HER2 and trastuzumab treatment response H&E slides with tumor ROI annotations

The current standard of care for many patients with HER2-positive breast cancer is neoadjuvant chemotherapy in combination with anti-HER2 agents, based on HER2 amplification as detected by in situ hybridization (ISH) or protein immunohistochemistry (IHC). However, hematoxylin & eosin (H&E) tumor stains are more commonly available, and accurate prediction of HER2 status and anti-HER2 treatment response from H&E would reduce costs and increase the speed of treatment selection. Computational algorithms for H&E have been effective in predicting a variety of cancer features and clinical outcomes, including moderate success in predicting HER2 status. We trained a CNN classifier on 188 H&E whole slide images (WSIs) manually annotated for tumor regions of interest (ROIs) by our pathology team. Our classifier achieved an area under the curve (AUC) of 0.90 in cross-validation of slide-level HER2 status and 0.81 on an independent TCGA test set. Moreover, we trained our classifier on pre-treatment samples from 187 HER2+ patients that subsequently received trastuzumab therapy. Our classifier achieved an AUC of 0.80 in a five-fold cross validation. Our work provides an H&E-based algorithm that can predict HER2 status and trastuzumab response in breast cancer at an accuracy that may benefit clinical evaluations. Here, we are providing the datasets used in the study to facilitate development of other HER2+ diagnosis and trastuzumab response applications.

当前针对多数HER2阳性乳腺癌（HER2-positive breast cancer）患者的标准治疗方案，是基于原位杂交（in situ hybridization, ISH）或蛋白质免疫组化（immunohistochemistry, IHC）检测到的HER2扩增结果，采用新辅助化疗（neoadjuvant chemotherapy）联合抗HER2药物（anti-HER2 agents）开展治疗。然而，苏木精-伊红（hematoxylin & eosin, H&E）肿瘤染色更为普及，若能通过H&E染色图像精准预测HER2状态及抗HER2治疗响应，将有效缩减治疗成本并提速治疗方案遴选流程。基于H&E染色图像的计算算法已在多种癌症特征与临床结局预测领域展现出有效性，在HER2状态预测方面亦已取得阶段性进展。我们的病理团队对188张H&E全玻片图像（Whole Slide Images, WSIs）的肿瘤感兴趣区域（Regions of Interest, ROIs）完成人工标注后，基于该标注集训练了卷积神经网络分类器（Convolutional Neural Network classifier, CNN classifier）。该分类器在玻片级HER2状态的交叉验证（cross-validation）中取得了0.90的曲线下面积（Area Under the Curve, AUC），在独立的癌症基因组图谱（The Cancer Genome Atlas, TCGA）测试集上的曲线下面积为0.81。此外，我们从187名后续接受曲妥珠单抗（trastuzumab）治疗的HER2阳性患者的治疗前样本中训练了该分类器，其在五折交叉验证（five-fold cross validation）中的曲线下面积达到0.80。本研究提出了一种基于H&E染色图像的算法，可在乳腺癌患者中预测HER2状态与曲妥珠单抗治疗响应，其预测精度可为临床评估提供有力支撑。在此我们公开本研究使用的数据集，以推动其他HER2阳性乳腺癌诊断及曲妥珠单抗治疗响应预测相关应用的开发。