检索结果-南通市图书馆

Using Multiple Risk Factors and Generalized Linear Mixed Models with 5-Fold Cross-Validation Strategy for Optimal Carotid Plaque Progression Prediction

引用

医用生物力学 2019年第A1期34卷 74-75页

作者： Qingyu Wang Dalin Tang Liang Wang gador canton Zheyang Wu Thomas SHatsukami Kristen L Billiar Chun Yuan School of Biological Science and Medical Engineering Southeast UniversityNanjing210096China Mathematical Sciences Department Worcester Polytechnic InstituteWorcesterMA01609USA Department of Mechanical Engineering University of WashingtonSeattleWA98195USA Division of Vascular Surgery University of WashingtonSeattleWA98195USA Biomedical Engineering Department Worcester Polytechnic InstituteWorcesterMA01609USA Department of Radiology University of WashingtonSeattleWA98195USA

Background Cardiovascular diseases are closely linked to atherosclerotic plaque development and *** progression prediction is of fundamental significance to cardiovascular research and disease diagnosis,prevention,and *** linear mixed models(GLMM)is an extension of linear model for categorical responses while considering the correlation among *** Magnetic resonance image(MRI)data of carotid atheroscleroticplaques were acquired from 20 patients with consent obtained and 3D thin-layer models were constructed to calculate plaque stress and strain for plaque progression *** for ten morphological and biomechanical risk factors included wall thickness(WT),lipid percent(LP),minimum cap thickness(MinCT),plaque area(PA),plaque burden(PB),lumen area(LA),maximum plaque wall stress(MPWS),maximum plaque wall strain(MPWSn),average plaque wall stress(APWS),and average plaque wall strain(APWSn)were extracted from all slices for *** thickness increase(WTI),plaque burden increase(PBI)and plaque area increase(PAI) were chosen as three measures for plaque *** linear mixed models(GLMM)with 5-fold cross-validation strategy were used to calculate prediction accuracy for each predictor and identify optimal predictor with the highest prediction accuracy defined as sum of sensitivity and *** 201 MRI slices were randomly divided into 4 training subgroups and 1 verification *** training subgroups were used for model fitting,and the verification subgroup was used to estimate the *** combinations(total1023)of 10 risk factors were feed to GLMM and the prediction accuracy of each predictor were selected from the point on the ROC(receiver operating characteristic)curve with the highest sum of specificity and *** LA was the best single predictor for PBI with the highest prediction accuracy(1.360 1),and the area under of the ROC curve(AUC)is0.654 0,followed by APWSn(1.336

关键词： Multiple Risk Factors Generalized Linear 5-Fold Cross-Validation Strategy AUC

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

基于U-Net神经网络的多模态MR颈动脉血管成像的分割方法研究

引用

中华放射学杂志 2019年第12期53卷 1091-1095页

作者：李继凡陈硕章强宋焱 gador canton 孙杰许东翔赵锡海苑纯李睿清华大学医学院生物医学工程系生物医学影像研究中心北京100084 北京医院放射科 100730 美国华盛顿大学放射学系血管成像实验室西雅图90876

目的探讨基于U-Net神经网络的多模态MR影像颈动脉血管分割方法的价值.方法回顾性分析了2012年至2015年中国动脉粥样硬化风险评估研究项目中,经标准多模态MR扫描,且两周内出现缺血性脑卒中或短暂性脑缺血的患者.经纳入标准和排除标准... 详细信息

目的探讨基于U-Net神经网络的多模态MR影像颈动脉血管分割方法的价值.方法回顾性分析了2012年至2015年中国动脉粥样硬化风险评估研究项目中,经标准多模态MR扫描,且两周内出现缺血性脑卒中或短暂性脑缺血的患者.经纳入标准和排除标准筛选后,有658例患者共17 568层颈动脉血管壁影像纳入研究.应用定制设计的心血管疾病评估计算机辅助系统(CASCADE,华盛顿大学血管成像实验室,西雅图)对所有影像数据进行分析.按照训练集、验证集和测试集6∶2∶2的比例,随机选取10 592个样本作为训练集,3 488个样本作为验证集,3 488个样本作为测试集.为防止模型过拟合,提高模型泛化能力,对原始的多模态血管斑块MR影像进行数据增强.应用经过微调的U-Net神经网络构建多模态MR影像颈动脉血管分割模型,在训练集上训练,在验证集上验证并优化训练超参数,在测试集上测试并计算像素级别的颈动脉血管分割的敏感度、特异度和Dice系数,并计算U-Net分割方法和手工分割方法下的最大管壁厚度和管壁面积,利用组内相关系数和Bland-Altman分析来验证两种方法的一致性.结果在测试集上应用训练得到的U-Net神经网络模型进行颈动脉血管分割,计算敏感度为0.878,特异度为0.986,Dice系数为0.858.最大管壁厚度的组内相关系数(95%可信区间)为0.921(0.915~0.925),管壁面积的组内相关系数(95%可信区间)为0.929 (0.924~0.933),Bland-Altman分析中最大管壁厚度差值为(0.037±0.316)mm,管壁面积差值为(1.182± 4.953)mm2,U-Net分割方法和手工分割方法具有较高一致性.结论应用U-Net神经网络的方法,在大规模经过专业医师标注的数据集上进行训练和验证,可以实现对多模态MR影像颈动脉血管自动分割.

关键词：神经网络颈动脉动脉粥样硬化磁共振成像

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Combine morphological and mechanical risk factors for improved carotid plaque progression prediction:A patient-specific magnetic resonance image-based follow-up study

Combine morphological and mechanical risk factors for improv...

引用

第十二届全国生物力学学术会议暨第十四届全国生物流变学学术会议

作者： Qingyu Wang Dalin Tang gador canton Thomas S.Hatsukami Kristen L Billiar Zheyang Wu Chun Yuan School of Biological Science and Medical Engineering Southeast University Mathematical Sciences Department Worcester Polytechnic Institute Department of Mechanical Engineering University of Washington Division of Vascular Surgery University of Washington Biomedical Engineering Department Worcester Polytechnic Institute Department of Radiology University of Washington

Objective It is well known that the benefits from performing carotid endarterectomy for the patients with stenosis severity between 50%and 70%, remains questionable. With a 2%-4%event rate, most of the surgeries were unnecessary. Investigation of plaque development for these patients may aid in making more plausible decision on clinical intervention. We hypothesize that combining morphological and mechanical risk factors may improve plaque progression prediction. In this paper, plaque burden (PB),cap thickness (CT),lipid percent

关键词：

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：