Weak Boundaries Research Articles

A Markov Random Field and Adaptive Regularization Embedded Level Set Segmentation Model Solving by Graph Cuts

This paper presents a novel Markov random field (MRF) and adaptive regularization embedded level set model for robust image segmentation and uses graph cuts optimization to numerically solve it. Firstly, a special MRF-based energy term in the form of level set formulation is constructed for strong local neighborhood modeling. Secondly, a regularization constraint with adaptive properties is imposed onto the proposed model with the following purposes: reduce the influence of noise, force the power exponent of the regularization process to change adaptively with image coordinates, and ensure the active contour does not pass through the weak object boundaries. Thirdly, graph cuts optimization is used to implement the numerical solution of the proposed model to obtain extremely fast convergence performance. The extensive and promising experimental results on wide variety of images demonstrate the excellent performance of the proposed method in both segmentation accuracy and convergence rate.

Boundary segmentation based on modified random walks for vascular Doppler optical coherence tomography images

Vascular Doppler optical coherence tomography (DOCT) images with weak boundaries are usually difficult for most algorithms to segment. We propose a modified random walk (MRW) algorithm with a novel regularization for the segmentation of DOCT vessel images. Based on MRW, we perform automatic boundary detection of the vascular wall from intensity images and boundary extraction of the blood flowing region from Doppler phase images. Dice, sensitivity, and specificity coefficients were adopted to verify the segmentation performance. The experimental study on DOCT images of the mouse femoral artery showed the effectiveness of our proposed method, yielding three-dimensional visualization and quantitative evaluation of the vessel.

Transformational leadership and polychronicity as antecedents of work-home boundaries

PurposeThis paper aims to bring together leadership and boundary theories to conceptualize how transformational leadership behaviors and polychronicity might impact our life satisfaction through the boundaries we maintain around our work and home domains. It is argued that transformational behavior of the supervisor will be negatively associated with the strength of boundary that the followers construct around their home domain but will be positively associated with the boundary strength around the work domain. Additionally, it is posited that polychronicity will be negatively associated with the boundary strengths at home and at work but will be positively related with life satisfaction.Design/methodology/approachThe concepts of leadership, polychronicity and work-home boundaries are explained, and logical arguments are presented to develop a conceptual framework incorporating these constructs.FindingsThe conceptual exploration of this study denotes that transformational leadership of supervisors would positively impact the life satisfaction of employees, directly as well as through the boundaries around their work and home domains. Specifically, transformational leadership behaviors of supervisors are expected to be associated with followers’ strong work boundaries but with weak home boundaries. At the same time, highly polychronic individuals are expected to keep weak boundaries around their work and home domains and to have higher life satisfaction.Research limitations/implicationsThe conceptualization of this paper focused on constructs that have not been linked before in one framework. As such, empirical research is suggested to validate the model.Practical implicationsUnderstanding the antecedents of life satisfaction of employees is of crucial interest to managers at workplaces. It is suggested that managers should engage employees in co-constructing their work and home boundaries, with a view to increasing the life satisfaction of employees. Further, it seems possible that the hitherto prevalent practice of fostering strong boundaries at work may be hindering the well-being of employees.Social implicationsVariables active at workplaces, such as polychronicity, also affect the non-work domain and, thereby, the life satisfaction of employees.Originality/valueThrough this conceptualization, this paper has attempted to fill a gap in boundary management literature by linking transformational leadership of the supervisor to the work and home boundaries of the followers. This study also situates polychronicity as an important player in the work-home interface and life satisfaction of employees. This research links transformational leadership, polychronicity, boundary management and life satisfaction in one model. It thereby contributes to the leadership literature and extends the nomological network of work-non-work boundary management.

Automatic segmentation of vertebrae in 3D CT images using adaptive fast 3D pulse coupled neural networks.

Two systems are presented for segmentation of vertebrae in a 3D computed tomography (CT) image. The first method extracts seven features from each voxel and uses a multi-layer perceptron neural network (MLPNN) to classify the voxel as vertebrae or background. In the second method, the segmentation is completed in two steps: first, a newly developed adaptive pulse coupled neural network (APCNN) directly applied to a given image segments vertebrae, then the result is refined using a median filter. In the developed APCNN, the values for the user-defined parameters of the pulse coupled neural networks (PCNN) are adaptively adjusted for each image individually, instead of using one value for all images as in conventional PCNN. The performance of both systems in terms of Dice index (DI) was evaluated and compared against the state-of-the-art segmentation methods using seventeen clinical and standard CT images. Overall, both systems demonstrated statistically similar and promising performance with average DI > 95%. Compared to existing PCNN-based segmentation algorithms, the accuracy of the proposed APCNN improved by 29.3% on average. The developed APCNN-based system is more accurate than MLPNN-based system and existing PCNN-based algorithms in segmentation of vertebrae with blurred and weak boundaries and in the images contaminated by salt- and- pepper noise. In terms of computation time, the APCNN-based system is 16 times faster than the MLPNN-based system. Consequently, the presented APCNN-based algorithm is both accurate and fast and could be used in clinical environment for segmentation of vertebrae in 3D CT images.

Earth dynamics and the development of plate tectonics.

This volume brings together contributions from the Royal Society Discussion Meeting on ‘Earth dynamics and the development of plate tectonics' held in March 2018. Other planets in the Solar System do not exhibit plate tectonics, so why does it occur on Earth, how did it develop and when did Earth adopt this tectonic regime? In evaluating evidence from the geological record, it is critical to distinguish between local and global phenomena in a discussion of the why, how and when of the transition to plate tectonics on Earth. Thus, evidence of local or episodic subduction in the geological record, for example, does not necessarily provide evidence for the development of a sustainable global network of mobile belts that forms the basis for a mosaic of plates. The tectonic regime at any point in the evolution of a planet appears to depend on the initial conditions set by crystallization of the last magma ocean. These conditions determine the thermal state—‘hot’ or ‘cold’—at the start of sub-solidus mantle convection, which is subsequently driven by the relative contributions of basal and internal heating to the mantle through time. Plate tectonics is linked to the ability of mantle convection to form plate boundaries, which requires localized weakening of the lithospheric lid. How and when did this become possible? Consideration of the tectonic regime on Venus, which may be an analogue for the early tectonic development of Earth, evidence from the rock record, rock deformation experiments, geodynamic models extrapolated back to the thermal conditions appropriate to the Archaean, and geochemical models for the development and growth of the continental crust have led to the currently popular view that plate tectonics developed from a stagnant lid regime. However, if mantle convection is able to form weak plate boundaries at the higher mantle temperatures expected during the …

The dependence of planetary tectonics on mantle thermal state: applications to early Earth evolution.

For plate tectonics to operate on a planet, mantle convective forces must be capable of forming weak, localized shear zones in the lithosphere that act as plate boundaries. Otherwise, a planet's mantle will convect in a stagnant lid regime, where subduction and plate motions are absent. Thus, when and how plate tectonics initiated on the Earth is intrinsically tied to the ability of mantle convection to form plate boundaries; however, the physics behind this process are still uncertain. Most mantle convection models have employed a simple pseudoplastic model of the lithosphere, where the lithosphere 'fails' and develops a mobile lid when stresses in the lithosphere reach the prescribed yield stress. With pseudoplasticity high mantle temperatures and high rates of internal heating, conditions relevant for the early Earth, impede plate boundary formation by decreasing lithospheric stresses, and hence favour a stagnant lid for the early Earth. However, when a model for shear zone formation based on grain size reduction is used, early Earth thermal conditions do not favour a stagnant lid. While lithosphere stress drops with increasing mantle temperature or heat production rate, the deformational work, which drives grain size reduction, increases. Thus, the ability of convection to form weak plate boundaries is not impeded by early Earth thermal conditions. However, mantle thermal state does change the style of subduction and lithosphere mobility; high mantle temperatures lead to a more sluggish, drip-like style of subduction. This 'sluggish lid' convection may be able to explain many of the key observations of early Earth crust formation processes preserved in the geologic record. Moreover, this work highlights the importance of understanding the microphysics of plate boundary formation for assessing early Earth tectonics, as different plate boundary formation mechanisms are influenced by mantle thermal state in fundamentally different ways.This article is part of a discussion meeting issue 'Earth dynamics and the development of plate tectonics'.

X-The Effect of Microstructure on the Corrosion Fatigue Property of A7N01P-T4 Aluminum Alloy Welding Joints

The corrosion fatigue short crack propagation (CFSCP) behavior of A7N01P-T4 Al alloy welded joints in 3.5 wt% NaCl solution has been investigated. The test results indicate that the CFSCP followed a cyclical type of growth. Microscopic study shows that almost all second-phase particles are distributed along the grain boundary areas. These particles were easily dissolved during the corrosion fatigue test, resulting in weak grain boundaries. Therefore, the fatigue short crack will grow along the winding grain boundaries. While the second-phase particles on the grain boundaries were the main factor to cause the intergranular crack. Transgranular cracking may occur to the coarse grains in the matrix, which indicate that grain size also has a strong influence on the CFSCP behavior of A7N01P-T4 Al alloy.

Modulation of the following segment effect on English coronal stop deletion by syntactic boundaries

Variable deletion of word-final coronal stops in English is strongly conditioned by whether the following segment is a consonant or a vowel. This paper uses corpus data to show that this following segment effect is weaker across strong syntactic boundaries (such as between independent matrix clauses) than across weak syntactic boundaries (between a verb and its direct object). This result is argued to be compatible with the Production Planning Hypothesis: that following context effects on phonological variation can be bled by failure to encode the next word in time for it to influence an alternation. Further, the interaction of boundary and following segment is asymmetric; the deletion-inhibiting effect of a following vowel is significantly weakened across stronger syntactic boundaries, while the deletion rate before consonants is more stable across different boundary types. The asymmetry provides new evidence in favor of syllabification-based explanations for why coronal stop deletion exhibits the following segment effect.

In-situ quantification of intra and intergranular deformation in pure magnesium using full-field measurements at low and high strain rates

Due to the presence of weak grain boundaries as well as significantly coarse grain structure with minimal deformability, grain boundary cracking is almost an inevitable source of failure when a cast magnesium-based alloy is deformed at low homologous temperatures. The main objective in this work is to quantitatively investigate the contribution of inter- and intragranular deformation to the macroscale deformability and ductility of nominally pure as-cast magnesium subjected to quasi-static and dynamic loading. The proposed mesoscale full-field measurement approach is first presented and verified through measurements carried out to investigate deformation and grain boundary cracking in cast magnesium subjected to quasi-static loading. The method is then extended into the analysis of mesoscale deformation and failure under dynamic loading conditions using an experimental setup consisting of a split Hopkinson pressure bar (SHPB) and a high-speed imaging system. In both cases, the effect of the initial grain configuration on the local deformation response of Mg is investigated. The results indicate that the contribution of grain boundary region deformation to the total deformation exerted on the Mg samples is significant and depends on the initial grain configuration. Also, the strain rate sensitivity of the material is found to be dominated by the material deformation in the vicinity of grain boundaries.

A Cascaded Deep Convolutional Neural Network for Joint Segmentation and Genotype Prediction of Brainstem Gliomas.

Automatic segmentation of brainstem gliomas and prediction of genotype (H3 K27M) mutation status based on magnetic resonance (MR) images are crucial but challenging tasks for computer-aided diagnosis in neurosurgery. In this paper, we present a novel cascaded deep convolutional neural network (CNN) to address these two challenging tasks simultaneously. Our novel segmentation task contains two feature-fusion modules: the Gaussian-pyramid multiscale input features-fusion technique and the brainstem-region feature enhancement. The aim is to resolve very difficult problems in brainstem glioma segmentation. Our prediction model combines CNN features and support-vector-machine classifier to automatically predict genotypes without region-of-interest labeled-MR images and is learned jointly with the segmentation task. First, Gaussian-pyramid multiscale input feature fusion is added to our glioma-segmentation task to solve the problems of size variety and weak brainstem-gliomas boundaries. Second, the two feature-fusion modules provide both local and global contexts to retain higher frequency details for sharper tumor boundaries, handling the problem of the large variation of tumor shape, and volume resolution. Experiments demonstrate that our cascaded CNN method achieves not only a good tumor segmentation result with a high Dice similarity coefficient of 77.03%, but also a competitive genotype prediction result with an average accuracy of 94.85% upon fivefold cross-validation.

Level set evolution driven by optimized area energy term for image segmentation

As a classic and famous active contour model for image segmentation, distance regularized level set evolution method avoids the process of re-initialization and can segment images flexibly, but it is easy to leak from objects with weak boundaries and fall into false boundaries. In this paper, an improved level set evolution model is proposed, in which an optimized area energy term combining a region growing matrix and an adaptive boundary indicator function is added to effectively detect boundaries for images with several adjacent targets and accelerate convergence at the same time. With an adaptive boundary indicator function involving a threshold defined by the standard deviation of images to be detected, this model can cross false boundaries and implement a correct segmentation for low contrast images. Meanwhile, the double-well potential function is optimized to make the model more stable. Experimental results on images of different objects have proved that the proposed model not only improves the precision of locating boundaries but also reduces the computational cost and works a stronger robustness than some other edge-based active contour models.

Ultrafast Acoustofluidic Exfoliation of Stratified Crystals.

While the remarkable properties of 2D crystalline materials offer tremendous opportunities for their use in optics, electronics, energy systems, biotechnology, and catalysis, their practical implementation largely depends critically on the ability to exfoliate them from a 3D stratified bulk state. This goal nevertheless remains elusive, particularly in terms of a rapid processing method that facilitates high yield and dimension control. An ultrafast multiscale exfoliation method is reported which exploits the piezoelectricity of stratified materials that are noncentrosymmetric in nature to trigger electrically-induced mechanical failure across weak grain boundaries associated with their crystal domain planes. In particular, it is demonstrated that microfluidic nebulization using high frequency acoustic waves exposes bulk 3D piezoelectric crystals such as molybdenum disulphide (MoS2 ) and tungsten disulphide (WS2 ) to a combination of extraordinarily large mechanical acceleration (≈108 m s-2 ) and electric field (≈107 V m-1 ). This results in the layered bulk material being rapidly cleaved into pristine quasi-2D-nanosheets that predominantly comprise single layers, thus constituting a rapid and high throughput chip-scale method that opens new possibilities for scalable production and spray coating deposition.

Level set evolution of biomedical MRI and CT scan images using optimized fuzzy region clustering

In recent years, image segmentation based on level set formulations was encompassed by proficiently implementing various image processing applications, especially in case of reformative models for medical image segmentation. Existing level set methods under this criterion are not up to the mark in terms of noise, weak boundaries, and inhomogeneity. In this paper, we put forward a new formulation for selective segmentation with level set model using optimised fuzzy region clustering and implementation is carried out in two stages. In first, optimised fuzzy region clustering (OFR) is employed in which particle swarm optimisation technique is utilised at the initialisation of FCM clustering to obtain optimal cluster centres and then it is incorporated with region competition. While in second, implementing OFR clustering using level set methods. The proposed formulation is successfully implemented on some contemporary medicinal images. It is capable to identify the weak boundaries and segment the desired components of an image such as white substance, grey substance, cerebrospinal fluid, bone sarcoma, breast cancer and Alzheimer’s disease, etc. The visual results and quantitative analysis show its effectiveness, superiority and accuracy over the existing formulations.

Transition of creep damage region in dissimilar welds between Inconel 740H Ni-based superalloy and P92 ferritic/martensitic steel

Characterization of microstructures and creep fracture characteristics of dissimilar welds between Ni-based Inconel 740H superalloy and ferritic/martensitic P92 steel has been investigated. The welds were produced by shielded metal arc (SMA) welding process with the AWS A5.11 Class ENiCrFe-3 filler metal, commonly known as Inconel 182 superalloy. Postweld heat treatment (PWHT) at 760 °C for 4 h was conducted to temper the martensite in heat-affected zone (HAZ) of P92 and to form γ′ strengthener in Inconel 740H. The deposited Inconel 182 austenitic weld metal had a columnar microstructure, and grew epitaxially from the Inconel 740H base metal. The weld interface between P92 and weld metal was characterized by the discrete line with a minimal inter-diffusion, where the fresh untempered martensite was found to be formed during PWHT due to higher Ni contents diffused from Inconel 182 into P92. The P92 base metal and Inconel 182 weld metal displayed low hardness values (~240 Hv), and the sharp hardness increase was detected at coarse-grained HAZ of P92 while the hardness minimum occurred at the fine-grained HAZ (FGHAZ). Fracture location after creep was found to shift from the P92-sided fusion line to the FGHAZ of P92 with increasing creep temperature. The carbon migration from the P92 into the weld metal was not significant at lower creep temperature (600 °C), where the crack initiation at the P92-sided fusion line appeared to be related with a significant strain incompatibility across the fusion line. At both 650 °C and 700 °C where diffusion-controlled creep was more pronounced, the type IV cracking was observed. This may be attributed to the strain localization at the weak grain boundaries of FGHAZ due to the smaller grain size as well as the lack of grain boundary strengthening by carbides.

Fully automatic liver segmentation in CT images using modified graph cuts and feature detection

PurposeLiver segmentation from CT images is a fundamental step in trajectory planning for computer-assisted interventional surgery. In this paper, we present a fully automatic procedure using modified graph cuts and feature detection for accurate and fast liver segmentation. MethodsThe initial slice and seeds of graph cuts are automatically determined using an intensity-based method with prior position information. A contrast term based on the similarities and differences of local organs across multi-slices is proposed to enhance the weak boundaries of soft organs and to prevent over-segmentation. The term is then integrated into the graph cuts for automatic slice segmentation. Patient-specific intensity and shape constraints of neighboring slices are also used to prevent leakage. Finally, a feature detection method based on vessel anatomical information is proposed to eliminate the adjacent inferior vena cava with similar intensities. ResultsWe performed experiments on 20 Sliver07, 20 3Dircadb datasets and local clinical datasets. The average volumetric overlap error, volume difference, symmetric surface distance and volume processing time were 5.3%, −0.6%, 1.0 mm, 17.8 s for the Sliver07 dataset and 8.6%, 0.7%, 1.6 mm, 12.7 s for the 3Dircadb dataset, respectively. ConclusionsThe proposed method can effectively extract the liver from low contrast and complex backgrounds without training samples. It is fully automatic, accurate and fast for liver segmentation in clinical settings.

Robust active contour via additive local and global intensity information based on local entropy

Active contour-based image segmentation can be a very challenging task due to many factors such as high intensity inhomogeneity, presence of noise, complex shape, weak boundaries objects, and dependence on the position of the initial contour. We propose a level set-based active contour method to segment complex shape objects from images corrupted by noise and high intensity inhomogeneity. The energy function of the proposed method results from combining the global intensity information and local intensity information with some regularization factors. First, the global intensity term is proposed based on a scheme formulation that considers two intensity values for each region instead of one, which outperforms the well-known Chan–Vese model in delineating the image information. Second, the local intensity term is formulated based on local entropy computed considering the distribution of the image brightness and using the generalized Gaussian distribution as the kernel function. Therefore, it can accurately handle high intensity inhomogeneity and noise. Moreover, our model is not dependent on the position occupied by the initial curve. Finally, extensive experiments using various images have been carried out to illustrate the performance of the proposed method.

A Dynamic Graph Cuts Method with Integrated Multiple Feature Maps for Segmenting Kidneys in 2D Ultrasound Images

Automatic segmentation of kidneys in ultrasound (US) images remains a challenging task because of high speckle noise, low contrast, and large appearance variations of kidneys in US images. Because texture features may improve the US image segmentation performance, we propose a novel graph cuts method to segment kidney in US images by integrating image intensity information and texture feature maps. We develop a new graph cuts-based method to segment kidney US images by integrating original image intensity information and texture feature maps extracted using Gabor filters. To handle large appearance variation within kidney images and improve computational efficiency, we build a graph of image pixels close to kidney boundary instead of building a graph of the whole image. To make the kidney segmentation robust to weak boundaries, we adopt localized regional information to measure similarity between image pixels for computing edge weights to build the graph of image pixels. The localized graph is dynamically updated and the graph cuts-based segmentation iteratively progresses until convergence. Our method has been evaluated based on kidney US images of 85 subjects. The imaging data of 20 randomly selected subjects were used as training data to tune parameters of the image segmentation method, and the remaining data were used as testing data for validation. Experiment results demonstrated that the proposed method obtained promising segmentation results for bilateral kidneys (average Dice index = 0.9446, average mean distance = 2.2551, average specificity = 0.9971, average accuracy = 0.9919), better than other methods under comparison (P < .05, paired Wilcoxon rank sum tests). The proposed method achieved promising performance for segmenting kidneys in two-dimensional US images, better than segmentation methods built on any single channel of image information. This method will facilitate extraction of kidney characteristics that may predict important clinical outcomes such as progression of chronic kidney disease.

Automated Segmentation of Left Ventricle Using Local and Global Intensity Based Active Contour and Dynamic Programming

The aim of this work is to develop an improved region based active contour and dynamic programming based method for accurate segmentation of left ventricle (LV) from multi-slice cine short axis cardiac magnetic resonance (MR) images. Intensity inhomogeneity and weak object boundaries present in MR images hinder the segmentation accuracy. The proposed active contour model driven by a local Gaussian distribution fitting (LGDF) energy and an auxiliary global intensity fitting energy improves the accuracy of endocardial boundary detection. The weightage of the global energy fitting term is dynamically adjusted using a spatially varying weight function. Dynamic programming scheme proposed for the segmentation of epicardium considers the myocardium probability map and a distance weighted edge map in the cost matrix. Radial distance weighted technique and conical geometry are employed for segmenting the basal slices with left ventricle outflow tract (LVOT) and most apical slices. The proposed method is validated on a public dataset comprising 45 subjects from medical image computing and computer assisted interventions (MICCAI) 2009 segmentation challenge. The average percentage of good endocardial and epicardial contours detected is about 99%, average perpendicular distance of the detected good contours from the manual reference contours is 1.95 mm, and the dice similarity coefficient between the detected contours and the reference contours is 0.91. Correlation coefficient and the coefficient of determination between the ejection fraction measurements from manual segmentation and the automated method are respectively 0.978 1 and 0.956 7, for LV mass these values are 0.924 9 and 0.855 4. Statistical analysis of the results reveals a good agreement between the clinical parameters determined manually and those estimated using the automated method.

An Improved Adaptive Level Set Method for Image Segmentation

In order to improve the accuracy of image segmentation, an improved adaptive level set method is proposed based on level set evolution without re-initialization method and adaptive distance preserving level set evolution method. A new definition of weight coefficient in evolution equations is the main innovation of this paper. The improved method can detect certain object boundaries, interior and exterior contours of an object, edges of multi-objects and weak boundaries of an object by synthetic and real images numerical experiments. Numerical results show that the improved adaptive level set method has faster segmentation speed and higher segmentation accuracy compared with the previous two methods, especially in weak boundaries and edges of multi-objects segmentation problems.

A variational level set method image segmentation model with application to intensity inhomogene magnetic resonance imaging

ABSTRACT Background and Objectives: In this article, we propose an image segmentation model based on Chan-Vese (CV) for image segmentation. By taking into account the local features of the image, the new proposed model can successfully segment images with intensity nonuniformity. Materials and Methods: We quantitatively compare our method with other two state-of-the-art algorithms, namely, CV model and local binary fitting (LBF) model in segmenting synthetic MR images with the ground truth from BrainWeb; the data can be available at: https://www.mni/mcgill.ca/brainweb/. For segmenting the missing and weak boundaries, to deal with the intensity inhomogeneity, based on the LBF model, we introduced the convex total variation regularization term, for explicit smoothing of the level set function ø. The evolution equation will be solved through the level set method of calculus of variations. Results: In the experimental processing, we use some real images and magnetic resonance imaging brain images as the experimental images, to validate the stabilization of algorithm. The experimental results on comprehensive and sincerity images show the outstanding of our proposed model with reference to stabilization and availability. Conclusions: We propose a new segmentation local information of an image and introduce a new regularization functional is to keep the level set function smooth. Finally, various experimental results on real and low-contrast image, showing which is a powerful type of images, including some that would be difficult to segment with gradient-based methods. In addition, the advantages of the proposed model are better than CV model and the LBF model. Our new model can effectively segment a real image.