Pathological complete response (pCR) is considered a surrogate endpoint for favorable survival in breast cancer patients treated with neoadjuvant chemotherapy (NAC). Predictive biomarkers of treatment response are crucial for guiding treatment decisions. With the hypothesis that histological information on tumor biopsy images could predict NAC response in breast cancer, we proposed a novel deep learning (DL)-based biomarker that predicts pCR from images of hematoxylin and eosin (H&E)-stained tissue and evaluated its predictive performance. In total, 540 breast cancer patients receiving standard NAC were enrolled. Based on H&E-stained images, DL methods were employed to automatically identify tumor epithelium and predict pCR by scoring the identified tumor epithelium to produce a histopathological biomarker, the pCR-score. The predictive performance of the pCR-score was assessed and compared with that of conventional biomarkers including stromal tumor-infiltrating lymphocytes (sTILs) and subtype. The pCR-score derived from H&E staining achieved an area under the curve (AUC) of 0.847 in predicting pCR directly, and achieved accuracy, F1 score, and AUC of 0.853, 0.503, and 0.822 processed by the logistic regression method, respectively, higher than either sTILs or subtype; a prediction model of pCR constructed by integrating sTILs, subtype and pCR-score yielded a mean AUC of 0.890, outperforming the baseline sTIL-subtype model by 0.051 (0.839, P = 0.001). The DL-based pCR-score from histological images is predictive of pCR better than sTILs and subtype, and holds the great potentials for a more accurate stratification of patients for NAC.

中文翻译：

---

基于深度学习的乳腺癌组织学图像对新辅助化疗病理完全反应的预测性生物标志物

病理学完全缓解 (pCR) 被认为是接受新辅助化疗 (NAC) 治疗的乳腺癌患者良好生存的替代终点。治疗反应的预测性生物标志物对于指导治疗决策至关重要。假设肿瘤活检图像的组织学信息可以预测乳腺癌的 NAC 反应，我们提出了一种基于深度学习 (DL) 的新型生物标志物，它可以从苏木精和伊红 (H&E) 染色的组织图像中预测 pCR 并评估其预测性能. 总共招募了 540 名接受标准 NAC 的乳腺癌患者。基于 H&E 染色图像，采用 DL 方法自动识别肿瘤上皮并通过对识别的肿瘤上皮进行评分以产生组织病理学生物标志物 pCR 评分来预测 pCR。评估了 pCR 评分的预测性能，并与包括间质肿瘤浸润淋巴细胞 (sTIL) 和亚型在内的传统生物标志物的预测性能进行了比较。H&E 染色得到的 pCR 评分在直接预测 pCR 方面的曲线下面积 (AUC) 为 0.847，准确率、F1 评分和逻辑回归方法处理的 AUC 分别为 0.853、0.503 和 0.822，更高比 sTIL 或亚型；通过整合 sTIL、亚型和 pCR 分数构建的 pCR 预测模型产生 0.890 的平均 AUC，比基线 sTIL 亚型模型高 0.051（0.839，P = 0.001）。来自组织学图像的基于 DL 的 pCR 评分比 sTIL 和亚型更能预测 pCR，并且在更准确地对 NAC 患者进行分层方面具有巨大潜力。