Deep-learning based breast cancer detection for cross-staining histopathology images
Pei-Wen Huang,
Hsu Ouyang,
Bang-Yi Hsu,
Yu-Ruei Chang,
Yu-Chieh Lin,
Yung-An Chen,
Yu-Han Hsieh,
Chien-Chung Fu,
Chien-Feng Li,
Ching-Hung Lin,
Yen-Yin Lin,
Margaret Dah-Tsyr Chang,
Tun-Wen Pai
Affiliations
Pei-Wen Huang
Institute of Molecular and Cellular Biology, National Tsing Hua University, Hsinchu, Taiwan; Department of Pathology, Hsinchu Mackay Memorial Hospital, Hsinchu, Taiwan
Hsu Ouyang
Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, Taiwan
Bang-Yi Hsu
Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, Taiwan
Yu-Ruei Chang
Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, Taiwan
Yu-Chieh Lin
Department of Power Mechanical Engineering, National Tsing Hua University, Taiwan; JelloX Biotech Inc., Hsinchu, Taiwan
Yung-An Chen
Department of Power Mechanical Engineering, National Tsing Hua University, Taiwan
Yu-Han Hsieh
JelloX Biotech Inc., Hsinchu, Taiwan
Chien-Chung Fu
Department of Power Mechanical Engineering, National Tsing Hua University, Taiwan
Chien-Feng Li
Department of Medical Research, Chi Mei Medical Center, Tainan, Taiwan; National Institute of Cancer Research, National Health Research Institutes, Tainan, Taiwan
Ching-Hung Lin
National Taiwan University Hospital Hsinchu Branch, Hsinchu, Taiwan
Yen-Yin Lin
JelloX Biotech Inc., Hsinchu, Taiwan
Margaret Dah-Tsyr Chang
Institute of Molecular and Cellular Biology, National Tsing Hua University, Hsinchu, Taiwan; JelloX Biotech Inc., Hsinchu, Taiwan
Tun-Wen Pai
Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, Taiwan; Corresponding author.
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.
