Wang Simin, Mao Ning, Duan Shaofeng, Li Qin, Li Ruimin, Jiang Tingting, Wang Zhongyi, Xie Haizhu, Gu Yajia
Department of Radiology, Fudan University Shanghai Cancer Center, Shanghai, China.
Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, China.
Front Oncol. 2021 May 28;11:600546. doi: 10.3389/fonc.2021.600546. eCollection 2021.
A limited number of studies have focused on the radiomic analysis of contrast-enhanced mammography (CEM). We aimed to construct several radiomics-based models of CEM for classifying benign and malignant breast lesions. The retrospective, double-center study included women who underwent CEM between November 2013 and February 2020. Radiomic analysis was performed using high-energy (HE), low-energy (LE), and dual-energy subtraction (DES) images from CEM. Datasets were randomly divided into the training and testing sets at a ratio of 7:3. The maximum relevance minimum redundancy (mRMR) method and least absolute shrinkage and selection operator (LASSO) logistic regression were used to select the radiomic features and construct the best classification models. The performances of the models were assessed by the area under the receiver operating characteristic curve (AUC) with a 95% confidence interval (CI). Leave-group-out cross-validation (LGOCV) for 100 rounds was performed to obtain the mean AUCs, which were compared by the Wilcoxon rank-sum test and the Kruskal-Wallis rank-sum test. A total of 192 women with 226 breast lesions (101 benign; 125 malignant) were enrolled. The median age was 48 years (range, 22-70 years). For the classification of breast lesions, the AUCs of the best models were 0.931 (95% CI: 0.873-0.989) for HE, 0.897 (95% CI: 0.807-0.981) for LE, 0.882 (95% CI: 0.825-0.987) for DES images and 0.960 (95% CI: 0.910-0.998) for all of the CEM images in the testing set. According to LGOCV, the models constructed with the HE images and all of the CEM images showed the highest mean AUCs for the training (0.931 and 0.938, respectively; < 0.05 for both) and testing sets (0.892 and 0.889, respectively; = 0.55 for both), which were significantly higher than those of the two models constructed with the LE and DES images in the training (0.912 and 0.899, respectively; all < 0.05) and testing sets (0.866 and 0.862, respectively; all < 0.05). Radiomic analysis of CEM images was valuable for classifying benign and malignant breast lesions. The use of HE images or all three types of CEM images can achieve the best performance.
少数研究聚焦于对比增强乳腺钼靶摄影（CEM）的影像组学分析。我们旨在构建基于影像组学的CEM模型，用于对乳腺良恶性病变进行分类。这项回顾性、双中心研究纳入了2013年11月至2020年2月期间接受CEM检查的女性。使用CEM的高能（HE）、低能（LE）和双能减影（DES）图像进行影像组学分析。数据集按7:3的比例随机分为训练集和测试集。采用最大相关最小冗余（mRMR）方法和最小绝对收缩与选择算子（LASSO）逻辑回归来选择影像组学特征并构建最佳分类模型。通过受试者操作特征曲线（AUC）下的面积及95%置信区间（CI）评估模型性能。进行100轮留一法交叉验证（LGOCV）以获得平均AUC，并通过Wilcoxon秩和检验和Kruskal-Wallis秩和检验进行比较。共纳入192例患有226个乳腺病变的女性（101个良性；125个恶性）。中位年龄为48岁（范围22 - 70岁）。对于乳腺病变的分类，测试集中最佳模型的AUC分别为：HE图像0.931（95%CI：0.873 - 0.989），LE图像0.897（95%CI：0.807 - 0.981），DES图像0.882（95%CI：0.825 - 0.987），所有CEM图像0.960（95%CI：0.910 - 0.998）。根据LGOCV，用HE图像和所有CEM图像构建的模型在训练集（分别为0.931和0.938；两者均P<0.05）和测试集（分别为0.892和0.889；两者均P = 0.55）中显示出最高的平均AUC，显著高于用LE和DES图像构建的两个模型在训练集（分别为0.912和0.899；均P<0.05）和测试集（分别为0.866和0.862；均P<0.05）中的表现。CEM图像的影像组学分析对于乳腺良恶性病变的分类具有重要价值。使用HE图像或所有三种类型的CEM图像可实现最佳性能。
