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:李瑞 陈吉虎 刘浩 鄂林宁 LI Rui;CHEN Jihu;LIU Hao;ELinning(Department of Radiology,Shanzi Bethune Hospital,Taiyuan 030024,China;Beijing Yizhun Medical AI Co.Ltd.,Beijing 100088,China)
机构地区:[1]山西白求恩医院放射科,山西太原030024 [2]北京医准智能科技有限公司,北京100088
出 处:《实用放射学杂志》2022年第10期1629-1632,共4页Journal of Practical Radiology
摘 要:目的运用影像组学评估Ⅲ期结肠腺癌患者术后3年复发的预测价值。方法回顾性选取Ⅲ期结肠腺癌患者163例,以7GA9553比例随机分为训练组(n=114)和验证组(n=49)。运用达尔文智能科研平台从图像中提取影像组学特征,筛选后构建影像组学模型,联合临床因素与影像组学模型建立联合模型并制作列线图,绘制受试者工作特征(ROC)曲线评价模型预测效能,基于列线图计算患者术后复发风险系数。结果共提取1316个影像学特征,降维后筛选出4个价值较大特征。Logistic多因素分析结果显示,影像组学模型有良好诊断效能,曲线下面积(AUC)为0.72[95%置信区间(CI)0.66~0.97];联合模型进一步提高了预测效能,AUC为0.75(95%CI 0.62~0.89);基于联合模型建立列线图区分高风险组和低风险组术后复发患者数差异有统计学意义(P<0.01)。结论影像组学可作为量化工具预测Ⅲ期结肠腺癌复发风险,影像组学特征联合临床资料(术前CA19-9水平)模型表现出更优越的预测效能。ObjectiveTo evaluate the predictive value in the application of radiomics in 3-year postoperative recurrence of stage Ⅱ colon adenocarcinoma.Methods A total of 163 patients with stage II colon adenocarcinoma were analyzed restrospectively and randomly divided into the training group(n=114)and the verification group(n=49)at a ratio of 7:3.Darwin intelligent scientific research platform was adopted to extract radiomics features from images,among which screening were performed to construct the radiomics model.Combined with clinical factors and radiomics model,the joint model was established,the nomogram was made and receiver operating characteristic(ROC)curve was drawn to evaluate the predictive effectiveness of the model.The postoperative recurrence risk coefficient of each patient was calculated based on nomogram.Results A total of 1316 imaging features were extracted and 4 features with great value were selected after dimension reduction.As demonstrated by Logistic multivariate analysis,the radiomics model had good diagnostic efficiency with area under the curve(AUC)at 0.72[95%confidence interval(CI)0.66-0.97],the joint model further improved the predictive effectiveness with AUC of 0.75(95%CI 0.62-0.89),and there was statistical significance difference in the number of patients with postoperative recurrence between high-risk group and low-risk group based on nomogram(P<0.01).Conclusion Radiomics can be used as a quantitative tool to predict the recurrence risk of stage Ⅱ colon adenocarcinoma,and the combination of radiomics features and clinical data(preoperative CA19-9 level)shows superior predictive effectiveness.
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:216.73.216.117