety of synthetic and real textured frames.