检索结果-南通市图书馆

Deep learning model combined with computed tomography features to preoperatively predicting the risk stratification of gastrointestinal stromal tumors

引用

World Journal of Gastrointestinal Oncology 2024年第12期16卷 4663-4674页

作者： Yi Li Yan-Bei Liu Xu-Bin Li Xiao-Nan Cui Dong-Hua Meng cong-cong yuan Zhao-Xiang Ye Department of Radiology Tianjin Medical University Cancer Institute and HospitalNational Clinical Research Center for CancerTianjin’s Clinical Research Center for CancerState Key Laboratory of Druggability Evaluation and Systematic Translational MedicineTianjin Key Laboratory of Digestive CancerTianjin 300060China School of Life Sciences Tiangong UniversityTianjin 300387China Department of Radiology Tianjin First Central HospitalTianjin 300190China

BACKGROUND Gastrointestinal stromal tumors(GIST)are prevalent neoplasm originating from the gastrointestinal *** 50%of GIST patients experience tumor recurrence within 5 ***,there is a pressing need to accurately evaluate risk stratification *** To assess the application of a deep learning model(DLM)combined with computed tomography features for predicting risk stratification of *** Preoperative contrast-enhanced computed tomography(CECT)images of 551 GIST patients were retrospectively *** image features were independently analyzed by two *** parameters were statistically analyzed to identify significant predictors of high-risk *** were randomly assigned to the training(n=386)and validation cohorts(n=165).A DLM and a combined DLM were established for predicting the GIST risk stratification using convolutional neural network and subsequently evaluated in the validation *** Among the analyzed CECT image features,tumor size,ulceration,and enlarged feeding vessels were identified as significant risk predictors(P<0.05).In DLM,the overall area under the receiver operating characteristic curve(AUROC)was 0.88,with the accuracy(ACC)and AUROCs for each stratification being 87%and 0.96 for low-risk,79%and 0.74 for intermediate-risk,and 84%and 0.90 for high-risk,*** overall ACC and AUROC were 84%and 0.94 in the combined *** ACC and AUROCs for each risk stratification were 92%and 0.97 for low-risk,87%and 0.83 for intermediate-risk,and 90%and 0.96 for high-risk,*** in AUROCs for each risk stratification between the two models were significant(P<0.05).CONCLUSION A combined DLM with satisfactory performance for preoperatively predicting GIST stratifications was developed using routine computed tomography data,demonstrating superiority compared to DLM.

关键词： Gastrointestinal stromal tumors Deep learning Risk stratification Tomography,X-ray computed Prognosis

来源：

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

Peripheral mitochondrial DNA as a neuroinflammatory biomarker for major depressive disorder

引用

Neural Regeneration Research 2025年第6期20卷 1541-1554页

作者： Jinmei Ye cong Duan Jiaxin Han Jinrong Chen Ning Sun yuan Li Tifei yuan Daihui Peng Division of Mood Disorder Shanghai Mental Health CenterShanghai Jiao Tong University School of MedicineShanghaiChina Department of Psychiatry First Hospital of Shanxi Medical UniversityTaiyuanShanxi ProvinceChina Shanghai Key Laboratory of Psychotic Disorders Brain Health InstituteNational Center for Mental DisordersShanghai Mental Health CenterShanghai Jiao Tong University School of MedicineShanghaiChina Co-Innovation Center of Neuroregeneration Nantong UniversityNantongJiangsu ProvinceChina

In the pathogenesis of major depressive disorder, chronic stress-related neuroinflammation hinders favorable prognosis and antidepressant response. Mitochondrial DNA may be an inflammatory trigger, after its release from stress-induced dysfunctional central nervous system mitochondria into peripheral circulation. This evidence supports the potential use of peripheral mitochondrial DNA as a neuroinflammatory biomarker for the diagnosis and treatment of major depressive disorder. Herein, we critically review the neuroinflammation theory in major depressive disorder, providing compelling evidence that mitochondrial DNA release acts as a critical biological substrate, and that it constitutes the neuroinflammatory disease pathway. After its release, mitochondrial DNA can be carried in the exosomes and transported to extracellular spaces in the central nervous system and peripheral circulation. Detectable exosomes render encaged mitochondrial DNA relatively stable. This mitochondrial DNA in peripheral circulation can thus be directly detected in clinical practice. These characteristics illustrate the potential for mitochondrial DNA to serve as an innovative clinical biomarker and molecular treatment target for major depressive disorder. This review also highlights the future potential value of clinical applications combining mitochondrial DNA with a panel of other biomarkers, to improve diagnostic precision in major depressive disorder.

关键词： biomarker cytokine exosomes inflammasome major depressive disorder microglia mitochondrial DNA mitochondrial dysfunction neuroinflammation Toll-like receptor

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

Poorly controlled type Ⅱ diabetes mellitus significantly enhances postoperative chemoresistance in patients with stage Ⅲ colon cancer

引用

World Journal of Gastroenterology 2025年第3期31卷 29-41页

作者： Ruo-Yu Guan Jia-Wei Wu Zi-Yun yuan Zhi-yuan Liu Zi-Zhu Liu Zhi-cong Xiao Jing-Hui Li Cheng-Zhi Huang Jun-Jiang Wang Xue-Qing Yao Guangdong Cardiovascular Institute Guangdong Provincial People’s HospitalGuangdong Academy of Medical SciencesSouthern Medical UniversityGuangzhou 510080Guangdong ProvinceChina Department of Gastrointestinal Surgery Department of General SurgeryGuangdong Provincial People’s Hospital(Guangdong Academy of Medical Sciences)Southern Medical UniversityGuangzhou 510080Guangdong ProvinceChina Department of General Surgery Guangdong Provincial People’s Hospital Ganzhou Hospital(Ganzhou Municipal Hospital)Ganzhou 341000Jiangxi ProvinceChina Shantou University Medical College Shantou 515041Guangdong ProvinceChina School of Medicine South China University of TechnologyGuangzhou 510006Guangdong ProvinceChina Gannan Medical University Ganzhou 341000Jiangxi ProvinceChina

BACKGROUND Type Ⅱ diabetes mellitus(T2DM)has been associated with increased risk of colon cancer(CC)and worse prognosis in patients with *** effects of T2DM on postoperative chemoresistance rate(CRR)and long-term disease-free survival(DFS)and overall survival(OS)in patients with stage Ⅲ CC who receive curative resection remain *** To investigate whether T2DM or glycemic control is associated with worse postoperative survival outcomes in stage Ⅲ *** This retrospective cohort study included 278 patients aged 40-75 years who underwent surgery for stage Ⅲ CC from 2018 to *** on preoperative T2DM history,the patients were categorized into non-DM(n=160)and DM groups(n=118).The latter was further divided into well-controlled(n=73)and poorly controlled(n=45)groups depending on the status of glycemic ***,OS,and CRR were compared between the groups and Cox regression analysis was used to identify risk *** Patients in the DM and non-DM groups demonstrated similar DFS,OS,and CRR(DFS:72.03%vs 78.75%,P=0.178;OS:81.36%vs 83.12%,P=0.638;CRR:14.41%vs 7.5%,P=0.063).Poorly controlled DM was associated with a significantly worse prognosis and higher CRR than well-controlled DM(DFS:62.22%vs 78.07%,P=0.021;OS:71.11%vs 87.67%,P=0.011;CRR:24.40%vs 8.22%,P=0.015).High preoperative fasting plasma glucose[DFS:Hazard ratio(HR)=2.684,P<0.001;OS:HR=2.105,P=0.019;CRR:HR=2.214,P=0.005]and glycosylated hemoglobin levels(DFS:HR=2.344,P=0.006;OS:HR=2.119,P=0.021;CRR:HR=2.449,P=0.009)indicated significantly poor prognosis and high CRR,while T2DM history did not(DFS:HR=1.178,P=0.327;OS:HR=0.933,P=0.739;CRR:HR=0.997,P=0.581).CONCLUSION Increased preoperative fasting plasma glucose and glycosylated hemoglobin levels,but not T2DM history,were identified as risk factors associated with poor postoperative outcomes and high CRR in patients with stage Ⅲ CC.

关键词： Colon cancer Chemoresistance Diabetes mellitus Prognosis TypeⅡdiabetes mellitus

来源：

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

Intestinal glucagon-like peptide-1:A new regulator of impaired counterregulatory responses to hypoglycemia in type 1 diabetes mellitus

引用

World Journal of Diabetes 2025年第1期16卷 217-221页

作者： Le-Rong Liu yuan-yuan Luo Pei-Zhu Su cong Zhang Zhao-Tao Li Department of Endocrinology and Metabolism Nanfang HospitalSouthern Medical UniversityGuangzhou 510515Guangdong ProvinceChina Department of Endocrinology Chongqing University Three Gorges HospitalChongqing 404100China Chongqing Municipality Clinical Research Center for Endocrinology and Metabolic Diseases Chongqing University Three Gorges HospitalChongqing 404100China Department of Endocrinology The Second Affiliated HospitalChongqing Medical UniversityChongqing 400013China Department of Gastroenterology The First People's Hospital of FoshanFoshan 528000Guangdong ProvinceChina

In this article,we review the study by Jin et al,which examined the role of intestinal glucagon-like peptide-1(GLP-1)in counterregulatory responses to hypoglycemia in patients with type 1 diabetes mellitus(T1DM).With the global rise of T1DM,there is an increased burden on society and healthcare *** to insulin therapy and islet dysfunction,T1DM patients are highly vulnerable to severe hypoglycemia,a leading cause of *** healthy individuals,counterregulatory mechanisms restore blood glucose during hypoglycemia,but repeated episodes impair these *** et al demonstrated that overexpression of GLP-1 attenuates the sympathetic-adrenal reflex and disrupts the secretion of counterregulatory hormones such as glucagon during hypoglycemia,leading to counterregulatory *** findings highlight the critical role of GLP-1 in the impaired counterregulatory response to hypoglycemia in T1DM patients and provide new insights into the potential application of GLP-1-related therapies in T1DM patients.

关键词： Glucagon-like peptide-1 Impaired counterregulation Type 1 diabetes mellitus Sympathetic-adrenal reflex Glucagon

来源：

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

Research landmarks on the 60th anniversary of Epstein-Barr virus

引用

Science China(Life Sciences) 2025年第2期68卷 354-380页

作者： Lan-Yi Zhong Chu Xie Le-Le Zhang Yan-Lin Yang yuan-Tao Liu Ge-Xin Zhao Guo-Long Bu Xian-Shu Tian Zi-Ying Jiang Bo-Yu yuan Peng-Lin Li Pei-Huang Wu Wei-Hua Jia Christian Münz Benjamin E.Gewurz Qian Zhong cong Sun Mu-Sheng Zeng State Key Laboratory of Oncology in South China Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and TherapyGuangdong Provincial Clinical Research Center for CancerSun Yat-sen University Cancer CenterGuangzhou 510060China Viral Immunobiology Institute of Experimental ImmunologyUniversity of ZürichZürich 8092Switzerland Division of Infectious Diseases Department of MedicineBrigham and Women’s HospitalBoston MA 02115USA Department of Microbiology Harvard Medical SchoolBoston MA 02115USA Harvard Program in Virology Boston MA 02115USA Broad Institute of Harvard and MIT Cambridge MA 02142USA

Epstein-Barr virus(EBV),the first human oncovirus discovered in 1964,has become a focal point in virology,immunology,and oncology because of its unique biological characteristics and significant role in human *** we commemorate the 60th anniversary of EBV's discovery,it is an opportune moment to reflect on the major advancements in our understanding of this complex *** this review,we highlight key milestones in EBV research,including its virion structure and life cycle,interactions with the host immune system,association with EBV-associated diseases,and targeted intervention strategies.

关键词： Epstein-Barr virus oncovirus immune response epidemiology vaccines antibodies

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

天基单视线测量目标轨道可观性分析及确定方法

引用

航空学报 2025年第3期46卷 47-59页

作者：李佳兴袁利张聪北京控制工程研究所北京100094 空间智能控制技术全国重点实验室北京100094 中国空间技术研究院北京100094

针对利用天基单视线测量信息确定空间目标轨道问题,定义了一种新的可观性指标,分析了高阶摄动项对系统可观性的影响,并给出了单视线测量轨道确定算法。首先,采用李导数推导了系统可观性矩阵,根据系统局部弱可观条件得到了可观性指标,并... 详细信息

针对利用天基单视线测量信息确定空间目标轨道问题,定义了一种新的可观性指标,分析了高阶摄动项对系统可观性的影响,并给出了单视线测量轨道确定算法。首先,采用李导数推导了系统可观性矩阵,根据系统局部弱可观条件得到了可观性指标,并推导了高阶摄动项可观性的近似计算公式。然后,在近圆轨道假设下建立了空间目标和观测平台轨道参数与可观性指标间的关系。之后,提出了适用于单视线测量的迭代最小二乘轨道确定算法,并推导了轨道确定误差协方差矩阵。数字仿真结果表明:空间目标和观测平台的轨道倾角差是影响系统可观性的主要因素,高阶摄动项通过增加矢量异面度来提高系统可观性;观测平台远离其升交点可保证系统可观性;可观性指标越大,目标轨道确定精度越高;位置估计误差标准差受系统可观性和观测时长影响。

关键词：天基单视线测量轨道确定可观性分析李导数迭代最小二乘

来源：

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

Stabilities of delay stochastic McKean-Vlasov equations in the G-framework

引用

Science China(Information Sciences) 2025年第1期68卷 255-277页

作者： Haiyan yuan Quanxin ZHU Department of Mathematics Heilongjiang Institute of Technology Key Laboratory of Computing and Stochastic Mathematics (Ministry of Education) School of Mathematics and Statistics Hunan Normal University

This article focuses on a type of stochastic Mc Kean-Vlasov equation in the G-framework(G-SMVE) and addresses the stability issue for delay stochastic Mc Kean-Vlasov equations in the G-framework(G-SMVDEs). Distribution dependence and uncertainty prevent us from directly applying the stochastic analysis method for stochastic Mc Kean-Vlasov equations(SMVEs)to G-SMVEs directly. To overcome this difficulty, we introduce definitions, including the derivative of a function with a law under the G-expectation and the Lions derivatives. Then we construct a new G-It? formula for G-SMVEs according to the G-It? formula for stochastic differential equations in the G-framework(G-SDEs) and the It? formula for SMVEs. Using the new G-It? formula and the Lyapunov functional method, we investigate the moment exponential stability and almost sure asymptotic stability of G-SMVDEs. To overcome the difficulty in obtaining the distribution dependence of the exact solution to the G-SMVDE, we introduce the empirical measure and the corresponding interacting particle system, and then prove the stability equivalence between the underlying G-SMVDE and the corresponding interacting particle system. Two examples are used to confirm our theoretical results.

关键词： delay stochastic McKean-Vlasov equations Wasserstein distance G-Brownian motion Lions derivative stability

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

面向参数化动作空间的多智能体中心化策略梯度分解及其应用

引用

软件学报 2025年第2期36卷 590-607页

作者：田树聪谢愈张远龙周正春高阳西南交通大学信息科学与技术学院四川成都611756 国防科技大学智能科学学院湖南长沙410073 计算机软件新技术国家重点实验室(南京大学) 江苏南京210023

近年来,多智能体强化学习方法凭借AlphaStar、AlphaDogFight、AlphaMosaic等成功案例展示出卓越的决策能力以及广泛的应用前景.在真实环境的多智能体决策系统中,其任务的决策空间往往是同时具有离散型动作变量和连续型动作变量的参数化... 详细信息

近年来,多智能体强化学习方法凭借AlphaStar、AlphaDogFight、AlphaMosaic等成功案例展示出卓越的决策能力以及广泛的应用前景.在真实环境的多智能体决策系统中,其任务的决策空间往往是同时具有离散型动作变量和连续型动作变量的参数化动作空间.这类动作空间的复杂性结构使得传统单一针对离散型或连续型的多智能体强化学习算法不在适用,因此研究能用于参数化动作空间的多智能体强化学习算法具有重要的现实意义.提出一种面向参数化动作空间的多智能体中心化策略梯度分解算法,利用中心化策略梯度分解算法保证多智能体的有效协同,结合参数化深度确定性策略梯度算法中双头策略输出实现对参数化动作空间的有效耦合.通过在Hybrid Predator-Prey场景中不同参数设置下的实验结果表明该算法在经典的多智能体参数化动作空间协作任务上具有良好的性能.此外,在多巡航导弹协同突防场景中进行算法效能验证,实验结果表明该算法在多巡航导弹突防这类具有高动态、行为复杂化的协同任务中有效性和可行性.

关键词：参数化动作空间多智能体强化学习中心化策略梯度分解多巡航导弹突防

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

开放环境下的协作多智能体强化学习进展

引用

中国科学:信息科学 2025年第2期55卷 217-268页

作者：袁雷张子谦李立和管聪俞扬南京大学计算机软件新技术国家重点实验室南京210023

多智能体强化学习(multi-agent reinforcement learning, MARL)近年来获得广泛关注并在不同领域取得进展.其中,协作多智能体强化学习专注于训练智能体团队以协同完成单智能体难以应对的任务目标,在路径规划、无人驾驶、主动电压控制和... 详细信息

多智能体强化学习(multi-agent reinforcement learning, MARL)近年来获得广泛关注并在不同领域取得进展.其中,协作多智能体强化学习专注于训练智能体团队以协同完成单智能体难以应对的任务目标,在路径规划、无人驾驶、主动电压控制和动态算法配置等场景展现出巨大的应用潜力.如何提升系统协作效能是协作多智能体强化学习领域研究重点之一.以往的研究工作主要在简单、静态和封闭的环境设定中展开.随着人工智能技术落地的驱使,目前在多智能体协作领域也有部分研究开始对开放环境下的多智能体协作展开研究,这些工作从多个方面对智能体所处环境中要素可能发生改变这一情况进行探索与研究,并取得一定进展.但是当前主流工作仍然缺乏对该方向的综述.本文从强化学习概念着手,针对多智能体系统、协作多智能体强化学习、典型方法与测试环境进行介绍,对封闭到开放环境下的协作多智能体强化学习研究工作进行总结,提炼出多类研究方向并对典型工作进行介绍.最后,本文对当前研究的优势与不足进行了总结,对未来开放环境下协作多智能体强化学习的发展方向与待研究问题进行展望,以吸引更多研究人士参与这个新兴方向的研究与交流.

关键词：强化学习多智能体系统多智能体协作开放环境机器学习开放环境多智能体协作

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

基于属性强度关联性矩阵的零样本滚动轴承故障诊断

引用

振动与冲击 2025年第2期44卷 302-311页

作者：苑茹马萍张宏立王聪王瑾春李家声新疆大学电气工程学院乌鲁木齐830017 新疆大学智能科学与技术学院乌鲁木齐830017

针对传统有监督学习模型难以辨别滚动轴承未知类故障的问题,提出一种基于属性强度关联性矩阵的零样本滚动轴承故障诊断模型。首先,利用样本之间属性强度关系对数据库中故障样本进行细粒度描述,建立各故障样本与故障类别间的关联关系;其... 详细信息

针对传统有监督学习模型难以辨别滚动轴承未知类故障的问题,提出一种基于属性强度关联性矩阵的零样本滚动轴承故障诊断模型。首先,利用样本之间属性强度关系对数据库中故障样本进行细粒度描述,建立各故障样本与故障类别间的关联关系;其次,引入自适应深度可分离残差网络提取故障属性相关的特征信息;最后,根据属性细粒度描述和特征信息,使用属性学习模块预测未知类故障的属性,通过计算其与属性矩阵的欧氏距离,实现零样本轴承故障的诊断。试验结果表明,相较于其他模型,该模型在识别未知滚动轴承故障类别方面取得了优异的性能,平均诊断准确率达到90.45%,验证了该模型的有效性与优越性,为实际生产提供了有益的应用价值。

关键词：滚动轴承故障诊断零样本学习属性强度关联性矩阵特征提取属性学习

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

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

在线全文

在线全文

在线全文

在线全文

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

在线全文

在线全文

在线全文

在线全文

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：