关键词: 胃腺癌, 淋巴结转移, 增强CT影像, 影像组学, 列线图预测模型

Abstract: Objective To explore its application value of LNM in patients with gastric adenocarcinoma based on the construction of a radiomic nomogram prediction model for preoperative lymph node metastasis in gastric adenocarcinoma using enhanced CT imaging features and parameters.Methods 131 patients with gastric adenocarcinoma who underwent radical gastric cancer surgery(Billroth Ⅱ) + lymph node dissection in our hospital from August 2019 to October 2023 were retrospectively analysed,and the preoperative enhancement CT extracted lesions,histological features of lymph node images,and pathological examination of LNM were recorded respectively,and the statistically significant Enhanced CT image histological features and parameters,multifactorial Logistic regression to analyse the independent risk factors of gastric adenocarcinoma LNM(+) and construct a column-line diagram,and evaluate its performance.The performance and clinical value of the prediction model were evaluated using subject work characteristic(ROC) curves,and the column-line diagram was internally validated.Results The results of univariate analysis showed that the maximum diameter of the tumour,the lymph node status,the short-axis length and volume of the largest lymph node in the lymph node group and the sum of the short-axis lengths of all the lymph nodes were associated with the occurrence of LNM,and the difference was statistically significant(P<0.05);multifactorial Logistic regression analysis suggested that the maximum diameter of the tumour was ≥15mm and the lymph node status was positive in the enhanced CT imaging examination,maximum lymph node short-axis length ≥7mm in the lymph node group,the sum of short-axis lengths of all lymph nodes ≥11mm,and the maximum lymph node short-axis volume ≥300mm³ in the lymph node group were the independent risk factors for gastric adenocarcinoma patients with LNM(+)(P<0.05);the area under the curve of the model was plotted using a ROC curve with an AUC=0.816(95%CI 0.810-0.939),with the sensitivity of 0.91 and the specificity of 0.86.Model validation was performed using the BOOTSTRAP method containing 500 resamples,and the results suggested that the differences between the fitted curves and the ideal curves of the constructed column-line graphical model were not significant,and the validity and reliability were good.Conclusion The radiomic nomogram prediction model based on enhanced CT imaging features and parameters can effectively predict preoperative lymph node metastasis in gastric adenocarcinoma,providing strong support for clinical decision-making in gastric adenocarcinoma patients.

Key words: gastric adenocarcinoma, lymph node metastasis, enhanced CT imaging, radiomics, predictive model