Hao Wen, Gong Jing, Wang Shengping, Zhu Hui, Zhao Bin, Peng Weijun
Department of Radiology, Fudan University Shanghai Cancer Center, Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, China.
Shandong Medical Imaging Research Institute, Shandong University, Jinan, China.
Front Oncol. 2020 Oct 29;10:531476. doi: 10.3389/fonc.2020.531476. eCollection 2020.
This study aimed to explore the potential of magnetic resonance imaging (MRI) radiomics-based machine learning to improve assessment and diagnosis of contralateral Breast Imaging Reporting and Data System (BI-RADS) category 4 lesions in women with primary breast cancer.
A total of 178 contralateral BI-RADS 4 lesions (97 malignant and 81 benign) collected from 178 breast cancer patients were involved in our retrospective dataset. T1 + C and T2 weighted images were used for radiomics analysis. These lesions were randomly assigned to the training (n = 124) dataset and an independent testing dataset (n = 54). A three-dimensional semi-automatic segmentation method was performed to segment lesions depicted on T2 and T1 + C images, 1,046 radiomic features were extracted from each segmented region, and a least absolute shrinkage and operator feature selection method reduced feature dimensionality. Three support vector machine (SVM) classifiers were trained to build classification models based on the T2, T1 + C, and fusion image features, respectively. The diagnostic performance of each model was evaluated and tested using the independent testing dataset. The area under the receiver operating characteristic curve (AUC) was used as a performance metric.
The T1+C image feature-based model and T2 image feature-based model yielded AUCs of 0.71 ± 0.07 and 0.69 ± 0.07 respectively, and the difference between them was not significant (P > 0.05). After fusing T1 + C and T2 imaging features, the proposed model's AUC significantly improved to 0.77 ± 0.06 (P < 0.001). The fusion model yielded an accuracy of 74.1%, which was higher than that of the T1 + C (66.7%) and T2 (59.3%) image feature-based models.
The MRI radiomics-based machine learning model is a feasible method to assess contralateral BI-RADS 4 lesions. T2 and T1 + C image features provide complementary information in discriminating benign and malignant contralateral BI-RADS 4 lesions.
本研究旨在探讨基于磁共振成像（MRI）影像组学的机器学习在改善原发性乳腺癌女性对侧乳腺影像报告和数据系统（BI-RADS）4类病变评估及诊断方面的潜力。
我们的回顾性数据集纳入了从178例乳腺癌患者收集的总共178个对侧BI-RADS 4类病变（97个恶性和81个良性）。T1+C和T2加权图像用于影像组学分析。这些病变被随机分配到训练数据集（n = 124）和独立测试数据集（n = 54）。采用三维半自动分割方法对T2和T1+C图像上描绘的病变进行分割，从每个分割区域提取1046个影像组学特征，并采用最小绝对收缩和选择算子特征选择方法降低特征维度。分别训练三个支持向量机（SVM）分类器，以基于T2、T1+C和融合图像特征构建分类模型。使用独立测试数据集对每个模型的诊断性能进行评估和测试。采用受试者操作特征曲线（AUC）下面积作为性能指标。
基于T1+C图像特征的模型和基于T2图像特征的模型的AUC分别为0.71±0.07和0.69±0.07，两者差异不显著（P>0.05）。融合T1+C和T2影像特征后，所提出模型的AUC显著提高至0.77±0.06（P<0.001）。融合模型的准确率为74.1%，高于基于T1+C（66.7%）和T2（59.3%）图像特征的模型。
基于MRI影像组学的机器学习模型是评估对侧BI-RADS 4类病变的可行方法。T2和T1+C图像特征在鉴别对侧BI-RADS 4类病变的良恶性方面提供互补信息。
