Virtual staining for mitosis detection in Breast Histopathology

2020/03/17 by Caner Mercan, Mercan, Caner, Germonda Reijnen-Mooij +11
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #cs.CV #eess.IV #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2003.07801

5 pages, 4 figures. Accepted for publication at the IEEE International Symposium on Biomedical Imaging (ISBI), 2020

arxiv created 2020/03/17 · arxiv updated 2020/03/18

Abstract

We propose a virtual staining methodology based on Generative Adversarial Networks to map histopathology images of breast cancer tissue from H&E stain to PHH3 and vice versa. We use the resulting synthetic images to build Convolutional Neural Networks (CNN) for automatic detection of mitotic figures, a strong prognostic biomarker used in routine breast cancer diagnosis and grading. We propose several scenarios, in which CNN trained with synthetically generated histopathology images perform on par with or even better than the same baseline model trained with real images. We discuss the potential of this application to scale the number of training samples without the need for manual annotations.

Related

• Whole-Slide Mitosis Detection in H&E Breast Histology Using PHH3 as a Reference to Train Distilled Stain-Invariant Convolutional Networks
• Neural Stain Normalization and Unsupervised Classification of Cell Nuclei in Histopathological Breast Cancer Images
• Mitosis Detection for Breast Cancer Pathology Images Using UV-Net
• MITOS-RCNN: A Novel Approach to Mitotic Figure Detection in Breast Cancer Histopathology Images using Region Based Convolutional Neural Networks
• Deep Feature Fusion for Mitosis Counting