病变周围区域与病变内部区域的MRI影像组学特征对临床显著性前列腺癌的诊断价值

Comparison of value of perilesional and intralesional radiomics features for diagnosis of clinically significant prostate cancer

目的比较前列腺病变周围区域(PLV)与病变内部区域(ILV)的MRI影像组学特征对临床显著性前列腺癌(csPCa)的诊断价值。方法回顾性分析140例进行过前列腺MRI检查的患者(训练集112例,测试集28例)。分别在T2加权成像(T2WI)、表观弥散系数(ADC)、动态对比增强磁共振成像(DCE-MRI)勾画可疑病变区域及病变周围区域,并提取影像组学特征,运用单变量分析及最小绝对值收敛和选择算子(LASSO)筛选特征,LASSO回归结合10折交叉验证建立预测模型,运用受试者操作特征曲线下面积(AUC)、德隆检验(Delong test)分别对模型进行评估及比较。结果ILV模型的在训练集及测试集中的AUC分别为0.91、0.91,PLV模型的在训练集及测试集中的AUC分别为0.89、0.87。两预测模型在训练集与测试集中的诊断效能差异均无统计学意义。结论前列腺病变周围区域的MRI影像组学特征对于csPCa的诊断价值低于病变内部区域的MRI影像组学特征的诊断价值。

Objective To compare value of perilesional volume(PLV)and intralesional volume(ILV)radiomics features for diagnosis of clinically significant prostate cancer.Methods One hundred and forty patients who received prostate magnetic resonance imaging(MRI)examination(training set 112,testing set 28)was respectively analyzed.ILV and PLV were segmented on T2 weighted imaging(T2WI),apparent diffusion coefficient(ADC)map,dynamic contrast enhanced magnetic resonance imaging(DCE-MRI),respectively.Radiomic features extracted from ILV and PLV were selected via univariate analysis and least absolute shrinkage and selection operator(LASSO)combined with 10-fold cross validation.ILV and PLV prediction models were built based on LASSO regression.Area under receiver operating characteristic curve(AUC)and DeLong test were used to evaluate and compare the models.Results AUC of ILV model in training and testing set were 0.91,0.91,respectively.AUC of PLV model in training and testing set were 0.89,0.87,respectively.Prediction ability of two models were not significantly different.Conclusion The value of PLV radiomics features was lower than ILV radiomics features for diagnosis of csPCa.There was no significant difference between them.