肺混合密度磨玻璃结节中临床影像学信息对淋巴结转移的预测价值

Prediction of Lymph Node Metastasis of Mixed Ground-glass Nodules Based on Clinical Imaging Information

背景与目的 部分胸部计算机断层扫描(computed tomography, CT)上表现为混合磨玻璃结节(mixed ground-glass nodules, mGGNs)的浸润性腺癌(invasive adenocarcinoma, IAC)会出现淋巴结转移,需由亚肺叶切除及纵隔淋巴结采样的术式改为肺叶切除及纵隔淋巴结清扫,故术前进行淋巴结转移的评估对指导手术切除范围及患者预后非常重要。本研究在病理为IAC的大样本mGGN队列中,探索能够预测淋巴结转移的临床和影像学指标,构建mGGN合并淋巴结转移的评估模型。方法 通过收集北京大学人民医院胸外科2014年1月-2019年10月收治的患者信息,筛选胸部CT病变表现为mGGN且术后病理证实为IAC的患者。统计入组患者的临床信息、影像学信息和淋巴结转移状态,并使用基于人工智能技术的肺结节辅助诊断系统(InferRead CT Lung)获取病例的平均密度、实性成分体积、实性成分百分比、质量等三维度量指标,构建CT密度直方图信息。通过应用R软件建立Lasso逻辑斯蒂回归模型分析评估临床影像学指标与淋巴结转移的相关性。结果 研究共纳入883例mGGN患者,其中12例(1.36%)出现淋巴结转移。mGGN中的临床影像信息与淋巴结转移的Lasso回归模型分析显示,既往恶性肿瘤病史、平均密度、实性成分平均密度、毛刺征和三维实性成分百分比具有参考意义。基于Lasso回归模型结果建立mGGN中淋巴结转移的评估模型,曲线下面积为0.899。结论 临床信息结合CT影像信息可以较准确评估mGGN的淋巴结转移情况。

Background and objective Previous studies have shown that lymph node metastasis only occurs in some mixed ground-glass nodules(mGGNs) which the pathological results were invasive adenocarcinoma(IAC).However,the presence of lymph node metastasis leads to the upgrading of tumor-node-metastasis(TNM) stage and worse prognosis of the patients,so it is important to perform the necessary evaluation before surgery to guide the operation method of lymph node.The aim of this study was to find suitable clinical and radiological indicators to distinguish whether mGGNs with pathology as IAC is accompanied by lymph node metastasis,and to construct a prediction model for lymph node metastasis.Methods From January 2014 to October 2019,the patients with resected IAC appearing as mGGNs in computed tomography(CT)scan were reviewed.All the lesions were divided into two groups(with lymph node metastasis or not) according to their lymph node status.Lasso regression model analysis by applying R software was used to evaluate the relationship between clinical and radiological parameters and lymph node metastasis of mGGNs.Results A total of 883 mGGNs patients were enroled in this study,among which,12(1.36%) showed lymph node metastasis.Lasso regression model analysis of clinical imaging information in mGGNs with lymph node metastasis showed that previous history of malignancy,mean density,mean density of solid components,burr sign and percentage of solid components were informative.Prediction model for lymph node metastasis in mGGNs was developed based on the results of Lasso regression model with area under curve=0.899.Conclusion Clinical information combined with CT imaging information can predict lymph node metastasis in mGGNs.