Huang Yuhong, Chen Wenben, Zhang Xiaoling, He Shaofu, Shao Nan, Shi Huijuan, Lin Zhenzhe, Wu Xueting, Li Tongkeng, Lin Haotian, Lin Ying
Breast Disease Center, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China.
State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China.
Front Bioeng Biotechnol. 2021 Jul 6;9:662749. doi: 10.3389/fbioe.2021.662749. eCollection 2021.
After neoadjuvant chemotherapy (NACT), tumor shrinkage pattern is a more reasonable outcome to decide a possible breast-conserving surgery (BCS) than pathological complete response (pCR). The aim of this article was to establish a machine learning model combining radiomics features from multiparametric MRI (mpMRI) and clinicopathologic characteristics, for early prediction of tumor shrinkage pattern prior to NACT in breast cancer. This study included 199 patients with breast cancer who successfully completed NACT and underwent following breast surgery. For each patient, 4,198 radiomics features were extracted from the segmented 3D regions of interest (ROI) in mpMRI sequences such as T1-weighted dynamic contrast-enhanced imaging (T1-DCE), fat-suppressed T2-weighted imaging (T2WI), and apparent diffusion coefficient (ADC) map. The feature selection and supervised machine learning algorithms were used to identify the predictors correlated with tumor shrinkage pattern as follows: (1) reducing the feature dimension by using ANOVA and the least absolute shrinkage and selection operator (LASSO) with 10-fold cross-validation, (2) splitting the dataset into a training dataset and testing dataset, and constructing prediction models using 12 classification algorithms, and (3) assessing the model performance through an area under the curve (AUC), accuracy, sensitivity, and specificity. We also compared the most discriminative model in different molecular subtypes of breast cancer. The Multilayer Perception (MLP) neural network achieved higher AUC and accuracy than other classifiers. The radiomics model achieved a mean AUC of 0.975 (accuracy = 0.912) on the training dataset and 0.900 (accuracy = 0.828) on the testing dataset with 30-round 6-fold cross-validation. When incorporating clinicopathologic characteristics, the mean AUC was 0.985 (accuracy = 0.930) on the training dataset and 0.939 (accuracy = 0.870) on the testing dataset. The model further achieved good AUC on the testing dataset with 30-round 5-fold cross-validation in three molecular subtypes of breast cancer as following: (1) HR+/HER2-: 0.901 (accuracy = 0.816), (2) HER2+: 0.940 (accuracy = 0.865), and (3) TN: 0.837 (accuracy = 0.811). It is feasible that our machine learning model combining radiomics features and clinical characteristics could provide a potential tool to predict tumor shrinkage patterns prior to NACT. Our prediction model will be valuable in guiding NACT and surgical treatment in breast cancer.
新辅助化疗（NACT）后，与病理完全缓解（pCR）相比，肿瘤缩小模式是决定是否可行保乳手术（BCS）的更合理指标。本文旨在建立一种机器学习模型，该模型结合多参数磁共振成像（mpMRI）的影像组学特征和临床病理特征，用于在乳腺癌新辅助化疗前早期预测肿瘤缩小模式。本研究纳入了199例成功完成新辅助化疗并接受后续乳房手术的乳腺癌患者。对于每位患者，从mpMRI序列（如T1加权动态对比增强成像（T1-DCE）、脂肪抑制T2加权成像（T2WI）和表观扩散系数（ADC）图）中分割出的三维感兴趣区域（ROI）提取4198个影像组学特征。采用特征选择和监督机器学习算法来识别与肿瘤缩小模式相关的预测因子，具体如下：（1）使用方差分析（ANOVA）和具有10倍交叉验证的最小绝对收缩和选择算子（LASSO）来降低特征维度；（2）将数据集分为训练数据集和测试数据集，并使用12种分类算法构建预测模型；（3）通过曲线下面积（AUC）、准确率、灵敏度和特异性评估模型性能。我们还比较了乳腺癌不同分子亚型中最具鉴别力的模型。多层感知器（MLP）神经网络比其他分类器具有更高的AUC和准确率。在30轮6倍交叉验证下，影像组学模型在训练数据集上的平均AUC为0.975（准确率 = 0.912），在测试数据集上为0.900（准确率 = 0.828）。纳入临床病理特征后，训练数据集上的平均AUC为0.985（准确率 = 0.930），测试数据集上为0.939（准确率 = 0.870）。在乳腺癌的三种分子亚型中，该模型在30轮5倍交叉验证的测试数据集上也取得了良好的AUC，具体如下：（1）HR+/HER2-：0.901（准确率 = 0.816）；（2）HER2+：0.940（准确率 = 0.865）；（3）三阴型（TN）：0.837（准确率 = 0.811）。我们结合影像组学特征和临床特征的机器学习模型有可能为新辅助化疗前预测肿瘤缩小模式提供一种潜在工具。我们的预测模型在指导乳腺癌的新辅助化疗和手术治疗方面将具有重要价值。
