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:文荣 高瑞智 林鹏 黄静[1] 万达 何云[1] 杨红[1] Wen Rong;Gao Ruizhi;Lin Peng;Huang Jing;Wan Da;He Yun;Yang Hong(Departiiiciil of Ultrasound,the First Affiliated Hospital of Guangxi Medical University,Nanning,Guangxi Zhuang,530021 China)
机构地区:[1]广西医科大学第一附属医院超声诊断科,南宁市530021
出 处:《中国超声医学杂志》2021年第7期733-736,共4页Chinese Journal of Ultrasound in Medicine
摘 要:目的探讨超声组学鉴别腮腺混合瘤和Warthin瘤的价值。方法选取38例混合瘤及20例Warthin瘤患者作为研究对象。基于感兴趣区的勾选,从腮腺肿瘤的超声图像中提取超声组学特征。通过假设检验及套索回归,从所选特征构建预测模型并评估其诊断效能。结果通过特征提取共获得5 936个超声组学特征。通过假设检验及套索回归,最终纳入2个特征用于诊断模型的构建。超声组学评分模型在训练组的曲线下面积(area under curve, AUC)为0.91,灵敏度为94.1%,特异度为83.3%;验证组的AUC为0.88,灵敏度为100%,特异度为78.6%。结论基于超声的影像组学评分对鉴别腮腺混合瘤和Warthin瘤具有良好的诊断效能。Objective To evaluate the value of ultrasomics in differential diagnosis of pleomorphic adenoma and Warthin tumor of parotid gland. Methods 38 patients with pleomorphic adenoma and 20 patients with Warthin tumor were retrospectively analyzed. Based on the selection of region of interest(ROI), the ultrasomics features were extracted from the ultrasound images of parotid tumors. Then, through hypothesis testing and Least Absolute Shrinkage and Selection Operator regression(LASSO) regression, a prediction model was constructed from the selected features and its diagnostic efficiency was also evaluated. Results Through the feature extraction of ultrasonic images, a total of 5936 ultrasonic features were obtained. Through hypothesis testing and LASSO regression, 2 ultrasomics features were finally included in the construction of the diagnostic model. The area under the curve of training group was 0.91, sensitivity 94.1%, specificity 83.3% and the verification group was 0.88, sensitivity 100%, specificity 78.6%. Conclusions The ultrasomics shows great efficiency in differentiating pleomorphic adenoma from Warthin tumor in parotid gland.
关 键 词:超声组学 腮腺混合瘤 腮腺WARTHIN瘤 鉴别诊断
分 类 号:R445.1[医药卫生—影像医学与核医学] R739.87[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:216.73.216.249