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

ABSTRACT

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.