合成MRI定量直方图特征对预测乳腺癌腋窝淋巴结转移状态的价值  

The value of synthetic MRI quantitative histogram features in predicting axillary lymph node metastases of breast cancer

作　　者：王玲廷 周智鹏[1] 余雪燕 刘蒋静 WANG Lingting;ZHOU Zhipeng;YU Xueyan;LIU Jiangjing(Department of Radiology,the Affiliated Hospital of Guilin Medical University,Guangxi Guilin 541000,China)

机构地区：[1]桂林医学院附属医院放射科,广西桂林541000

出　　处：《现代肿瘤医学》2025年第1期96-101,共6页Journal of Modern Oncology

基　　金：广西桂林市科技计划项目(编号:20220139-2)。

摘　　要：目的:探讨合成MRI基于ALN本身定量直方图特征在预测乳腺癌腋窝淋巴结转移(axillary lymph node metastasis,ALNM)中的潜在价值,并将其预测效能与常规影像征象以及ADC值定量直方图特征进行比较。方法:共纳入104枚乳腺癌腋窝淋巴结(ALNM组45枚,非ALNM组59枚),所有患者接受完整乳腺MR检查,包括合成MRI、DWI和DCE MRI。采用PyRadiomics软件提取合成MRI、ADC的定量直方图特征。采用卡方检验、独立样本t检验及Mann-Whitney U检验比较ALNM组与非ALNM组的合成MRI[T1、T2和质子密度(PD)]、ADC值的直方图特征及其DCE-MRI上的影像征象差异。将差异有统计学意义的参数纳入多因素logistic回归分析,采用ROC的曲线下面积(AUC)评估上述变量预测乳腺癌腋窝淋巴结转移状态的诊断性能。结果:合成MRI中T2-最小值、ADC-10th及淋巴结DCE-MRI影像征象(短径)为鉴别乳腺癌腋窝淋巴结转移状态的独立预测因素(P值分别为0.041、0.022、0.023),而T2-最小值所建立的预测模型具有较好的诊断效能[0.765(95%CI:0.673~0.858)]并优于单独ADC(ADC-10th)、影像征象(短径)预测模型,此外,合成MRI(T2-最小值)+ADC(ADC-10th)+影像征象(短径)所建立的多参数模型可显著提高对乳腺癌腋窝淋巴结转移状态的整体诊断效能。结论:合成MRI基于ALN本身定量参数直方图特征在预测乳腺癌腋窝淋巴结转移状态中具有一定价值,合成MRI+ADC定量参数直方图特征+淋巴结影像征象多参数模型预测效能最优,这种多参数联合模型可能是一种预测ALNM有前景的替代方法。Objective:To investigate the potential value of synthetic MRI is based on the ALN itself quantitative histogram features in predicting axillary lymph node metastasis(ALNM)of breast cancer,and to compare its predictive efficacy with conventional imaging features and ADC value quantitative histogram features.Methods:A total of 104 breast axillary lymph nodes(45 in the ALNM group and 59 in the non-ALNM group)were included.All patients underwent complete breast MR examination,including synthetic MRI,DWI and DCE MRI.PyRadiomics software was used to extract the quantitative histogram features of synthetic MRI and ADC.Chi-square test,independent sample t test and Mann-Whitney U test were used to compare the histogram features of synthetic MRI T1,T2 and proton density(PD),ADC values and the differences of image signs on DCE-MRI between the ALNM group and the non-ALNM group.The parameters with statistically significant differences were included in multivariate logistic regression analysis,and the area under the curve(AUC)of ROC was used to evaluate the diagnostic performance of the above variables in predicting axillary lymph node metastasis status of breast cancer.Results:The T2-minimum value,ADC-10th and lymph node DCE-MRI image sign(short diameter)in synthetic MRI were independent predictors for differentiating axillary lymph node metastasis of breast cancer(P values were 0.041,0.022,0.023,respectively).However,the prediction model established by T2-minimum value has better diagnostic efficiency[0.765(95%CI:0.673 to 0.858)]and was superior to ADC(ADC-10th)and image sign(short diameter)prediction models.In addition,the multi-parameter model established by synthetic MRI(T2-minimum)+ADC(ADC-10th)+image sign(short diameter)significantly improved the overall diagnostic efficiency of axillary lymph node metastasis of breast cancer.Conclusion:The Synthetic MRI is based on the ALN itself quantitative parameter histogram features have certain value in predicting the status of axillary lymph node metastasis of breast cancer,and

关 键 词：乳腺癌 合成MRI 淋巴结 ADC 直方图特征 

分 类 号：R737.9[医药卫生—肿瘤]