检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:李梦园 付泽辉 李蔚 张剑[1] 卢叶君[1] 褚一川 陈卉[1] Li Mengyuan;Fu Zehui;Li Wei;Zhang Jian;Lu Yejun;Chu Yichuan;Chen Hui(Department of Ultrasound,The Third Affiliated Hospital of Soochow University,Changzhou,Jiangsu 213000,China)
机构地区:[1]苏州大学附属第三医院(江苏省常州市第一人民医院)超声医学科,江苏省常州市213000
出 处:《中国超声医学杂志》2024年第9期968-971,共4页Chinese Journal of Ultrasound in Medicine
摘 要:目的探讨人工智能S-Detect技术对水平位生长的甲状腺结节良恶性的诊断价值。方法回顾性分析经手术病理证实的183个水平位生长的甲状腺结节的声像图资料。以病理结果为金标准,比较良恶性结节的常规超声特征及S-Detect技术诊断结果的差异,绘制结节超声特征模型及超声特征联合S-Detect技术模型,并采用受试者工作特征(ROC)曲线和Z检验分析比较两种预测模型的诊断效能。结果结节最大径、内部回声、是否存在微钙化及S-Detect技术诊断结果是水平位生长的甲状腺结节良恶性的独立预测因子。超声特征联合S-Detect技术模型诊断的曲线下面积、准确度及特异度均高于超声特征模型(P<0.05)。结论S-Detect技术对水平位生长的甲状腺结节良恶性的鉴别具有重要诊断价值。Objective To evaluate the auxiliary diagnostic value of artificial intelligence(AI)S-Detect technology in distinguishing between benign and malignant wider-than-tall thyroid nodules.Methods A retrospective analysis was performed on the ultrasonographic data of 183 case of wider-than-tall thyroid nodules confirmed by surgery and pathology.Based on the pathological results as the gold standard,comparing conventional ultrasound features and S-Detect diagnostic results between groups,and developing ultrasound feature model and ultrasound combined with S-Detect diagnostic model,The diagnostic efficacy of each prediction model was analyzed and compared using the re-ceiver operating characteristic(ROC)curve and Z-tests.Results Lesion maximum diameter,microcalcifications,and S-Detect diagnostic results were identified as independent predictors for the wider-than-tall thyroid nodules.The diag-nostic sensitivity,accuracy and the area under the curve of the ultrasound combined with S-Detect diagnostic model was higher than that of the ultrasound feature model(P<0.05).Conclusions There is an auxiliary diagnostic value for S-Detect technology to discriminate the benign and malignant feature of wider-than-tall thyroid nodules.
关 键 词:S-Detect技术 水平位生长 甲状腺结节 超声 诊断价值
分 类 号:R445.1[医药卫生—影像医学与核医学] R581[医药卫生—诊断学]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.190