CT征象及能谱定量参数Nomogram模型鉴别直肠癌肠周脂肪癌性浸润与炎性浸润

A radiomic nomogram based on morphological CT features combined with quantitative dual-source CT dual-energy in distinguishing pericolic infiltration in rectal adenocarcinoma

目的:联合CT征象及能谱定量参数建立基于Logistic回归的Nomogram预测模型鉴别有浸润征象的直肠癌肠周脂肪是癌性浸润还是炎性浸润。方法:搜集能谱增强CT检查肠周脂肪具有浸润征象的直肠癌患者62例,根据病理结果分为癌性浸润组32例,炎性浸润组30例。比较两组CT征象及能谱参数的差异,筛选鉴别诊断意义较大的特征建立Logistic回归模型,绘制Nomogram、ROC曲线图及校准曲线图。结果:鉴别意义较大的特征为肠周淋巴结增大(短径≥5mm)、动脉期水浓度差(Water差)和有效原子序数(Effective-Z)、静脉期Water差和碘浓度差(Iodine差)、延迟期Water差和标准化碘浓度差(NIC差)。上述七个特征纳入多因素Logistic回归模型绘制Nomogram,模型符合率为95.2%,ROC曲线下面积(AUC)为0.986,预测能力校准曲线示预测浸润和实际浸润一致性较高。结论:基于CT征象及能谱CT定量参数建立Nomogram预测模型在鉴别有浸润征象的直肠癌肠周脂肪是否伴随癌性浸润有重要价值。

Objective:To establish a morphological CT features combined with quantitative dual-source CT dual-energy-based radiomics nomogram for distinguishing pericolic fat infiltration in rectal adenocarcinoma.Methods:62 patients with signs of perirectal fat infiltration by energy spectrum contrast CT scan were divided into two groups according to pathology:cancerous infiltration group(N=32);inflammatory infiltration group(N=30).CT signs as well as energy spectrum parameters were compared,the most significant features were selected to establish a multivariate Logistic regression model,and nomogram,ROC curve and calibration curve were drawn.Results:Characteristics highly significant were presence of mesorectal lymph node enlargement(diameter≥5mm),Water difference and Effective-Z(arterial phase),Iodine difference and Water difference(venous phase),and Water difference and NIC difference(delayed phase).A multivariate Logistic regression analysis was applied to build a radiomics nomogram with seven characteristics.The diagnostic accuracy of this model was 95.2%,and the AUC was 0.986.The calibration curve revealed a high level of consistency between predicated infiltration and actual infiltration.Conclusions:The morphological CT features combined with quantitative dual-source CT dual-energy-based radiomics nomogram might be helpful for differentiating pericolic fat infiltration in rectal adenocarcinoma.