摘要
目的探究基于电子计算机断层扫描(CT)的影像组学联合肺癌三项肿瘤标志物预测肺癌病理分级的价值。方法选取2021年8月至2023年12月本院收治的153例肺癌患者为研究对象,以病理学检查结果为“金标准”,将患者分为低分化组(106例)和中分化组(47例)。所有患者均接受CT及肺癌三项肿瘤标志物[血清癌胚抗原(CEA)、神经元特异性烯醇化酶(NSE)、细胞角蛋白19片段(Cyfra21-1)]检查,比较不同病理分级患者的CT检查结果及CEA、NSE、Cyfra21-1差异,并分析CT影像组学联合肺癌三项肿瘤标志物预测肺癌病理分级的价值。结果中分化组患者CEA、NSE、Cyfra21-1均较低分化组低,差异均具有统计学意义(P<0.05)。CT检查灵敏度、特异度及准确度分别为82.08%、78.72%、81.05%。受试者工作特征曲线(ROC)分析结果显示,CEA、NSE、Cyfra21-1及CT影像组学联合CEA、NSE、Cyfra21-1预测肺癌患者病理分级的AUC值分别为0.774、0.758、0.742、0.829,特异度分别为74.14%、78.22%、77.15%、87.3 3%,灵敏度分别为71.98%、77.25%、74.86%、85.49%,联合检测AUC值、特异度、灵敏度均高于单—检测(P<0.05)。结论CT影像组学联合肺癌三项肿瘤标志物(CEA、NSE、Cyfra21-1)在预测肺癌病理分级方面具有—定诊断价值。
Objective To explore the value of computed tomography(CT)based imaging combined with three tumor markers in predicting the pathological grade of lung cancer.Methods A total of 153 patients with lung cancer admitted to our hospital from August 2021 to December 2023 were selected as the study objects.Using pathological examination results as the gold standard,the patients were divided into low-differentiation group(106 cases)and medium-differentiation group(47 cases)according to pathological grade.All patients were examined by CT and three tumor markers of lung cancer(serum carcinoembryonic antigen(CEA),neuron-specific enolase(NSE),and cytokeratin 19 fragment antigen21-1(Cyfra21-1)).CT findings and the differences of CEA,NSE,and Cyfra21-1 among patients with different pathological grades were compared.The value of CT imaging combined with three tumor markers in predicting the pathological grade of lung cancer was analyzed.Results The CEA,NSE and Cyfra21-1 in the medium-differentiated group were lower than those in the low-differentiated group,and the differences were statistically significant(P<0.05).The sensitivity,specificity and accuracy of CT examination were 82.08%,78.72%,and 81.05%,respectively.ROC curve analysis results showed that the AUC values of CEA,NSE,Cyfra21-1 and CT imaging combined with CEA,NSE and Cyfra21-1 to predict the pathological grade of lung cancer patients were 0.774,0.758,0.742,0.829,respectively.The specificity was 74.14%,78.22%,77.15%,87.33%,and the sensitivity was 71.98%,77.25%,74.86%,85.49%,respectively.The AUC value,specificity and sensitivity of combined detection were higher than that of single detection(P<0.05).Conclusion CT imaging combined with three tumor markers of lung cancer(CEA,NSE,Cyfra21-1)has certain diagnostic value in predicting the pathological grade of lung cancer.
作者
赵亮
李晋
ZHAO Liang;LI Jin(Medical Imaging Center,Changzhi People's Hospital,Changzhi 046000,Shanxi Province,China;Department of Respiratory and Critical Care Medicine,Changzhi People's Hospital,Changzhi 046000,Shanxi Province,China)
出处
《中国CT和MRI杂志》
2025年第8期59-62,共4页
Chinese Journal of CT and MRI
