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:马涛 程好堂 高强[1] 高晓龙 MA Tao;CHENG Haotang;GAO Qiang;GAO Xiaolong(CT Room,Taihe County Hospital of Traditional Chinese Medicine,Fuyang,Anhui Province 236600,China;Department of Radiology,Luodian Hospital,Baoshan District,Shanghai 201908,China)
机构地区:[1]太和县中医院CT室,安徽阜阳236600 [2]上海市宝山区罗店医院放射科,上海201908
出 处:《实用放射学杂志》2023年第9期1448-1452,共5页Journal of Practical Radiology
基 金:罗店医院院级课题(2019-A-3)。
摘 要:目的 探讨基于增强CT动脉期影像组学模型术前预测胃癌淋巴结转移(LNM)的价值.方法 回顾性收集 296 例胃癌患者的影像图像及临床资料,按 7 ︰ 3 随机分为训练组(n=207)及验证组(n=89).对验证组采用单因素及多因素回归分析比较临床变量和LNM情况.对放射组学特征采用组间一致性分析后,使用最小绝对收缩和选择算子(LASSO)算法筛选最佳特征并构建影像组学评分(Radscore).最终构建临床、Radscore及临床+ Radscore的组合模型.结果 基于临床+放射组学特征建立的预测模型具有出色的 LNM检测性能.校准图和临床决策曲线显示出良好的临床校准度和临床实用性.结论 基于增强 CT 动脉期CT纹理特征及临床因素建立的列线图对术前预测胃癌患者有无 LNM具有较大潜力.Objective To construct and validate the radiologic nomogram based on the radiologic characteristics and clinical data of enhanced CT,which can be used for preoperative diagnosis of gastric cancer patients to predict lymph node metastasis(LNM).Methods A total of 296 patients with gastric cancer were divided into training group(n=207)and verification group(n=89)ran-domly according to the ratio of 7:3.The clinical variables and LNM of the validation group were compared by single factor and multiple factor regression analysis,respectively.The radiologic features were analyzed via inter group consistency analysis,and the least absolute shrinkage and selection operator(LASSO)regression method was further used to screen the best features and con-struct the Radscore.The clinical,Radscore and clinical combined with Radscore models were finally constructed.Results The excel-lent detective performance of LNM was presented via predictive model based on clinical and radiological characteristics.The calibra-tion chart and clinical decision curve showed good clinical calibration and practicability.Conclusion The nomogram based on enhanced CT texture features and clinical factors has great potential to predict LNM in gastric cancer patients before operation.
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