基于Myrian影像后处理系统鉴别肺部小结节良恶性质及构建列线图预测模型  

Identification of Benign and Malignant Pulmonary Nodules Based on Myrian Image Post-processing System and Establishment of a Nomograph Predictive Model

作　　者：朱斌 贺清明[1] ZHU Bin;HE Qingming(Yangjialing Campus of Medical College of Yan’an University,Yan’an 716000,China)

机构地区：[1]延安大学医学院杨家岭校区,陕西延安716000

出　　处：《湖北民族大学学报（医学版）》2022年第1期52-55,60,共5页Journal of Hubei Minzu University(Medical Edition)

摘　　要：目的探讨基于Myrian影像后处理系统鉴别肺部单发小结节良恶性质,并构建列线图预测模型以提高临床早期鉴别肺部恶性结节的准确性。方法回顾性总结2019年2月-2021年2月延安大学附属医院诊断为肺部单发小结节患者112例(结节直径8~30 mm),经64层螺旋CT增强扫描和Myrian影像后处理系统重建,良恶性质经CT引导穿刺活检或手术病理证实,其中恶性结节40例(恶性组),良性结节72例(良性组)。采用单因素比较两组患者性别、年龄、结节位置、结节直径、结节内部和外部纹理特征,其中内部特征包括分叶、空洞、钙化、血流信号,外部纹理特征包括毛刺、不规则、支气管征和血管束。采用多因素Logistic回归分析筛选影响性质判断的危险因素,绘制列线图预测模型,受试者工作曲线(ROC)计算模型预测的准确性,Hosmer-Lemeshow检验计算预测效能。结果恶性组年龄高于良性组,结节内部和外部纹理特征数量多于良性组(P<0.05),两组性别、结节位置、结节直径比较,差异无统计学意义(P>0.05)。Logistic回归分析筛选发现,患者年龄、结节直径、结节内部和外部纹理特征数量是性质判断的独立危险因素(P<0.05)。列线图预测模型显示,患者年龄和结节直径越大,结节内部和外部纹理特征数量越多,提示恶性结节的可能性越高。ROC分析显示,该模型预测的准确性为0.896;Hosmer-Lemeshow检验计算预测效能为91.07%,拟合效果良好。结论基于Myrian影像后处理系统能够更加清晰、准确提供更多肺部单发小结节信息,并构建恶性结节性质判断的列线图预测模型,主要指标包括患者年龄、结节直径、结节内部和外部纹理特征数量,有较好的准确性和应用价值。Objective To evaluate the value of Myrian image post-processing system for identification of benign and malignant pulmonary nodules and establish a nomograph predictive model,so as to improve the accuracy for early clinical differentiation of pulmonary malignant nodules.Methods From February 2019 to February 2021,112 patients with small solitary pulmonary nodules(nodule diameter from 8mm to 3cm)in our hospital were retrospectively summarized.After 64 slice spiral CT enhanced scanning and reconstruction by Myrian image post-processing system,the benign and malignant nature was confirmed by CT guided puncture biopsy or surgical pathology,including 40 patients of malignant nodules(malignant group)and 72 patients of benign nodules(benign group).Single factor analysis was used to compare the gender,age,nodule location,nodule diameter,internal and external texture characteristics between the two groups.The internal features included lobulation,cavity,calcification,blood flow signal,and the external texture features included burr,irregularity,bronchial sign and vascular bundle.Then multivariate Logistic regression analysis was used to screen the risk factors affecting the quality judgment,and the nomograph predictive model was drawn.The receiver operating curve(ROC)was used to calculate the accuracy of the model prediction,and the Hosmer-Lemeshow test was used to test the prediction efficiency.Results The age of malignant group was higher than that of benign group,and the numbers of internal and external texture characteristics of nodules increased(P<0.05),but there were no differences in gender,nodule location and nodule diameter between the two groups(P>0.05).Logistic regression analysis showed that age,nodule diameter,the numbers of internal and external texture characteristics were independent risk factors(P<0.05).The nomograph predictive model showed that the larger the patient’s age and nodule diameter,the more number the internal and external texture features of nodules,the higher possibility of malignant nodul

关 键 词：肺部小结节 良恶性质 Myrian影像后处理系统 列线图预测模型 

分 类 号：R816.41[医药卫生—放射医学]