检索结果-南通市图书馆

Study of Texture Segmentation and Classification for Grading Small Hepatocellular Carcinoma Based on CT Images

在线全文

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2021年第2期26卷 199-207页

作者： bei hui Yanbo Liu Jiajun Qiu Likun Cao Lin Ji Zhiqiang He School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu 610054China West China Biomedical Big Data Center West China HospitalSichuan UniversityChengdu 610041China Department of Radiology of Peking Union Medical College Hospital Beijing 100032China Department of Radiology West China HospitalSichuan UniversityChengdu 610041China

To grade Small Hepatocellular Car Cinoma(SHCC)using texture analysis of CT images,we retrospectively analysed 68 cases of Grade II(medium-differentiation)and 37 cases of Grades III and IV(high-differentiation).The grading scheme follows 4 stages:(1)training a Super Resolution Generative Adversarial Network(SRGAN)migration learning model on the Lung Nodule Analysis 2016 Dataset,and employing this model to reconstruct Super Resolution Images of the SHCC Dataset(SR-SHCC)images;(2)designing a texture clustering method based on Gray-Level Co-occurrence Matrix(GLCM)to segment tumour regions,which are Regions Of Interest(ROIs),from the original and SR-SHCC images,respectively;(3)extracting texture features on the ROIs;(4)performing statistical analysis and *** segmentation achieved accuracies of 0.9049 and 0.8590 in the original SHCC images and the SR-SHCC images,*** classification achived an accuracy of 0.838 and an Area Under the ROC Curve(AUC)of *** grading scheme can effectively reduce poor impacts on the texture analysis of SHCC *** may play a guiding role for physicians in early diagnoses of medium-differentiation and high-differentiation in SHCC.

关键词： grading of Small Hepatocellular Car Cinoma(SHCC) Gray-Level Co-occurrence Matrix(GLCM) texture clustering super-resolution reconstruction

Mu-Net:Multi-Path Upsampling Convolution Network for Medical Image Segmentation

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2022年第4期131卷 73-95页

作者： Jia Chen Zhiqiang He Dayong Zhu bei hui Rita Yi Man Li Xiao-Guang Yue School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu610054China Department of Economics and Finance/Sustainable Real Estate Research Center Hong Kong Shue Yan UniversityHongkongChina Rattanakosin International College of Creative Entrepreneurship Rajamangala University of Technology RattanakosinNakhon Pathom73170Thailand Department of Computer Science and Engineering School of SciencesEuropean University CyprusNicosia1516Cyprus CIICESI ESTGPolit′ecnico do Porto4610-156FelgueirasPortugal

Medical image segmentation plays an important role in clinical diagnosis,quantitative analysis,and treatment *** 2015,U-Net-based approaches have been widely used formedical image *** purpose of the U-Net expansive path is to map low-resolution encoder feature maps to full input resolution feature ***,the consecutive deconvolution and convolutional operations in the expansive path lead to the loss of some high-level *** high-level information can make the segmentationmore *** this paper,we propose MU-Net,a novel,multi-path upsampling convolution network to retain more high-level *** MU-Net mainly consists of three parts:contracting path,skip connection,and multi-expansive *** proposed MU-Net architecture is evaluated based on three different medical imaging *** experiments show that MU-Net improves the segmentation performance of U-Net-based methods on different *** the same time,the computational efficiency is significantly improved by reducing the number of parameters by more than half.

关键词： Medical image segmentation MU-Net(multi-path upsampling convolution network) U-Net clinical diagnosis encoder-decoder networks

Research on Mediate Temperature Decomposition of High Nitrogen Austenite

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

材料热处理学报 2004年第5期25卷 214-216页

作者： LIXiao-ling beiDuo-hui HUMing-juan ZHUZu-chang SchoolofMaterialScienceandEngineering ShanghaiJiaoTongUniversityShanghaiChina

The decomposed products from high nitrogen austenite aging at 225°C were investigated by TEM. It is found that the shape of decomposition products inside the austenite grains is not regular and not strictly oriented. Preferential nucleation of y-Fe4N at dislocations and grain boundaries has been observed. It also has been found that during the first stage of the high nitrogen austenite decomposition a large quantity of ultra-fine /-Fe4N precipitate inside the parent austenite, which has been thought to be the undecomposed region before. The ultimate products are composed of highly dispersed a-Fe and /-Fe4N, with both of them maintaining nanometer scale. The micro-hardness of them can be as high as 900HV.

关键词：高氮奥氏体温度分解微硬度 TEM

Research of Anti-spam System Basing on Immunity Systemand Mobile Agent

在线全文

学校读者我要写书评

暂无评论

现代电子技术 2007年第3期30卷 62-64页

作者： hui bei WU Yue JI Lin CHEN Jia School of Computer University of Electronic Science and TechnologyChengdu 610054China Huaxi Hospital Sichuan UniversityChengdu610041 China

The human immune system has the function of *** can identify the non-self antigen and clear it through the immune response ***,human body has the power of resisting *** anti-spam system basing on immune system is proposed by using immune system′s theory,and it is introduced in the mail service of enterprise *** VPN as the human body,the mobile agent is simulated the antibody because of its movable and intelligent,and the spam is simulated the *** can clear the spam by using immune *** method is a new thinking of anti-spam *** advantage is overcoming the weakness on independence of traditional antispam system.

关键词：免疫系统移动Agent 免疫响应虚拟网络垃圾邮件

在线全文

学校读者我要写书评

暂无评论

乳清大豆复合蛋白饮料的研制

食品科技 2006年第11期31卷 198-201页

作者：贝惠玲广东轻工职业技术学院食品与生物工程系广州510300

对乳清大豆复合蛋白饮料的加工工艺进行了研究,通过单因素及正交试验确定了最佳配方及工艺条件,试验结果表明选择合适的复合乳化稳定剂、工艺上采用预乳化及二次高压均质均有助于提高复合蛋白饮料的稳定性。

关键词：乳清蛋白大豆复合蛋白饮料

基于不完全朴素贝叶斯分类模型的垃圾邮件分类模型

在线全文

学校读者我要写书评

暂无评论

计算机应用 2009年第3期29卷 903-904,907页

作者：惠孛吴跃电子科技大学计算机科学与工程学院成都610054

由于朴素贝叶斯分类模型的简单高效,在垃圾邮件分类时可以达到较好的效果;但朴素贝叶斯的条件独立假设割裂了属性之间的关系,影响了分类的准确性。放松朴素贝叶斯分类模型关于属性之间条件独立假设,介绍一种新的基于不完全朴素贝叶斯分... 详细信息

由于朴素贝叶斯分类模型的简单高效,在垃圾邮件分类时可以达到较好的效果;但朴素贝叶斯的条件独立假设割裂了属性之间的关系,影响了分类的准确性。放松朴素贝叶斯分类模型关于属性之间条件独立假设,介绍一种新的基于不完全朴素贝叶斯分类模型的垃圾邮件分类模型,N平均1-依赖邮件过滤模型。使用N个1-依赖分类模型的平均概率作为分类的预测概率。实验证明,该模型在简单、高效的同时降低了对垃圾邮件分类的错误率。

关键词：贝叶斯分类不完全朴素贝叶斯垃圾邮件

在线全文

学校读者我要写书评

暂无评论

柚子粉的研制

食品研究与开发 2007年第2期28卷 98-101页

作者：贝惠玲莫慧平广东轻工职业技术学院食品与生物工程系广东广州510300

对利用柚皮及柚子汁加工柚子粉的工艺进行了研究,试验结果表明:在浆料中使用果胶酶及纤维素酶可有效降低浆料粘度,利于均质、喷雾干燥等后加工;经过盐水热烫及清水漂洗后的柚子皮可去除苦涩味;添加纽甜及β-环糊精,可掩盖果汁的苦涩味,... 详细信息

对利用柚皮及柚子汁加工柚子粉的工艺进行了研究,试验结果表明:在浆料中使用果胶酶及纤维素酶可有效降低浆料粘度,利于均质、喷雾干燥等后加工;经过盐水热烫及清水漂洗后的柚子皮可去除苦涩味;添加纽甜及β-环糊精,可掩盖果汁的苦涩味,使产品具有良好的口味。

关键词：柚子柚子粉加工工艺

在线全文

学校读者我要写书评

暂无评论

基于NB的双级分类模型在邮件过滤中的研究

计算机科学 2006年第5期33卷 110-112页

作者：惠孛吴跃陈佳电子科技大学成都610054

使用朴素的贝叶斯(NB)分类模型对邮件进行分类,是目前基于内容的垃圾邮件过滤方法的研究热点。朴素的贝叶斯在参数之间联系不强的时候分类效果简单而有效。但是朴素的贝叶斯分类模型中对特征参数的条件独立假设无法表达参数之间在语义... 详细信息

使用朴素的贝叶斯(NB)分类模型对邮件进行分类,是目前基于内容的垃圾邮件过滤方法的研究热点。朴素的贝叶斯在参数之间联系不强的时候分类效果简单而有效。但是朴素的贝叶斯分类模型中对特征参数的条件独立假设无法表达参数之间在语义上的关系,影响分类性能。在朴素的贝叶斯分类模型的基础上,我们提出了一种双级贝叶斯分类模型(DLB,Double Level Bayes),既考虑到了参数之间的影响又保留了朴素的贝叶斯分类模型的优点。同时对DLB 模型与朴素的贝叶斯分类模型的性能进行比较。仿真实验表明,DLB 分类模型在垃圾邮件过滤应用中的效果在大部分条件下优于朴素的贝叶斯分类模型。

关键词：垃圾邮件过虑朴素贝叶斯分类模型双级分类模型

在线全文

学校读者我要写书评

暂无评论

关联理论在中医英语翻译中的应用

中西医结合学报 2010年第2期8卷 195-197页

作者：惠佳蓓张斌南京中医药大学外国语学院江苏南京210029

关联理论(relevance theory)认为,人类语言交际是通过寻找关联进行双重明示一推理的交际过程。是涉及原文作者、译者和译文读者3个交际主体的动态关系。中医英译属于跨文化交际。我们探讨了关联理论在中医英语翻译中的应用,并通过对某... 详细信息

关联理论(relevance theory)认为,人类语言交际是通过寻找关联进行双重明示一推理的交际过程。是涉及原文作者、译者和译文读者3个交际主体的动态关系。中医英译属于跨文化交际。我们探讨了关联理论在中医英语翻译中的应用,并通过对某些中医术语和中医典籍《伤寒论》英译片段的分析,说明关联理论在传递中医文化内涵的翻译实践中所起的指导作用。[第一段]

关键词：关联理论翻译英语中医名词