基于增强双期CT成像的肺亚厘米结节良恶性预测模型

目的  分析基于增强双期CT成像的肺亚厘米结节良恶性预测模型。方法  选择我院2019年1月~2021年3月收治的98例肺亚厘米结节患者作为研究对象，依照病理诊断结果分为良性病变组（n=64）和恶性病变组（n=34）。所有受试者行基于增强双期CT成像，采用Logistic回归模型分析增强双期CT成像预测结节良恶性预测模型，绘制ROC曲线分析增强双期CT成像的肺亚厘米结节良恶性预测模型的应用价值。结果  良性病变组患者毛刺、结节边界清楚、上叶、分叶征、空泡征、胸膜凹陷征、血管集束征、磨玻璃密度发生率与恶性病变组的差异有统计学意义（P < 0.05）；增强双期CT成像预测肺亚厘米结节良恶性预测模型为Log(P)=1.211×毛刺+2.843×分叶+1.981×磨玻璃+0.793×边界不清+1.326；增强双期CT成像预测肺亚厘米结节良恶性预测模型预测患者肺亚厘米结节良恶性的曲线下面积为0.930（P < 0.05）。结论  基于增强双期CT成像预测肺亚厘米结节良恶性模型临床价值较高，具有较高的预测价值。

Model for predicting the benignity and malignancy of pulmonary sub-centimetre nodules based on enhanced dual-phase CT imaging

  Objective  To analyze the prediction model of benign and malignant pulmonary sub-centimeter nodules based on enhanced dual-phase CT imaging.  Methods  Ninty-eight patients with pulmonary sub-centimeter nodules treated in our hospital from January 2019 to March 2021 were selected as the research objects, and divided into benign group (n=64) and malignant group (n=34) according to the pathological diagnosis. All the subjects underwent enhanced two-phase CT imaging, and a logistic regression model was used to analyze the predictive model of benign and malignant nodules by enhanced dual phase CT imaging, and ROC curve was drawn to analyze the application value of the predictive model of benign and malignant pulmonary sub-centimeter nodules by enhanced dual phase CT imaging.  Results  There were significant differences in the incidence of burr, clear nodule boundary, upper lobe, lobar sign, vacuole sign, pleural depression sign, vascular bundle sign and ground glass density between benign lesions and malignant lesions (P < 0.05). The prediction model for predicting the benignity and malignancy of pulmonary sub-centimeter nodules by enhanced duplex CT imaging was Log(P) =1.211×burr + 2.843×lobulation+1.981×groundglass+0.793×unclearboundary+1.326; The area under curve of enhanced dual phase CT imaging in predicting the benign and malignant of pulmonary sub-centimeter nodules was 0.930 (P < 0.05).  Conclusion  the model for predicting the benignity and malignancy of pulmonary sub-centimeter nodules based on enhanced dual phase CT imaging has high clinical value and high predictive value.