Deep-Learning Based Breast Cancer Detection for Cross-Staining Histopathology Images

Hematoxylin and eosin (H&E) staining is the gold standard for tissue characterization in routine pathological diagnoses. However, these visible light dyes do not exclusively label the nuclei and cytoplasm, making clear-cut segmentation of staining signals challenging. Currently, fluorescent staining technology is much more common in clinical research for analyzing tissue morphology and protein distribution owing to its advantages of channel independence, multiplex labeling, and the possibility of enabling 3D tissue labeling. Although both H&E and fluorescent dyes can stain the nucleus and cytoplasm for representative tissue morphology, color variation between these two staining technologies makes cross-analysis difficult, especially with computer-assisted artificial intelligence (AI) algorithms. In this study, we applied color normalization and nucleus extraction methods to overcome the variation between staining technologies. We also developed an available workflow for using an H&E-stained segmentation AI model in the analysis of fluorescent nucleic acid staining images in breast cancer tumor recognition, resulting in 89.6% and 80.5% accuracy in recognizing specific tumor features in H&E- and fluorescent-stained pathological images, respectively. The results show that the cross-staining inference maintained the same precision level as the proposed workflow, providing an opportunity for an expansion of the application of current pathology AI models.

Funding Information: This research received no external funding.

Declaration of Interests: The authors declare no conflict of interest.

Ethics Approval Statement: The study was conducted in accordance with the Declaration of Helsinki, and approved by the Institutional Review Board of Chi Mei Medical Center (ethical approval identifier: 10902-002) and Hsinchu NTUH (ethical approval identifier: 109-053-F). Patient consent was waived due to the researchers are collecting achieved retrospective samples and involve minimal risk to participants.

Keywords: Breast Cancer, cross-staining, Artificial Intelligence, adaptive color segmentation, color deconvolution, Computational Pathology

Suggested Citation: Suggested Citation

Huang, Pei-Wen and Ouyang, Hsu and Hsu, Bang-Yi and Chang, Yu-Ruei and Lin, Yu-Chieh and Chen, Yung-An and Hsieh, Yu-Han and Fu, Chien-Chung and Li, Chien-Feng and Lin, Ching-Hung and Lin, Yen-Yin and Chang, Margaret Dah-Tsyr and Pai, Tun-Wen, Deep-Learning Based Breast Cancer Detection for Cross-Staining Histopathology Images. Available at SSRN: https://ssrn.com/abstract=4257484 or http://dx.doi.org/10.2139/ssrn.4257484