Xu Feng, Zhu Chuang, Tang Wenqi, Wang Ying, Zhang Yu, Li Jie, Jiang Hongchuan, Shi Zhongyue, Liu Jun, Jin Mulan
Department of Breast Surgery, Beijing Chao-Yang Hospital, Beijing, China.
School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China.
Front Oncol. 2021 Oct 14;11:759007. doi: 10.3389/fonc.2021.759007. eCollection 2021.
To develop and validate a deep learning (DL)-based primary tumor biopsy signature for predicting axillary lymph node (ALN) metastasis preoperatively in early breast cancer (EBC) patients with clinically negative ALN.
A total of 1,058 EBC patients with pathologically confirmed ALN status were enrolled from May 2010 to August 2020. A DL core-needle biopsy (DL-CNB) model was built on the attention-based multiple instance-learning (AMIL) framework to predict ALN status utilizing the DL features, which were extracted from the cancer areas of digitized whole-slide images (WSIs) of breast CNB specimens annotated by two pathologists. Accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curves, and areas under the ROC curve (AUCs) were analyzed to evaluate our model.
The best-performing DL-CNB model with VGG16_BN as the feature extractor achieved an AUC of 0.816 (95% confidence interval (CI): 0.758, 0.865) in predicting positive ALN metastasis in the independent test cohort. Furthermore, our model incorporating the clinical data, which was called DL-CNB+C, yielded the best accuracy of 0.831 (95%CI: 0.775, 0.878), especially for patients younger than 50 years (AUC: 0.918, 95%CI: 0.825, 0.971). The interpretation of DL-CNB model showed that the top signatures most predictive of ALN metastasis were characterized by the nucleus features including density ( = 0.015), circumference ( = 0.009), circularity ( = 0.010), and orientation ( = 0.012).
Our study provides a novel DL-based biomarker on primary tumor CNB slides to predict the metastatic status of ALN preoperatively for patients with EBC.
开发并验证一种基于深度学习（DL）的原发性肿瘤活检特征，用于术前预测临床腋窝淋巴结（ALN）阴性的早期乳腺癌（EBC）患者的ALN转移情况。
2010年5月至2020年8月共纳入1058例经病理证实ALN状态的EBC患者。基于注意力的多实例学习（AMIL）框架构建了一个DL粗针活检（DL-CNB）模型，利用从两位病理学家标注的乳腺CNB标本数字化全切片图像（WSIs）的癌区提取的DL特征来预测ALN状态。分析准确性、敏感性、特异性、受试者工作特征（ROC）曲线和ROC曲线下面积（AUC）以评估我们的模型。
以VGG16_BN作为特征提取器的表现最佳的DL-CNB模型在独立测试队列中预测阳性ALN转移的AUC为0.816（95%置信区间（CI）：0.758，0.865）。此外，我们纳入临床数据的模型，即DL-CNB+C，产生了最佳准确性0.831（95%CI：0.775，0.878），尤其是对于年龄小于50岁的患者（AUC：0.918，95%CI：0.825，0.971）。DL-CNB模型的解释表明，最能预测ALN转移的顶级特征以包括密度（=0.015）、周长（=0.009）、圆形度（=0.010）和方向（=0.012）在内的细胞核特征为特点。
我们的研究在原发性肿瘤CNB玻片上提供了一种基于DL的新型生物标志物，用于术前预测EBC患者的ALN转移状态。
