A pipeline for computer aided polyp detection

We present a novel pipeline for computer-aided detection (CAD) of colonic polyps by integrating texture and shape analysis with volume rendering and conformal colon flattening. Using our automatic method, the 3D polyp detection problem is converted into a 2D pattern recognition problem. The colon surface is first segmented and extracted from the CT data set of the patient's abdomen, which is then mapped to a 2D rectangle using conformal mapping. This flattened image is rendered using a direct volume rendering technique with a translucent electronic biopsy transfer function. The polyps are detected by a 2D clustering method on the flattened image. The false positives are further reduced by analyzing the volumetric shape and texture features. Compared with shape based methods, our method is much more efficient without the need of computing curvature and other shape parameters for the whole colon surface. The final detection results are stored in the 2D image, which can be easily incorporated into a virtual colonoscopy (VC) system to highlight the polyp locations. The extracted colon surface mesh can be used to accelerate the volumetric ray casting algorithm used to generate the VC endoscopic view. The proposed automatic CAD pipeline is incorporated into an interactive VC system, with a goal of helping radiologists detect polyps faster and with higher accuracy.     

F-FDG PET imaging analysis for computer aided Alzheimer’s diagnosis

Finding sensitive and appropriate technologies for non-invasive observation and early detection of Alzheimer’s disease (AD) is of fundamental importance to develop early treatments. In this work we develop a fully automatic computer aided diagnosis (CAD) system for high-dimensional pattern classification of baseline ¹⁸F-FDG PET scans from Alzheimer’s disease neuroimaging initiative (ADNI) participants. Image projection as feature space dimension reduction technique is combined with an eigenimage based decomposition for feature extraction, and support vector machine (SVM) is used to manage the classification task. A two folded objective is achieved by reaching relevant classification performance complemented with an image analysis support for final decision making. A 88.24% accuracy in identifying mild AD, with 88.64% specificity, and 87.70% sensitivity is obtained. This method also allows the identification of characteristic AD patterns in mild cognitive impairment (MCI) subjects.     

肿瘤细胞辅助诊断系统的研究

介绍了一种用于宫颈癌早期普查的辅助诊断系统。与传统的对单个癌细胞排序的诊断系统不同,本系统是根据每幅图片中癌细胞核的综合参数直接对自动采集的整幅彩色细胞图片进行排序。综合参数主要利用癌细胞核形态学和色度学的特征以及黑区域消除与填补算法等图像处理技术获得。临床试验结果表明:本系统有效地提高了医生的诊断效率和准确率。     

A pentagonal surface patch for computer aided geometric design

A vector valued interpolation scheme for a pentagon is described which is compatible with surface patches which have a rectangular domain of definition. Such a scheme could be useful in computer-aided geometric design problems, where a pentagonal patch occurs within a rectangular patch framework.     

一种新型的计算机审计模型*

在分析计算机审计的特点及需求的基础上,借鉴数据仓库、OLAP、数据挖掘等技术的优势,提出了一种新型的计算机审计模型.该模型克服了传统审计软件的不足,有效地解决了面对海量数据的审计等问题,提高了审计的效率及质量.最后还对智能审计的发展作了一定的探讨.     

A random forest classifier for lymph diseases

Machine learning-based classification techniques provide support for the decision-making process in many areas of health care, including diagnosis, prognosis, screening, etc. Feature selection (FS) is expected to improve classification performance, particularly in situations characterized by the high data dimensionality problem caused by relatively few training examples compared to a large number of measured features. In this paper, a random forest classifier (RFC) approach is proposed to diagnose lymph diseases. Focusing on feature selection, the first stage of the proposed system aims at constructing diverse feature selection algorithms such as genetic algorithm (GA), Principal Component Analysis (PCA), Relief-F, Fisher, Sequential Forward Floating Search (SFFS) and the Sequential Backward Floating Search (SBFS) for reducing the dimension of lymph diseases dataset. Switching from feature selection to model construction, in the second stage, the obtained feature subsets are fed into the RFC for efficient classification. It was observed that GA-RFC achieved the highest classification accuracy of 92.2%. The dimension of input feature space is reduced from eighteen to six features by using GA.     

Internet-enabled computer aided design

Advances in computer networks are rapidly changing the way engineering is performed, making computer-aided design the front door to a web of interconnected software, information, and human resources. CAD software is the “browser” through which design interfaces with these resources. For engineering design, the network promises to integrate activities across enterprises and throughout product life cycles. This article describes some of the technology trends influencing network-enabled CAD, with a particular focus on how companies are assimilating new Internet and object-oriented concepts. It reflects nearly two years of discussions with many people in both the software and engineering industries, including discussions held at industry-focused panels and workshops sponsored by the National Institute of Standards and Technology     

An ontological basis for computer aided innovation

Knowledge acquisition and capitalization to solve problems concerning artefact evolution, still called inventive design, has a certain quantity of specific characteristics. It needs the choice of certain pieces of knowledge that may induce evolutions; it leads to reformulating the initial problem to build an abstract model of the artefact. The theoretical approach we are interested in, called TRIZ (the Russian acronym for Theory for Inventive Problem Solving), when translated into a methodological procedure, has not been fully formalized yet. This article proposes an ontology of the main notions of the concepts associated to knowledge acquisition in this framework. This ontology, beyond the clarification it brings to the involved notions, will be the support of a software architecture for implementing the method for knowledge acquisition and problem formulation.     

Interactive computer aided design using computer graphics

The development of a software system for general network design using interactive computer graphics poses many problems, which must be solved in a way consistent with the principles of man-machine communication as applied to network design, so as to obtain a system suited both to networks of any nature and also to any type of network design technique.This paper states the principles influencing the development of such a system and presents the design decisions made and the one implementation.     

A part recognition based computer aided assembly system

In this paper, a new approach has been developed to recognize the CAD models through their face adjacency relations and attributes and to automatically assemble the recognized parts in a CAD environment. Adjacent faces and the face attributes belonging to each face of parts designed in a CAD platform are derived by using of standard for the exchange of product data (STEP) file. They are represented in a square matrix format named face oriented relation matrix (FORM). An expert system was developed and embedded within the system. A knowledge base of the expert system is generated using a text editor. Reasoning the face adjacency relations and the face attributes in the knowledge base and FORM, the parts are recognized. Then, a reference face belonging to recognized parts is determined and they are positioned and assembled in assembly file through their reference faces. Part recognition approach developed in this study is applied to a computer aided assembly system. But it may be useful and practical for different CAD/CAM applications such as process planning and group technology too. The algorithm has been applied to a diesel automobile engine which has complex parts to demonstrate its efficiency and capability.     

A scheme for the realization of graphical computer aided design systems

We present some of the problems encountered in the study of CAD systems in an electro-mechanical company, and propose a methodology based entirely on a detailed object study. In the first part of this paper we analyse the traditional design process in the company and define the most important functions of a CAD system. In the second part, we show how a functional hierarchical decomposition of the product helps us to realize the CAD system, and then we describe the practical application.     

基于灌注分析模型的计算机辅助诊断*

在放射学领域引入了灌注分析方法作为辅助诊断的有效手段。介绍了计算机辅助诊断的基本原理、血流计算的灌注分析方法,并设计了一种针对结肠病变的灌注影像分析系统。实验表明使用动态CT灌注成像方法及后处理算法,可及时检测到一些常规CT检查所不能够检测到的结肠病变,对于一些病变的及时诊断、及时治疗具有重要意义。     

Periodic surface modeling for computer aided nano design

Current solid and surface modeling methods based on Euclidean geometry in traditional computer aided design are not efficient in constructing a large number of atoms and particles. In this paper, we propose a periodic surface model for computer aided nano design such that geometry of atoms and molecules can be constructed parametrically. At the molecular scale, periodicity of the model allows thousands of particles to be built efficiently. At the meso scale, inherent porosity of the model represents natural morphology of polymer and macromolecule. Surface and volume operations are defined to support crystal and molecular model creation with loci and foci periodic surfaces. The ultimate goal is to enable computer assisted material and system design at atomic, molecular, and meso scales.     

Robust uniform triangulation algorithm for computer aided design

This paper presents a new robust uniform triangulation algorithm that can be used in CAD/CAM systems to generate and visualize geometry of 3D models. Typically, in CAD/CAM systems 3D geometry consists of 3D surfaces presented by the parametric equations (e.g. surface of revolution, NURBS surfaces) which are defined on a two dimensional domain. Conventional triangulation algorithms (e.g. ear clipping, Voronoi-Delaunay triangulation) do not provide desired quality and high level of accuracy (challenging tasks) for 3D geometry. The approach developed in this paper combines lattice tessellation and conventional triangulation techniques and allows CAD/CAM systems to obtain the required surface quality and accuracy. The algorithm uses a Cartesian lattice to divide the parametric domain into adjacent rectangular cells. These cells are used to generate polygons that are further triangulated to obtain accurate surface representation. The algorithm allows users to control the triangle distribution intensity by adjusting the lattice density. Once triangulated, the 3D model can be used not only for rendering but also in various manufacturing and design applications. The approach presented in this paper can be used to triangulate any parametric surface given in S(u,v) form, e.g. NURBS surfaces, surfaces of revolution, and produces good quality triangulation which can be used in CAD/CAM and computer graphics applications.     

A novel solution of deep learning for endoscopic ultrasound image segmentation: enhanced computer aided diagnosis of gastrointestinal stromal tumor

Multimedia Tools and Applications - Gastrointestinal stromal tumor is one of the critical tumors that doctors do not suggest to get frequent endoscopy, so there is a need for a diagnosis system...     

随机森林在滚动轴承故障诊断中的应用

针对不同轴承数据特征选择困难和单个分类器方法在滚动轴承故障诊断中精度较低的问题,提出了一种基于分类回归树（CART）的随机森林滚动轴承故障诊断算法。随机森林是包含了多种分类器的集成学习方法。通过随机森林的“集成”思想来提高滚动轴承故障诊断的精度。从滚动轴承的振动信号中提取时域统计指标,将其作为特征向量,利用随机森林（Random Forest）对滚动轴承故障进行诊断。利用SQI-MFS实验平台的轴承数据,与传统分类器（SVM、kNN和ANN）以及单个分类回归树的诊断结果相比,随机森林算法具有比较高的诊断精度。     

A new computer system for education

Advances in available computer and data communications technology are not, in general, immediately available in the classroom and laboratory. This paper gives details of a computer board which uses state-of-the-art technology to create a system which is useful as a classroom tool as well as a research and laboratory instrument. The new system encourages a hands-on approach by making available to the user all the appropriate signals. The board utilizes a Motorola 68030 microprocessor augmented with a 68882 floating point unit (FPU) to provide the compute power of the system. The system also has 8 MB of dynamic RAM combined with a large cache, as well as 128 KB of read-only memory. In addition, the system has SCSI and VME bus interfaces, an Ethernet interface, two RS232 terminal connections, and two parallel/timer ports for project implementation. The new computer board is host independent and thus can operate as a stand alone system.

Researchers in electrical engineering can benefit from the facilities provided, as well as engineers working in microprocessor design and implementation, programming, data networking, operating systems, instrumentation and computer interfacing areas. In this paper, we cover topics which utilize many features of the system, such as digital signal processing, digital control and image processing.