Development of a nomogram for differentiation between pure mucinous breast carcinomas and fibroadenomas based on DCE-MRI features&nbsp;

QU Ning; LUO Yahongnbsp

doi:10.19732/j.cnki.2096-6210.2024.01.005

您当前的位置：

首页 >

文章列表页 >

Development of a nomogram for differentiation between pure mucinous breast carcinomas and fibroadenomas based on DCE-MRI features

更新时间：2025-12-15

- Development of a nomogram for differentiation between pure mucinous breast carcinomas and fibroadenomas based on DCE-MRI features
- Vol. 33, Issue 1, Pages: 31-38(2024)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.19732/j.cnki.2096-6210.2024.01.005
  CLC：
- Published Online：05 March 2024，
  
  Published：05 March 2024
- 稿件说明：
移动端阅览
曲宁,罗娅红. 基于DCE-MRI列线图鉴别乳腺单纯型黏液癌与T2WI明显高信号纤维腺瘤[J]. 肿瘤影像学, 2024, 33(1): 31-38 https://doi.

org/10.19732/j.cnki.2096-6210.2024.01.005
曲宁,罗娅红. 基于DCE-MRI列线图鉴别乳腺单纯型黏液癌与T2WI明显高信号纤维腺瘤[J]. 肿瘤影像学, 2024, 33(1): 31-38 https://doi. DOI： 10.19732/j.cnki.2096-6210.2024.01.005.

org/10.19732/j.cnki.2096-6210.2024.01.005 DOI：

摘要

目的：

基于动态对比增强磁共振成像（dynamic contrast-enhanced magnetic resonance imaging，DCE-MRI）表现构建乳腺单纯型黏液癌（pure mucinous breast carcinoma，PMBC）与T2加权成像（T2-weighted imaging，T2WI）明显高信号乳腺纤维腺瘤鉴别诊断的列线图模型，旨在提高对两种病变鉴别诊断的准确度。

方法：

回顾并分析64个PMBC和137个T2WI明显高信号纤维腺瘤病变的DCE-MRI表现。记录放射科医师的原始乳腺影像报告和数据系统（Breast Imaging Reporting and Data System，BI-RADS）诊断结果。将单因素分析差异有统计学意义的DCE-MRI特征纳入多因素logistic回归分析，建立影像学特征模型，绘制列线图。采用受试者工作特征（receiver operating characteristic，ROC）曲线的曲线下面积（area under curve，AUC）、灵敏度、特异度、准确度、阳性预测值（positive predictive value，PPV）和阴性预测值（negative predictive value，NPV）评价影像学特征模型的分类性能。绘制校正曲线，评价模型对病变分类的预测结果与实际结果的一致性。采用临床决策分析曲线（decision curve analysis，DCA）评估模型的临床应用价值。

结果：

放射科医师原始诊断的灵敏度、特异度、准确度、PPV和NPV分别为76.56%、73.00%、74.13%、56.98%和86.96%。多因素logistic分析显示，患者的年龄、病变的边缘、晚期内部强化特征、内部有无强化分隔和分叶特征是鉴别PMBC和纤维腺瘤的独立预测因子。模型的AUC、灵敏度、特异度、准确度、PPV和NPV分别为96.24%、87.50%、94.89%、92.54%、88.89%和94.20%。校正曲线显示模型的预测结果与实际结果高度一致。DCA显示，影像学特征模型鉴别两种病变的临床净获益明显高于将其全部视为PMBC或纤维腺瘤。

结论：

基于DCE-MRI表现构建的PMBC与纤维腺瘤鉴别诊断的列线图模型明显优于影像医师原始诊断，可提高对两种病变鉴别诊断的准确度。

Abstract

Objective:

To develop a nomogram to differentiate pure mucinous breast carcinoma (PMBC) from fibroadenoma(FA) with high signal intensity on T2-weighted imaging (T2WI) based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) features

in order to improve the accuracy of differential diagnosis between them.

Methods:

DCE-MRI features of 64 PMBC lesions and 137 FA lesions with T2WI were analyzed retrospectively. The Breast Imaging Reporting and Data System (BI-RADS) classification from the original report was recorded. DCE-MRI features with statistical difference in univariate analysis were included in multivariate logistic regression analysis to develop DCE-MRI nomogram. Area under curve (AUC)

sensitivity

specificity

accuracy

positive predictive value (PPV) and negative predictive value (NPV) of receiver operating characteristic (ROC) curve were used to evaluate DCE-MRI nomogram. The calibration curves were drawn to show the consistency between the predictive value and the true value. Decision curve analysis (DCA) was conducted to determine the clinical usefulness of DCE-MRI nomogram.

Results:

Sensitivity

specificity

accuracy

PPV and NPV calculated according to the BI-RADS classification from the original report were 76.56%

73.00%

74.13%

56.98% and 86.96%

respectively. Multivariate analysis showed that age

margin

delayed enhancement pattern

enhancing internal septation and extent of lobulation were independent predictors for differentiating PMBC from FA. AUC

sensitivity

specificity

accuracy

PPV and NPV of DCE-MRI nomogram were 96.24%

87.50%

94.89%

92.54%

88.89% and 94.20%

respectively. According to the calibration curve

the predicted and true values showed good consistency. Based on decision curve analysis

the net benefit of using DCE-MRI nomogram to differentiate PMBC from FA was greater than treat-all or treat-none scheme.

Conclusion:

The nomogram based on DCE-MRI features for differentiatio

n between PMBC and FA was superior to the BI-RADS classification from the original report and improved the accuracy of differential diagnosis of PMBC and FA.

关键词

Keywords

references

Views

411

下载量

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

Prediction of sentinel lymph node metastasis in breast cancer using multiparametric MRI radiomics and machine learning models

The predictive value of nomogram scoring model based on ultrasound and clinicopathological features to predict pCR in HER2 positive breast cancer after NAC

Prediction of microsatellite instability in rectal cancer using MRI radiomics models based on multiple machine learning algorithms

The progress of breast MRI in evaluating breast conservation therapy and ipsilateral breast tumor recurrence

Prediction value of breast MRI in ipsilateral breast tumor recurrence after breast-conserving surgery and distant metastasis following secondary surgery

Related Author

Hongkai YANG

Xuan QI

Wuling WANG

Weiqun CHENG

Dong QI

Yongsheng HE

Xinyue WANG

Kunpeng CAO

Related Institution

Department of Radiology, Ma’anshan People’s Hospital, Ma’anshan

The Graduate School, Anhui Medical University

The Fifth Clinical Medical College of Anhui Medical University

Department of Ultrasound, The First Affiliated Hospital of Nanjing Medical University

Department of Radiology, The First Affiliated Hospital of Bengbu Medical University

AI问答

⁰