期刊文献+
共找到849篇文章
< 1 2 43 >
每页显示 20 50 100
基于量子衍生涡流算法和T⁃S模糊推理模型的储层岩性识别
1
作者 赵娅 管玉 +1 位作者 李盼池 王伟 《石油地球物理勘探》 EI CSCD 北大核心 2024年第1期23-30,共8页
鉴于梯度下降法易陷入局部极值、普通群智能优化算法易早熟收敛,提出一种基于量子衍生涡流算法(Quantum Vortex Search Algorithm,QVSA)和T⁃S模糊推理模型的岩性识别方法,QVSA具有操作简单、收敛速度快、寻优能力强等优点,有助于T⁃S模... 鉴于梯度下降法易陷入局部极值、普通群智能优化算法易早熟收敛,提出一种基于量子衍生涡流算法(Quantum Vortex Search Algorithm,QVSA)和T⁃S模糊推理模型的岩性识别方法,QVSA具有操作简单、收敛速度快、寻优能力强等优点,有助于T⁃S模糊推理模型获得最优参数配置,从而实现储层岩性的准确识别。首先利用具有全局搜索能力的QVSA优化T⁃S模糊推理模型的各种参数;然后利用主成分分析方法降低获取的地震属性维度;再利用优化的T⁃S模糊推理模型识别储层岩性。实验结果表明,利用反映储层特征的8个地震属性识别储层岩性时,所提方法的识别正确率达到92%,比普通BP网络方法高5.1%,同时查准率、查全率、F1分数等指标也较BP网络方法提升明显。 展开更多
关键词 储层岩性识别 量子衍生涡流算法 T⁃s 模糊推理模型 模糊集 地震属性
下载PDF
甲状腺乳头状癌组织中SETDB2、Gal-3、PLEKHS1的表达情况及其对患者预后的预测价值
2
作者 桑妙玉 杨小洁 +4 位作者 王志慧 张超 刘晓霞 周玲玲 白宝琴 《广西医学》 CAS 2023年第21期2545-2550,共6页
目的分析SET结构域分叉组蛋白赖氨酸甲基转移酶2(SETDB2)、半乳糖凝集素3(Gal-3)、pleckstrin同源结构域S1(PLEKHS1)在甲状腺乳头状癌组织中的表达情况,以及三者对患者预后的预测价值。方法(1)选择118例甲状腺乳头状癌患者作为研究组,4... 目的分析SET结构域分叉组蛋白赖氨酸甲基转移酶2(SETDB2)、半乳糖凝集素3(Gal-3)、pleckstrin同源结构域S1(PLEKHS1)在甲状腺乳头状癌组织中的表达情况,以及三者对患者预后的预测价值。方法(1)选择118例甲状腺乳头状癌患者作为研究组,45例甲状腺良性结节患者作为对照组。采用免疫组化法检测甲状腺乳头状癌组织和甲状腺良性结节组织中SETDB2、Gal-3、PLEKHS1蛋白表达情况。比较研究组与对照组之间,以及不同特征甲状腺乳头状癌患者之间病灶组织中SETDB2、Gal-3、PLEKHS1蛋白的阳性表达率。(2)随访1年,记录甲状腺乳头状癌患者的生存情况。分析SETDB2、Gal-3、PLEKHS1蛋白阳性表达和阴性表达患者的生存率;比较预后良好和预后不良患者SETDB2、Gal-3、PLEKHS1蛋白的阳性表达率。采用受试者工作特征(ROC)曲线分析SETDB2、Gal-3、PLEKHS1对甲状腺乳头状癌患者预后的预测价值。结果(1)与对照组相比,研究组病灶组织中SETDB2蛋白阳性表达率较低,Gal-3、PLEKHS1蛋白阳性表达率较高(P<0.05)。在甲状腺乳头状癌患者中,Ⅲ~Ⅳ期、浸润深度≥1/2、组织中低分化、淋巴结转移、肿瘤直径>1 cm的患者病灶组织中SETDB2蛋白阳性表达率更低,Gal-3、PLEKHS1蛋白阳性表达率更高(P<0.05)。(2)在甲状腺乳头状癌患者中,SETDB2蛋白阳性表达患者生存率高于SETDB2蛋白阴性表达患者,Gal-3、PLEKHS1蛋白阳性表达患者生存率低于Gal-3、PLEKHS1蛋白阴性表达患者(P<0.05);预后良好患者的SETDB2蛋白阳性表达率高于预后不良患者,Gal-3、PLEKHS1蛋白阳性表达率低于预后不良患者(P<0.05)。ROC曲线分析结果显示,SETDB2、Gal-3、PLEKHS1蛋白总评分预测甲状腺乳头状癌患者预后不良的曲线下面积分别为0.826、0.841、0.859。结论在甲状腺乳头状癌中,SETDB2呈低表达,而Gal-3、PLEKHS1呈高表达,三者均与患者的病情严重程度相关,且对预后具有一定的预测价值。 展开更多
关键词 甲状腺乳头状癌 set结构域分叉组蛋白赖氨酸甲基转移酶2 半乳糖凝集素3 pleckstrin同源结构域s1 预后 预测价值
下载PDF
基于T-S模糊神经网络的光伏发电机组自动控制
3
作者 杨振睿 沈主浮 +2 位作者 孙辰 蔡斌 姜宽 《机械与电子》 2024年第2期35-39,共5页
光照情况变化会使光伏发电机组功率呈现不稳定性,加大光伏发电机组控制难度,为此,设计了基于T-S模糊神经网络的光伏发电机组自动控制方法。构建光伏阵列数学模型,分析在均匀和不均匀2种光照情况下光伏发电机组特性曲线。以分析结果为依... 光照情况变化会使光伏发电机组功率呈现不稳定性,加大光伏发电机组控制难度,为此,设计了基于T-S模糊神经网络的光伏发电机组自动控制方法。构建光伏阵列数学模型,分析在均匀和不均匀2种光照情况下光伏发电机组特性曲线。以分析结果为依据,采用T-S模糊神经网络构建光伏发电机组自动控制模型。为保证良好的控制效果,引入定比因子优化隶属度函数,输出最佳跟踪结果,结合最佳跟踪结果和自动控制模型实现光伏发电机组自动控制。测试结果显示,该方法能够完成光伏阵列特性分析,控制效果好。 展开更多
关键词 T-s模糊神经网络 光伏发电机组 自动控制 特性曲线 最大功率点 光照情况
下载PDF
用Level Set方法求解具有自由面的流动问题 被引量:11
4
作者 袁德奎 陶建华 《力学学报》 EI CSCD 北大核心 2000年第3期264-271,共8页
为采用 Level Set方法来计算有自由水面的流动问题提出了一种方案.把自由水面视为水和空气的交界面,两种介质用统一的N-S方程求解,在自由面两侧分别采用各自的密度和粘性,并在自由面上给以适当的光滑;采用边界无法求解... 为采用 Level Set方法来计算有自由水面的流动问题提出了一种方案.把自由水面视为水和空气的交界面,两种介质用统一的N-S方程求解,在自由面两侧分别采用各自的密度和粘性,并在自由面上给以适当的光滑;采用边界无法求解双调和方程来确定距离函数;N-S方程用投影法求解.文中给出了二维水池水面振荡和瞬时溃坝问题的算例,可以看出用 Level Set方法求解有自由面流动问题是有效的. 展开更多
关键词 LEVEL set方法 自由面 N-s方程 流动 水动力学
下载PDF
用LEVEL SET方法计算溃坝波的传播过程 被引量:5
5
作者 陶建华 谢伟松 《水利学报》 EI CSCD 北大核心 1999年第10期17-22,共6页
溃坝波的数值模拟在于正确地计算坝体溃决后上下游水面的迅速变化过程. 本文研究了近年发展起来的求解两种流体界面的Level Set 方法及其在具有自由表面的水动力学问题中的应用. 对不同底坡上的二维溃坝波进行了计算, 取得... 溃坝波的数值模拟在于正确地计算坝体溃决后上下游水面的迅速变化过程. 本文研究了近年发展起来的求解两种流体界面的Level Set 方法及其在具有自由表面的水动力学问题中的应用. 对不同底坡上的二维溃坝波进行了计算, 取得了和实验资料符合良好的结果. 展开更多
关键词 Levelset方法 自由表面 溃坝波 Ns方程
下载PDF
基于改进DSets的无参数雷达信号分选算法 被引量:3
6
作者 刘鲁涛 王璐璐 陈涛 《中国舰船研究》 CSCD 北大核心 2021年第4期232-238,共7页
[目的]随着电磁环境日益复杂,信号分选越来越困难。为了解决现有高效分选算法性能严重依赖于外界输入参数的不足,提出了基于DSets-DS的无参数雷达信号聚类算法。[方法]将直方图均衡化后的主导集(dominant sets,DSets)算法应用于雷达信... [目的]随着电磁环境日益复杂,信号分选越来越困难。为了解决现有高效分选算法性能严重依赖于外界输入参数的不足,提出了基于DSets-DS的无参数雷达信号聚类算法。[方法]将直方图均衡化后的主导集(dominant sets,DSets)算法应用于雷达信号分选,提出一种无参数的雷达信号脉冲聚类算法,然后结合D-S(Dempster-Shafer)证据理论,以解决DSets算法过度分割问题。[结果]在无任何先验信息条件下,能够完成对雷达信号混合脉冲精准聚类;此外,在虚假脉冲比例低于50%的情况下,分选正确率大于93.13%。将DSets算法与D-S证据理论结合,可有效完成对无先验信息的雷达信号脉冲聚类,且有很好的聚类性能。 展开更多
关键词 无参数聚类 主导集算法 直方图均衡 D-s证据理论
下载PDF
快速粒子level set方法的并行化
7
作者 黄筱云 夏波 +1 位作者 程永舟 赵利平 《哈尔滨工程大学学报》 EI CAS CSCD 北大核心 2018年第9期1478-1484,共7页
为缩短快速粒子level set(FPLS)方法追踪交界面的时间,分别运用区域分解和粒子分解算法来减少欧拉计算(level set对流方程和重新初始化)和拉格朗日计算(粒子时程积分和误差校正)的开销。算法采用OpenMP技术来实现,并通过Zalesak圆盘、... 为缩短快速粒子level set(FPLS)方法追踪交界面的时间,分别运用区域分解和粒子分解算法来减少欧拉计算(level set对流方程和重新初始化)和拉格朗日计算(粒子时程积分和误差校正)的开销。算法采用OpenMP技术来实现,并通过Zalesak圆盘、单涡以及三维变形等典型算例进行验证。计算结果表明:4线程下加速比能超过2,8线程下加速比也能接近4,并行化的FPLS方法具有良好的实用性和可扩展性。 展开更多
关键词 快速粒子level set方法 并行 区域分解 粒子分解 OPENMP Zalesak圆盘 单涡
下载PDF
RITT-WU'S CHARACTERISTIC SET METHOD FOR ORDINARY DIFFERENCE POLYNOMIAL SYSTEMS WITH ARBITRARY ORDERING 被引量:5
8
作者 高小山 袁春明 张桂林 《Acta Mathematica Scientia》 SCIE CSCD 2009年第4期1063-1080,共18页
In this paper, a Ritt-Wu's characteristic set method for ordinary difference systems is proposed, which is valid for any admissible ordering. New definition for irreducible chains and new zero decomposition algorithm... In this paper, a Ritt-Wu's characteristic set method for ordinary difference systems is proposed, which is valid for any admissible ordering. New definition for irreducible chains and new zero decomposition algorithms are also proposed. 展开更多
关键词 difference polynomial ascending chain characteristic set Ritt-Wu's zero decomposition theorem
下载PDF
Function S-Rough sets and its applications 被引量:25
9
作者 Cui Yuquan Shi Kaiquan 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2006年第2期331-338,共8页
Based on S-rough sets(singular rough sets), this paper presents function S-rough sets (function singular rough sets)and its mathematical structures and features. Function S-rough sets has two forms: function one ... Based on S-rough sets(singular rough sets), this paper presents function S-rough sets (function singular rough sets)and its mathematical structures and features. Function S-rough sets has two forms: function one direction S-rough sets (function one direction singular rough sets) and function two direction S-rough sets (function two direction singular rough sets). This paper advances the relationship theorem of function S-rough sets and S-rough sets. Function S-rough sets is the general form of S-rough sets, and S-rough sets is the special ease of function S-rough sets. In this paper, applications of function S-rough sets in rough law mining-discovery of system are given. Function S-rough sets is a new research direction of rough sets and rough system. 展开更多
关键词 function s-rough sets structure of function s-rough sets relationship theorem rough law mining-discovery applications.
下载PDF
Function S-rough sets and mining-discovery of rough law in systems 被引量:25
10
作者 Shi Kaiquan Xia Jiarong 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2006年第4期919-926,共8页
Function S-rough sets (function singular rough sets) is defined on a -function equivalence class [u]. Function S-rough sets is the extension form of S-rough sets. By using the function S-rough sets, this paper gives... Function S-rough sets (function singular rough sets) is defined on a -function equivalence class [u]. Function S-rough sets is the extension form of S-rough sets. By using the function S-rough sets, this paper gives rough law generation model of a-function equivalence class, discussion on law mining and law discovery in systems, and application of law mining and law discovery in communication system. Function S-rough sets is a new theory and method in law mining research. 展开更多
关键词 function s-rough sets structure of function s-rough sets relationship theorem rough law mining-discovery applications.
下载PDF
(S,T)-WEAK TRACTABILITY OF MULTIVARIATE LINEAR PROBLEMS IN THE AVERAGE CASE SETTING 被引量:1
11
作者 刘永平 许贵桥 《Acta Mathematica Scientia》 SCIE CSCD 2019年第4期1033-1052,共20页
The purpose of this article is to investigate (s, t)-weak tractability of multivariate linear problems in the average case set ting. The considered algorithms use finitely many evaluations of arbitrary linear function... The purpose of this article is to investigate (s, t)-weak tractability of multivariate linear problems in the average case set ting. The considered algorithms use finitely many evaluations of arbitrary linear functionals. Generally, we obtained matching necessary and sufficient conditions for (s,t)-weak tractability in terms of the corresponding non-increasing sequence of eigenvalues. Specifically, we discussed (s, t)-weak tractability of linear tensor product problems and obtained necessary and sufficient conditions in terms of the corresponding one-dimensional problem. As an example of applications, we discussed also (s,t)-weak tractability of a multivariate approximation problem. 展开更多
关键词 (s t)-weak TRACTABILITY LINEAR PROBLEM LINEAR tensor product PROBLEM HILBERT space AVERAGE case setting
下载PDF
The Geology and Tectonic Settings of China's Mineral Deposits by Franco Pirajno 被引量:5
12
作者 Yanjing Chen 《Geoscience Frontiers》 SCIE CAS CSCD 2013年第4期477-477,共1页
China is the third largest country in the world, with a land area of about 9.6 million km2. It is endowed with abundant mineral resources, and the metal mining activity can be traced back to ca. 8000 years ago. Howeve... China is the third largest country in the world, with a land area of about 9.6 million km2. It is endowed with abundant mineral resources, and the metal mining activity can be traced back to ca. 8000 years ago. However, due to language barrier, little has been known about the geology and tectonics to the outside world until 1980s. In the last three decades, a great deal of knowledge has been gained, enhanced by a vigorous cooperation between Chinese and Western geologists. Research papers about geological, geochemical, and geochronological features of mineral deposits of China are widely published and cited in international journals. A comprehen- sive and comprehensible English literature that summarises the features of mineral deposits in China, however, is still lacking. 展开更多
关键词 WORK this The Geology and Tectonic settings of China’s Mineral Deposits by Franco Pirajno
下载PDF
Research on knowledge acquisition method about the IF/THEN rules based on rough set theory 被引量:2
13
作者 Liu Daohua Yuan Sicong +1 位作者 Zhang Xiaolong Wang Fazhan 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2008年第3期628-634,F0003,共8页
The basic principles of IF/THEN rules in rough set theory are analyzed first, and then the automatic process of knowledge acquisition is given. The numerical data is qualitatively processed by the classification of me... The basic principles of IF/THEN rules in rough set theory are analyzed first, and then the automatic process of knowledge acquisition is given. The numerical data is qualitatively processed by the classification of membership functions and membership degrees to get the normative decision table. The regular method of relations and the reduction algorithm of attributes are studied. The reduced relations are presented by the multi-representvalue method and its algorithm is offered. The whole knowledge acquisition process has high degree of automation and the extracted knowledge is true and reliable. 展开更多
关键词 rough set theory knowledge's automatic gain IF/THEN rule attribute reduction multi-dimensionalrepresentative value.
下载PDF
S-rough sets and knowledge separation 被引量:104
14
作者 Shi Kaiquan 1,21. School of Mathematics and System Sciences, Liaocheng University, Liaocheng 252059, P. R. China 2. School of Mathematics and System Sciences, Shandong University, Jinan 250100, P. R. China 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2005年第2期403-410,共8页
The conceptions of the knowledge screen generated by S-rough sets are given: f- screen and - screen , and then puts forward - filter theorem, - filter theorem of knowledge. At last, the applications of knowledge separ... The conceptions of the knowledge screen generated by S-rough sets are given: f- screen and - screen , and then puts forward - filter theorem, - filter theorem of knowledge. At last, the applications of knowledge separation are given according to - screen and - screen. 展开更多
关键词 s- rough sets f- screen - screen f-filter theorem - filter theorem knowledge separation.
下载PDF
THE STRUCTURE AND APPROXIMATION OF A.S. SELF-SIMILAR SET 被引量:1
15
作者 胡迪鹤 《Acta Mathematica Scientia》 SCIE CSCD 2003年第2期201-207,共7页
The structure of any a.s. self-similar set K(w) generated by a class of random elements {gn,wσ} taking values in the space of contractive operators is given and the approximation of K(w) by the fixed points {Pn,wσ} ... The structure of any a.s. self-similar set K(w) generated by a class of random elements {gn,wσ} taking values in the space of contractive operators is given and the approximation of K(w) by the fixed points {Pn,wσ} of {gn,ow} is obtained. It is useful to generate the fractal in computer. 展开更多
关键词 a.s. self-similar set Hausdorff metric fixed point sTRUCTURE APPROXIMATION
下载PDF
Likely Limit Sets of a Class of p-order Feigenbaum's Maps 被引量:1
16
作者 WANG WEI LIAO LI 《Communications in Mathematical Research》 CSCD 2012年第2期137-145,共9页
A continuous map from a closed interval into itself is called a p-order Feigenbaum's map if it is a solution of the Feigenbaum's equation fP(λx)=λf(x). In this paper, we estimate Hausdorff dimensions of likely... A continuous map from a closed interval into itself is called a p-order Feigenbaum's map if it is a solution of the Feigenbaum's equation fP(λx)=λf(x). In this paper, we estimate Hausdorff dimensions of likely limit sets of some p-order Feigenbaum's maps. As an application, it is proved that for any 0 〈 t 〈 1, there always exists a p-order Feigenbaum's map which has a likely limit set with Hausdorff dimension t. This generalizes some known results in the special case of p =2. 展开更多
关键词 Feigenbaum's equation Feigenbaum's map likely limit set Hausdorff dimension
下载PDF
Topology and Shape Optimization of 2-D and 3-D Micro-ArchitecturedThermoelastic Metamaterials Using a Parametric Level Set Method 被引量:1
17
作者 Ellie Vineyard Xin-Lin Gao 《Computer Modeling in Engineering & Sciences》 SCIE EI 2021年第6期819-854,共36页
2-D and 3-D micro-architectured multiphase thermoelastic metamaterials are designed and analyzed using a parametric level set method for topology optimization and the finite element method.An asymptotic homogenization... 2-D and 3-D micro-architectured multiphase thermoelastic metamaterials are designed and analyzed using a parametric level set method for topology optimization and the finite element method.An asymptotic homogenization approach is employed to obtain the effective thermoelastic properties of the multiphase metamaterials.Theε-constraint multi-objective optimization method is adopted in the formulation.The coefficient of thermal expansion(CTE)and Poisson’s ratio(PR)are chosen as two objective functions,with the CTE optimized and the PR treated as a constraint.The optimization problems are solved by using the method of moving asymptotes.Effective isotropic and anisotropic CTEs and stiffness constants are obtained for the topologically optimized metamaterials with prescribed values of PR under the constraints of specified effective bulk modulus,volume fractions and material symmetry.Two solid materials along with one additional void phase are involved in each of the 2-D and 3-D optimal design examples.The numerical results reveal that the newly proposed approach can integrate shape and topology optimizations and lead to optimal microstructures with distinct topological boundaries.The current method can topologically optimize metamaterials with a positive,negative or zero CTE and a positive,negative or zero Poisson’s ratio. 展开更多
关键词 Topology optimization thermoelastic metamaterial level set method sensitivity analysis Poisson’s ratio coefficient of thermal expansion effective elastic properties
下载PDF
CALCULUS ON CANTOR TRIADIC SET (I)-DERIVATIVE
18
作者 XI LIFENG 《Applied Mathematics(A Journal of Chinese Universities)》 SCIE CSCD 1997年第4期483-492,共10页
For real valued functions defined on Cantor triadic set, a derivative with corresponding formula of Newton Leibniz’s type is given. In particular, for the self similar functions and alternately jumping f... For real valued functions defined on Cantor triadic set, a derivative with corresponding formula of Newton Leibniz’s type is given. In particular, for the self similar functions and alternately jumping functions defined in this paper, their derivative and exceptional sets are studied accurately by using ergodic theory on Σ 2 and Duffin Schaeffer’s theorem concerning metric diophantine approximation. In addition, Haar basis of L 2(Σ 2) is constructed and Haar expansion of standard self similar function is given. 展开更多
关键词 FRACTAL derivative on Cantor set exceptional set ergodic theory DUFFIN schaeffer’ s theorem
下载PDF
NRS下多证据融合的混凝土桥梁耐久性评估模型 被引量:2
19
作者 张永良 郑大为 《中国安全科学学报》 CAS CSCD 北大核心 2023年第1期169-176,共8页
为准确评估混凝土桥梁的耐久性,提出基于邻域粗糙集(NRS)与D-S证据理论的评估模型。首先,根据混凝土桥梁的结构特征,构建耐久性评估指标体系,并建立起耐久性评估数据库;其次,结合数据库,采用NRS的上下近似定义,确定不同评估指标的基本... 为准确评估混凝土桥梁的耐久性,提出基于邻域粗糙集(NRS)与D-S证据理论的评估模型。首先,根据混凝土桥梁的结构特征,构建耐久性评估指标体系,并建立起耐久性评估数据库;其次,结合数据库,采用NRS的上下近似定义,确定不同评估指标的基本信度分配,并基于各指标的综合权重构造证据折扣因子,实现对初始基本信度分配的修正;然后,通过D-S证据理论合成规则进行融合,得出耐久性状态等级命题的置信度,进而根据最大隶属原则确定耐久性状态等级;最后,以多座在役混凝土桥梁的实测数据进行算例验证。结果表明:利用该模型获得的耐久性评估结果与现场实测结果一致,相较于传统的评估模型,该模型不仅能更准确地评估混凝土桥梁的耐久性,而且,能通过置信度反映耐久性的劣化趋势,这可为混凝土桥梁的维修加固、养护提供参考依据。 展开更多
关键词 邻域粗糙集(NRs) 混凝土桥梁 耐久性评估 基本信度分配 综合权重 D-s证据理论
下载PDF
不同超声成像参数对S-Detect技术用于乳腺结节良恶性鉴别诊断中的影响
20
作者 金启成 吕江红 +4 位作者 许立龙 魏洪芬 汤桐芳 张传菊 李世岩 《实用医学杂志》 CAS 北大核心 2023年第22期2891-2897,共7页
目的探讨超声成像参数对S-Detect技术诊断结果产生的影响。方法前瞻性收集2021年10月至2022年3月因乳腺结节在浙江大学医学院附属邵逸夫医院就诊的患者,共纳入133例患者(143个结节)。设置5种超声成像参数条件,包括基准(单焦点、焦点位... 目的探讨超声成像参数对S-Detect技术诊断结果产生的影响。方法前瞻性收集2021年10月至2022年3月因乳腺结节在浙江大学医学院附属邵逸夫医院就诊的患者,共纳入133例患者(143个结节)。设置5种超声成像参数条件,包括基准(单焦点、焦点位于病灶中部水平、病灶深度适合)、双焦点、焦点位置过浅、焦点位置过深、扫查深度过深。分别存储在不同超声成像参数下获得的超声图像,并应用S-Detect技术对图像进行分析解读。比较基准参数设置与其他参数设置之间的诊断结果一致性及超声特征判读的一致性。并以病理结果为“金标准”,比较各个参数设置条件下的诊断效能。结果扫查深度过深与基准条件的诊断一致性(kappa=0.771)较其他设置更低,对于形状(kappa=0.489)及内部回声(kappa=0.442)这两个超声特征判读的一致性也较其他设置低。同时诊断效能(AUC=0.716)为各个设置中的最低者,且与基准设置的诊断效能差距最大。其他各项参数条件与基准条件的一致性较好,诊断效能与基准条件之间无显著性差异。结论对比基准参数设置,在不同成像参数设置中,扫查深度过深条件下的诊断一致性、超声特征判读一致性、诊断效能均较其他条件更低。因此应用S-Detect技术时应避免采用过深的扫查深度。 展开更多
关键词 人工智能 s-Detect技术 成像参数 超声 乳腺结节
下载PDF
上一页 1 2 43 下一页 到第
使用帮助 返回顶部