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:路丽 柳成良 张力[1] 左超 于淑靖[1] LU Li;LIU Chengliang;ZHANG Li;ZUO Chao;YU Shujing(Department of CT Diagnosis,Cangzhou Central Hospital,Cangzhou 061000,China;Second Department of Ultrasound,Cangzhou Central Hospital,Cangzhou 061000,China;Department of Nuclear Medicine,Cangzhou Central Hospital,Cangzhou 061000,China)
机构地区:[1]沧州市中心医院CT诊断科,河北沧州061000 [2]沧州市中心医院超声二科,河北沧州061000 [3]沧州市中心医院核医学科,河北沧州061000
出 处:《中国中西医结合影像学杂志》2025年第2期208-211,222,共5页Chinese Imaging Journal of Integrated Traditional and Western Medicine
基 金:河北省医学科学研究课题计划资助(20220378)。
摘 要:目的:探讨基于CT增强扫描影像组学联合临床模型鉴别腮腺多形性腺瘤和腺淋巴瘤的价值。方法:回顾性收集经病理证实的腮腺多形性腺瘤(90例)及腺淋巴瘤(70例)患者的临床和影像资料。采用单因素分析筛选出差异有统计学意义的临床数据构建临床模型,应用单因素秩和检验、相关性分析及最小绝对收缩与选择算子(LASSO)算法筛选组学特征并构建影像组学模型,最后构建临床-影像联合模型。将160例按7∶3比例随机分为训练集112例和验证集48例。利用ROC曲线分析各模型的预测效能。结果:利用患者性别、年龄、吸烟史和单发/多发构建临床模型,AUC为0.889(95%CI0.812~0.966)。动脉期、静脉期及2期联合分别有5、4、5个特征用于模型建立,影像组学模型以2期图像联合模型最佳,AUC为0.951(95%CI0.890~1.000)。将临床资料及动静脉期组学特征纳入联合模型,其AUC为0.969(95%CI0.922~1.000),优于其他模型。结论:动静脉期联合模型为腮腺多形性腺瘤与腺淋巴瘤鉴别诊断的优势影像组学模型,临床资料与影像组学联合模型鉴别诊断价值较高。Objective:To explore the value of enhanced CT-based radiomics combined clinical model in the differential diagnosis of pleomorphic adenoma(PA)from Warthin tumor(WT)in the parotid gland.Methods:This retrospective study analyzed 90 PA patients and 70 WT patients.Univariate analysis was used for clinical data selecting,while univariate rank sum test,correlation analysis and LASSO algorithm were used for radiomics features screening.The combined model was established by the selected optimal radiomics model and clinical data.All patients were randomly divided into a training cohort(112 cases)and a validation cohort(48 cases)at a 7∶3 ratio.The ROC curves were used to evaluate the predictive efficacies of each model.Results:The AUC was 0.889(95%CI 0.812—0.966)for clinical model,including sex,age,smoking history and lesion number.Five,four and five radiomics features of arterial-phase,venous-phase and the two-phase combined models were used to establish the radiomics models.The optimal radiomics model was the two-phase combined model,with the AUC of 0.951(95%CI 0.890—1.000).Ultimately the clinical data was added to the optimal radiomic model,the AUC was 0.969(95%CI 0.922—1.000),which was better than that of other models.Conclusions:The combination of arterial-and venous-phase radiomics model is superior to other radiomics models in differentiating PA and WT,and the combined model constructed by the optimal radiomics model and clinical model had a high differential value.
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:3.140.248.104