基于增强CT影像组学模型预测胰十二指肠切除术后胰瘘

Radiomics model based on enhanced CT for predicting pancreatic fistula after pancreaticoduodenectomy

目的评估基于术前腹部增强CT影像组学模型预测胰十二指肠切除术(PD)术后胰瘘(POPF)的价值。方法回顾性分析252例接受PD患者的术前腹部增强CT资料,按7∶3比例将其分为训练集(n=177)和验证集(n=75)。于训练集增强静脉期CT图像中勾画胰腺实质作为感兴趣容积(VOI),提取其影像组学特征,并筛选最优特征建立影像组学模型;绘制模型预测PD术后POPF的受试者工作特征(ROC)曲线,计算曲线下面积(AUC),评价模型预测效能;以验证集数据进行验证。结果共选出14个最优影像组学特征用于构建影像组学模型。影像组学模型在训练集和验证集的AUC分别为0.82[95%CI(0.76,0.88)]和0.82[95%CI(0.72,0.91)]。结论基于术前增强CT影像组学模型能有效预测PD术后POPF。

Objective To observe the value of radiomics model based on enhanced CT for predicting postoperative pancreatic fistula(POPF)in patients after pancreaticoduodenectomy(PD).Methods Preoperative abdominal enhanced CT data of 252 patients after PD were retrospectively analyzed.The patients were divided into training set(n=177)and validation set(n=75)at the ratio of 7∶3.The pancreatic parenchyma was delineated as volume of interest(VOI)on enhanced venous CT images of training set.The radiomics features of VOI were extracted,and the optimal radiomics features were selected for establishing radiomics model for predicting POPF.Receiver operating characteristic(ROC)curve of the radiomics model was drawn,and the corresponding area under the curve(AUC)was calculated to evaluate the predictive efficacy of the model.Then the model was verified with data of validation set.Results After screening,14 optimal radiomics features were obtained to construct the radiomics models.AUC of the radiomics model in training set and validation set were both 0.82(95%CI[0.76,0.88])and 0.82(95%CI[0.72,0.91]).Conclusion Radiomics model based on preoperative enhanced CT could effectively predict POPF after PD.