Clinical Analysis Of High Resolution CT Combined With Tumor Markers For Judgement Of Benign And Malignant Solitary Pulmonary Nodules

Objective:To explore the value of imaging combined with tumor markers in the diagnosis of benign and malignant SPN,and establish a mathematical prediction model of benign and malignant SPN by single factor and multiple factors analysis.Methods:A retrospective analysis of 97 cases with solitary pulmonary nodules in the Department of thoracic surgery of Affiliated Hospital of Guilin Medical University from January 2015 to December 2016,the high resolution CT scan of chest confirmed solitary pulmonary nodules,they all underwent thoracoscopic surgery and pathologically confirmed were benign or malignant.Collecting clinical and imaging characteristics of patients,include age,gender,smoking history,family history of cancer,tumor history,nodule diameter,location,boundary conditions,lobulation,spicule sign,vascular convergence sign,pleural indentation sign,cavitation,calcification,CEA,NSE,Cyfra21-1 and SCCA,and analyze its relationship with SPN lesions.Results:Univariate analysis showed that patients with benign and malignant SPN in age,smoking history,nodule diameter,border,lobulation and spicule sign,pleural indentation,CEA,NSE,Cyfra21-1,SCCA were statistically significant(P<0.05),multivariate logistic regression analysis showed that there were statistically significant differences in nodule maximum diameter,spicule sign,boundary,Cyfra21-1,CEA between benign and malignant SPN(P<0.05).To determine the independent risk factors of the properties of SPN.Then establish a mathematical prediction model.P=e~x/(1+e~x),where X=-17.230+(3.175*diameter)+(2.575*boundary)+(3.556*spicule sign)+(1.593*CEA)+(1.577*Cyfra21-1),e is the natural logarithm.According to the prediction model,the P value is taken as the test index,and the pathological diagnosis is the gold standard.The area under the ROC curve of the prediction model is0.989(0.974 to 1.000),and the diagnostic accuracy is high.Conclusion:the combination of high resolution CT imaging data and tumor markers in this study can improve the accuracy of the diagnosis of benign and malignant solitary pulmonary nodules.