Zhang Huiting, Lang Manlin, Shen Huiming, Li Hang, Yang Ning, Chen Bo, Chen Yixu, Ding Hong, Yang Weiping, Ji Xiaohui, Zhou Ping, Cui Ligang, Wang Jiandong, Xu Wentong, Ye Xiuqin, Liu Zhixing, Yang Yu, Wei Tianci, Wang Hui, Yan Yuanyuan, Wu Changjun, Wu Yiyun, Shi Jingwen, Wang Yaxi, Fang Xiuxia, Li Ran, Liang Ping, Yu Jie
Department of Interventional Ultrasound, PLA Medical College & Chinese PLA General Hospital, Beijing, China.
Department of Ultrasound, Zhongda Hospital, Nanjing, China.
Front Med (Lausanne). 2025 May 21;12:1585823. doi: 10.3389/fmed.2025.1585823. eCollection 2025.
To predict human epidermal growth factor receptor 2 (HER2) expression in breast cancer (BC) using Sonazoid-enhanced ultrasound in a machine learning-based model.
Between August 2020 and February 2021, patients with breast cancer who underwent surgical treatment without neoadjuvant chemotherapy were prospectively enrolled from 17 hospitals in China. HER2 expression status was assessed by immunohistochemistry or fluorescence hybridization (FISH). The training set contained data from 11 hospitals and the validation set contained 6 hospitals. Clinical features, B-mode ultrasound, contrast-enhanced ultrasound (CEUS), and time-intensity curve were selected by the Least Absolute Shrinkage and Selection Operator. Based on the selected features, six prediction models were established to predict HER2 3 + and 2 +/1 + expression: logistic regression (LR), support vector machine (SVM), random forest (RF), eXtreme Gradient Boosting (XGB), XGB combined with LR, and fusion model.
A total of 140 patients with breast cancer were enrolled in this study. Seven features related to HER2 3 + and six features related to HER2 2+/1 + were selected to establish prediction models. Among the six models, LR, SVM, and XGB showed the best prediction performance for both HER2 3 + and HER2 2+/1 + cases. These three models were then combined into a fusion model. In the validation, the fusion model achieved the highest value of area under the receiver operating characteristic curve as 0.869 (95%CI: 0.715-0.958) for predicting HER2 3 + and 0.747 (95%CI: 0.548-0.891) for predicting HER2 2+/1 + cases. The model could correctly upgrade HER2 2 + cases to HER2 3 + cases, consistent with the FISH test results.
Sonazoid-enhanced ultrasound can provide effective guidance for targeted therapy of breast cancer by predicting HER2 expression using machine learning approaches.
在基于机器学习的模型中，使用声诺维增强超声预测乳腺癌（BC）中的人表皮生长因子受体2（HER2）表达。
2020年8月至2021年2月期间，前瞻性纳入了来自中国17家医院的接受手术治疗且未接受新辅助化疗的乳腺癌患者。通过免疫组织化学或荧光杂交（FISH）评估HER2表达状态。训练集包含来自11家医院的数据，验证集包含6家医院的数据。通过最小绝对收缩和选择算子选择临床特征、B型超声、超声造影（CEUS）和时间强度曲线。基于所选特征，建立了六个预测模型来预测HER2 3 +和2 +/1 +表达：逻辑回归（LR）、支持向量机（SVM）、随机森林（RF）、极端梯度提升（XGB）、XGB联合LR以及融合模型。
本研究共纳入140例乳腺癌患者。选择了七个与HER2 3 +相关的特征和六个与HER2 2+/1 +相关的特征来建立预测模型。在六个模型中，LR、SVM和XGB在HER2 3 +和HER2 2+/1 +病例中均表现出最佳预测性能。然后将这三个模型合并为一个融合模型。在验证中，融合模型在预测HER2 3 +时的受试者操作特征曲线下面积最高值为0.869（95%CI：0.715 - 0.958），在预测HER2 2+/1 +病例时为0.747（95%CI：0.548 - 0.891）。该模型能够将HER2 2 +病例正确升级为HER2 3 +病例，与FISH检测结果一致。
声诺维增强超声可通过机器学习方法预测HER2表达，为乳腺癌的靶向治疗提供有效指导。
Zotero 插件
