Automated PET-guided liver segmentation from low-contrast CT volumes using probabilistic atlas

The use of the functional PET information from PET-CT scans to improve liver segmentation from low-contrast CT data is yet to be fully explored. In this paper, we fully utilize PET information to tackle challenging liver segmentation issues including (1) the separation and removal of the surrounding muscles from liver region of interest (ROI), (2) better localization and mapping of the probabilistic atlas onto the low-contrast CT for a more accurate tissue classification, and (3) an improved initial estimation of the liver ROI to speed up the convergence of the expectation-maximization (EM) algorithm for the Gaussian distribution mixture model under the guidance of a probabilistic atlas. The primary liver extraction from the PET volume provides a simple mechanism to avoid the complicated pre-processing of feature extraction as used in the existing liver CT segmentation methods. It is able to guide the probabilistic atlas to better conform to the CT liver region and hence helps to overcome the challenge posed by liver shape variability. Our proposed method was evaluated against manual segmentation by experienced radiologists. Experimental results on 35 clinical PET-CT studies demonstrated that our method is accurate and robust in automated normal liver segmentation.     

Feature based fuzzy inference system for segmentation of low-contrast infrared ship images

Segmentation of infrared ship target is important for sea surveillance system. However, as a result of the deficiencies of infrared images, the segmentation of infrared ship image becomes a challenge. For the purpose of addressing this problem, a feature based infrared ship image segmentation method utilizing the fuzzy inference system is proposed. Firstly, the intensity feature is extracted by applying unimodal threshold, which could preserve the low-contrast pixels in the infrared images. Secondly, the local spatial feature is extracted by employing saliency detection, region growing and morphology processing, which could express the shape of the target. Thirdly, the global spatial feature is extracted by utilizing partial region growing and weighted distance transformation, which could suppress the background. Then these features are fuzzified using accommodative ways and prior knowledge. And in light of the fuzzy rules based upon expert knowledge, these fuzzified features are integrated in fuzzy inference system. Finally, the complete target could be directly segmented from the output of the fuzzy inference system. Experimental results illustrate that the proposed method could effectively extract more intact targets from the low-contrast infrared ship images. Additionally, the proposed method outperforms some existed segmentation methods.     

Automating image segmentation verification and validation by learning test oracles

An image segmentation algorithm delineates (an) object(s) of interest in an image. Its output is referred to as a segmentation. Developing these algorithms is a manual, iterative process involving repetitive verification and validation tasks. This process is time-consuming and depends on the availability of experts, who may be a scarce resource (e.g., medical experts). We propose a framework referred to as Image Segmentation Automated Oracle (ISAO) that uses machine learning to construct an oracle, which can then be used to automatically verify the correctness of image segmentations, thus saving substantial resources and making the image segmentation verification and validation task significantly more efficient. The framework also gives informative feedback to the developer as the segmentation algorithm evolves and provides a systematic means of testing different parametric configurations of the algorithm. During the initial learning phase, segmentations from the first few (optimally two) versions of the segmentation algorithm are manually verified by experts. The similarity of successive segmentations of the same images is also measured in various ways. This information is then fed to a machine learning algorithm to construct a classifier that distinguishes between consistent and inconsistent segmentation pairs (as determined by an expert) based on the values of the similarity measures associated with each segmentation pair. Once the accuracy of the classifier is deemed satisfactory to support a consistency determination, the classifier is then used to determine whether the segmentations that are produced by subsequent versions of the algorithm under test, are (in)consistent with already verified segmentations from previous versions. This information is then used to automatically draw conclusions about the correctness of the segmentations. We have successfully applied this approach to 3D segmentations of the cardiac left ventricle obtained from CT scans and have obtained promising results (accuracies of 95%). Even though more experiments are needed to quantify the effectiveness of the approach in real-world applications, ISAO shows promise in increasing the quality and testing efficiency of image segmentation algorithms.     

钢板表面低对比度微小缺陷图像增强和分割

目的 环境干扰及光学元件不稳定等因素往往会造成钢板表面图像照度不均,钢板表面的微小缺陷具有图像灰度不均、对比度低、形态微小等特点,给后续图像分析和缺陷识别带来因难。为此,提出一种钢板表面低对比度微小缺陷图像增强和分割算法,以消除照度不均并突出缺陷信息,从而有效分割缺陷目标。方法 采用小波-同态滤波算法进行图像增强处理,即先利用小波变换对图像进行分解,再基于同态滤波对小波低频系数进行图像灰度修正,同时对高频系数进行高通滤波,然后将处理后的小波低频系数和高频系数进行重构得到增强的图像,从而达到消除照度不均、增强缺陷细节信息的目的。最后利用最大类间方差法（Otsu法）确定自适应阈值提供给Canny算子进行边缘检测。结果 采用本文算法对钢板表面多类型低对比度表面微小缺陷进行研究,有效消除了光照不均;单一的Otsu阈值分割和Canny算子难以有效检测这些缺陷,而本文Otsu-Canny算法的正确检测率达96%。结论 采用小波-同态滤波进行图像增强处理后,再利用Otsu-Canny算法对钢板表面多类型、低对比度的微小缺陷进行边缘检测取得了良好效果。     

Automating data exchange in process choreographies

Communication between organizations is formalized as process choreographies in daily business. While the correct ordering of exchanged messages can be modeled and enacted with current choreography techniques, no approach exists to describe and automate the exchange of data between processes in a choreography using messages. This paper describes an entirely model-driven approach for BPMN introducing a few concepts that suffice to model data retrieval, data transformation, message exchange, and correlation – four aspects of data exchange. For automation, this work utilizes a recent concept to enact data dependencies in internal processes. We present a modeling guideline to derive local process models from a given choreography; their operational semantics allows to correctly enact the entire choreography from the derived models only including the exchange of data. Targeting on successful interactions, we discuss means to ensure correct process choreography modeling. Finally, we implemented our approach by extending the camunda BPM platform with our approach and show its feasibility by realizing all service interaction patterns using only model-based concepts.     

Automating change evolution in model-driven engineering

The escalating complexity of software and system models is making it difficult to rapidly explore the effects of a design decision. Automating such exploration with model transformation and aspect-oriented techniques can improve both productivity and model quality. The combination of model transformation and aspect weaving provides a powerful technology for rapidly transforming legacy systems from the high-level properties that models describe. Further, by applying aspect-oriented techniques and program transformation, small changes at the modeling level can trigger very large transformations at the source code level. Thus, model engineers can explore alternative configurations using an aspect weaver targeted for modeling tools and then use the models to generate program transformation rules for adapting legacy source code on a wide scale.     

Automating Support for Software Evolution in UML

Disciplined support for evolution of software artifacts is important in all phases of the software life-cycle. In order to achieve this support, a uniform underlying foundation for software evolution is necessary. While, in the past, reuse contracts have been proposed as such a formalism in a number of different domains, this paper generalises the formalism, and integrates it into the UML metamodel. As such, support for evolution becomes readily available for many kinds of UML models, ranging from requirements to the implementation phase.     

Automating unobtrusive personalized services in ambient media environments

In the age of ambient media, people are surrounded by lots of physical objects (media objects) for rendering the digital world in the natural environment. These media objects should interact with users in a way that is not disturbing for them. To address this issue, this work presents a design and automation strategy for augmenting the world around us with personalized ambient media services that behave in a considerate manner. That is, ambient services are capable of adjusting its obtrusiveness level (i.e., the extent to which each service intrudes the user’s mind) by using the appropriate media objects for each user’s situation.     

Mathematical-morphology-based edge detectors for detection of thin edges in low-contrast regions

A new edge detector based on mathematical morphology to preserve thin edge features in low-contrast regions as well as other apparent edges is proposed. A quad-decomposition edge enhancement process, a thresholding process, and a mask-based noise filtering process were developed and used to enhance thin edge features, extract edge points and filter out some meaningless noise points, respectively. Moreover, five bipolar oriented edge masks were also designed to remove most of the incorrectly detected edge features. Many experiments were conducted to evaluate and compare the performance of the proposed algorithm and several conventional ones. Pratt's figure of merit achieved by the proposed algorithm was as high as 92.5. The comprehensive experimental results show that the proposed algorithm is capable of preserving thin edge details successfully in low-contrast regions and is robust against noise.     

Automating experiments using semantic data in a bioinformatics grid

The transition from laboratory science to in silico e-science has facilitated a paradigmatic shift in the way we conduct modern science. We can use computationally based analytical models to simulate and investigate scientific questions such as those posed by high-energy physics and bioinformatics, yielding high-quality results and discoveries at an unprecedented rate. However, while experimental media have changed, the scientific methodologies and processes we choose for conducting experiments are still relevant. As in the lab environment, experimental methodology requires samples to undergo several processing stages. The staging of operations is what constitutes the in silico experimental process. The use of workflows formalizes earlier ad hoc approaches for representing experimental methodology. We can represent the stages of in silico experiments formally as a set of services to invoke.     

低对比度下的智能电表液晶屏外观检测研究

为了解决智能电表（Smart Meter）自动化检测系统中的关键技术问题,提出了在低对比度环境下智能电表液晶屏外观质量检测的处理方法。实现液晶屏区域的准确分割;采用基于小波变换的图像增强算法在低对比度环境下突出液晶屏上的字符信息;利用形态学梯度对字符信息进行重构,最终实现对液晶屏的外观质量检测。实验结果表明,该处理方法能够有效地解决低对比度环境下的智能电表液晶屏外观质量检测问题,检测可靠性高,具有较高工程应用价值。     

Defect detection of uneven brightness in low-contrast images using basis image representation

In this paper, we propose a machine vision approach for detecting local irregular brightness in low-contrast surface images and, especially, focus on mura (brightness non-uniformity) defects in liquid crystal display (LCD) panels. A mura defect embedded in a low-contrast surface image shows no distinct intensity from its surrounding region, and even worse, the sensed image may also present uneven illumination on the surface. All these make the mura defect detection in low-contrast surface images extremely difficult.A set of basis images derived from defect-free surface images are used to represent the general appearance of a clear surface. An image to be inspected is then constructed as a linear combination of the basis images, and the coefficients of the combination form the feature vector for discriminating mura defects from clear surfaces. In order to find minimum number of basis images for efficient and effective representation, the basis images are designed such that they are both statistically independent and spatially exclusive. An independent component analysis-based model that finds both the maximum negentropy for statistical independency and minimum spatial correlation for spatial redundancy is proposed to extract the representative basis images. Experimental results have shown that the proposed method can effectively detect various mura defects in low-contrast LCD panel images.     

Automating Test Case Selection in Model-Based Software Product Line Development

We address the problem of how to select test cases for products in a controlled model-based software product line development process. CVL, the common variability language, gives a framework for materialisation of product models from a given base model, variability model and resolution model. From such product models, software products can be derived. In practise, test case development for the product line often is independent from the product development. Therefore, the problem arises which test cases can be applied to which products. In particular, the question is whether a test case for one speci c product can be also used for a "similar" product. In this paper, we show how the expected outcome of a test case to a product in a model-based software product line development can be determined. That is, we give a procedure for assigning the outcome of a given test case on an arbitrary member of a software product line. We recall the relevant de nitions for software product line engineering, describe our approach, and demonstrate it with the example of a product line of super-automatic espresso machines.     

Automating case selection in the construction of a case library

An approach to case selection in the construction of a case library is presented in which the most useful case to be added to the library is identified by evaluation of the additional coverage provided by candidate cases. Cases that can be solved by the addition of a candidate case to the library are discovered in the approach by reversing the direction of case-based reasoning. The computational effort required in the evaluation of candidate cases can be reduced by focusing the search on a specified region of the problem space. The approach has been implemented in CaseMaker, an intelligent case-acquisition tool designed to support the authoring process in a case-based reasoner for estimation tasks.     

Automating the synthesis of decision procedures in a constructive metatheory

We present an approach to the automatic construction of decision procedures, via a detailed example in propositional logic. The approach adapts the methods of proof‐planning and the heuristics for induction to a new domain, that of metatheoretic procedures. This approach starts by providing an alternative characterisation of validity; the proofs of the correctness and completeness of this characterisation, and the existence of a decision procedure, are then amenable to automation in the way we describe. In this paper we identify a set of principled extensions to the heuristics for induction needed to tackle the proof obligations arising in the new problem domain and discuss their integration within the clam‐Oyster system. This revised version was published online in June 2006 with corrections to the Cover Date.     

Automating manufacturability evaluation in CAD systems through expert systems approaches

Design for Manufacturability (DFM) represents a new awareness of the importance of product design as an integral part of manufacturing activities. Good design guidelines exist in industry for frequently used manufacturing processes. These guidelines are systematic statements of good design practices, empirically derived over years of design and manufacturing experience. Ensuring that the given product design conforms to each of the guidelines specific to the selected process results in better manufacturability. To meet the objectives of the DFM approach, design and manufacturing planning activities have to be combined into a single engineering effort and applied througout the life cycle of a product. Computer-aided design (CAD) systems offer powerful features such as the ability to develop complex solid models and perform engineering analyses, including stress analysis, interobject interference, collision detection, and inertial analysis. However, a prominent limitation faced by designers in CAD systems is the lack of “intelligence.” Though designs could be developed, analyzed, and perfected from a functional viewpoint in CAD systems, manufacturability consideration may get little or no attention at all. As a result, product designs that are functionally sound may be developed at a high manufacturing cost. Thus, intelligence should be incorporated in CAD systems, whereby product designs could not only be developed and analyzed but also evaluated for cost and manufacturability. This study attempts to perform this task automatically in a CAD system using a knowledge-based approach: the manufacturability criteria are considered for milling and drilling operations performed on a computerized numerically controlled (CNC) milling machine. The results obtained from the application of the expert system suggest that the expert systems methodology is a feasible method for implementing manufacturability evaluation capability in CAD systems.     

An independent component analysis-based filter design for defect detection in low-contrast surface images

In this paper, we propose a convolution filtering scheme for detecting small defects in low-contrast uniform surface images and, especially, focus on the applications for backlight panels and glass substrates found in liquid crystal display (LCD) manufacturing. A defect embedded in a low-contrast surface image shows no distinct intensity from its surrounding region, and even worse, the sensed image may present uneven brightness on the surface. All these make the defect detection in low-contrast surface images extremely difficult.In this study, a constrained independent component analysis (ICA) model is proposed to design an optimal filter with the objective that the convolution filter will generate the most representative source intensity of the background surface without noise. The prior constraint incorporated in the ICA model confines the source values of all training image patches of a defect-free image within a small interval of control limits. In the inspection process, the same control parameter used in the constraint is also applied to set up the thresholds that make impulse responses of all pixels in faultless regions within the control limits, and those in defective regions outside the control limits. A stochastic evolutionary computation algorithm, particle swarm optimization (PSO), is applied to solve for the constrained ICA model. Experimental results have shown that the proposed method can effectively detect small defects in low-contrast backlight panels and LCD glass substrate images.     

Automating the Detection and Simplification of Junctions in Road Networks

A road network is cartographically drawn in varying levels of detail depending on the resolution or scale of the output graphic. In automated generalization, the challenge is in deriving generalized forms of a road network, appropriate for the intended target scale and to achieve this with minimum intervention from the user. This paper presents a method for the detection and simplification of road junctions as part of that process. Road junctions within the network are identified using a combination of spatial clustering and graph theory. The junctions are simplified using a combination of contractions and restrictions of the graph. Consideration is given to ways in which attribute and cartometric information can be used both to modify the behavior of the algorithm, and to influence the choice of other generalization algorithms. This algorithm is considered to be part of a growing number of generalization algorithms that can be used to derive generalized products from single detailed database. The success and limitations are discussed and future developments are proposed.     

Automating controller tuning for gas-turbine mini power stations in computer testing

We justify the application of mathematical modeling methods for electric power systems in order to automate the tuning of controllers in control systems of gas-turbine power stations constructed on the basis of converted aviation engines. We develop a method for tuning controllers in computer testing that uses dynamic modeling of electric load. We show that one has to take into account the arbitrary nature of the electric load.