研究动态
Articles below are published ahead of final publication in an issue. Please cite articles in the following format: authors, (year), title, journal, DOI.

用于指导HER2 靶向疗法的HER2相关细胞分割的弱监督双层卷积网络。

Weakly supervised bilayer convolutional network in segmentation of HER2 related cells to guide HER2 targeted therapies.

发表日期:2023 Jul 18
作者: Ching-Wei Wang, Kun-Lin Lin, Hikam Muzakky, Yi-Jia Lin, Tai-Kuang Chao
来源: Parasites & Vectors

摘要:

人类表皮生长因子受体2(HER2/ERBB2)的过表达被视为乳腺癌转移的预后标志和判断ERBB2靶向药物效果的预测指标。准确的ERBB2检测对于确定乳腺癌转移患者的最佳治疗方案至关重要。近来,美国食品药品监督管理局通过了亮场双原位杂交(DISH)技术用于评估ERBB2的过表达,但是由于多种原因,这仍然是一项具有挑战性的任务。首先,触碰聚集和重叠细胞的存在使得分割独立HER2相关细胞变得困难,这些细胞必须包含ERBB2和CEN17信号。其次,模糊的细胞边界使得每个HER2相关细胞的定位变得困难。第三,HER2相关细胞的外观变异很大。第四,由于手动注释通常是基于高置信度的目标,导致有些未标记的HER2相关细胞被定义为背景,这将严重混淆全监督的人工智能学习,并导致模型的结果不佳。为了解决上述所有问题,我们提出了一个两阶段的弱监督深度学习框架,用于准确和稳健地评估ERBB2的过表达。所提出的深度学习框架的有效性和稳健性在两个不同放大倍数下获得的DISH数据集上进行评估。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对ERBB2过表达的分割分别实现了96.78 ± 1.25的准确度,97.77 ± 3.09的精确度,84.86 ± 5.83的召回率和90.77 ± 4.1的Dice指数,以及96.43 ± 2.67的准确度,97.82 ± 3.99的精确度,87.14 ± 10.17的召回率和91.87 ± 6.51的Dice指数。此外,所提出的深度学习框架在两个数据集上的IoU指标显著优于15种基准方法(P<0.05)。版权所有©2023 Elsevier Ltd. 保留所有权利。
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.Copyright © 2023 Elsevier Ltd. All rights reserved.