Graduate Institute of Biomedical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan.
Department of Pathology, Tri-Service General Hospital, Taipei, Taiwan; Institute of Pathology and Parasitology, National Defense Medical Center, Taipei, Taiwan.
Comput Med Imaging Graph. 2023 Sep;108:102270. doi: 10.1016/j.compmedimag.2023.102270. Epub 2023 Jul 18.
Overexpression of human epidermal growth factor receptor 2 (HER2/ERBB2) is identified as a prognostic marker in metastatic breast cancer and a predictor to determine the effects of ERBB2-targeted drugs. Accurate ERBB2 testing is essential in determining the optimal treatment for metastatic breast cancer patients. Brightfield dual in situ hybridization (DISH) was recently authorized by the United States Food and Drug Administration for the assessment of ERRB2 overexpression, which however is a challenging task due to a variety of reasons. Firstly, the presence of touching clustered and overlapping cells render it difficult for segmentation of individual HER2 related cells, which must contain both ERBB2 and CEN17 signals. Secondly, the fuzzy cell boundaries make the localization of each HER2 related cell challenging. Thirdly, variation in the appearance of HER2 related cells is large. Fourthly, as manual annotations are usually made on targets with high confidence, causing sparsely labeled data with some unlabeled HER2 related cells defined as background, this will seriously confuse fully supervised AI learning and cause poor model outcomes. To deal with all issues mentioned above, we propose a two-stage weakly supervised deep learning framework for accurate and robust assessment of ERBB2 overexpression. The effectiveness and robustness of the proposed deep learning framework is evaluated on two DISH datasets acquired at two different magnifications. The experimental results demonstrate that the proposed deep learning framework achieves an accuracy of 96.78 ± 1.25, precision of 97.77 ± 3.09, recall of 84.86 ± 5.83 and Dice Index of 90.77 ± 4.1 and an accuracy of 96.43 ± 2.67, precision of 97.82 ± 3.99, recall of 87.14 ± 10.17 and Dice Index of 91.87 ± 6.51 for segmentation of ERBB2 overexpression on the two experimental datasets, respectively. Furthermore, the proposed deep learning framework outperforms 15 state-of-the-art benchmarked methods by a significant margin (P<0.05) with respect to IoU on both datasets.
人表皮生长因子受体 2（HER2/ERBB2）的过表达被确定为转移性乳腺癌的预后标志物，也是预测 ERBB2 靶向药物疗效的指标。准确的 ERBB2 检测对于确定转移性乳腺癌患者的最佳治疗方案至关重要。荧光原位杂交（FISH）技术最近被美国食品和药物管理局授权用于评估 ERRB2 过表达，然而，由于各种原因，这是一项具有挑战性的任务。首先，由于存在聚集和重叠的细胞，使得分割单个 HER2 相关细胞变得困难，这些细胞必须同时包含 ERBB2 和 CEN17 信号。其次，由于细胞边界模糊，使得定位每个 HER2 相关细胞变得具有挑战性。第三，HER2 相关细胞的外观变化很大。第四，由于手动注释通常是在高置信度的目标上进行的，这会导致标记数据稀疏，一些未标记的 HER2 相关细胞被定义为背景，这将严重干扰完全监督的 AI 学习，并导致模型结果不佳。为了解决上述所有问题，我们提出了一种两阶段的弱监督深度学习框架，用于准确和稳健地评估 ERBB2 过表达。在两个不同放大倍数采集的两个 DISH 数据集上评估了所提出的深度学习框架的有效性和鲁棒性。实验结果表明，所提出的深度学习框架在两个实验数据集上分别实现了 96.78 ± 1.25 的准确率、97.77 ± 3.09 的精确率、84.86 ± 5.83 的召回率和 90.77 ± 4.1 的 Dice 指数，以及 96.43 ± 2.67 的准确率、97.82 ± 3.99 的精确率、87.14 ± 10.17 的召回率和 91.87 ± 6.51 的 Dice 指数，用于分割 ERBB2 过表达。此外，所提出的深度学习框架在两个数据集上的 IoU 方面均显著优于 15 种最先进的基准方法（P<0.05）。
