Stain Style Transfer of Histopathology Images Via Structure-Preserved Generative Learning
This addresses color variation issues in computational histopathology for improved disease diagnosis, representing an incremental advance with specific gains in normalization and efficiency.
The study tackled the problem of color variations in histopathology images, which hinder computational diagnosis, by proposing two stain style transfer models (SSIM-GAN and DSCSI-GAN) that preserve medical-relevant information; the methods outperformed prior arts in generating stain-consistent images and achieved significantly higher learning efficiency.
Computational histopathology image diagnosis becomes increasingly popular and important, where images are segmented or classified for disease diagnosis by computers. While pathologists do not struggle with color variations in slides, computational solutions usually suffer from this critical issue. To address the issue of color variations in histopathology images, this study proposes two stain style transfer models, SSIM-GAN and DSCSI-GAN, based on the generative adversarial networks. By cooperating structural preservation metrics and feedback of an auxiliary diagnosis net in learning, medical-relevant information presented by image texture, structure, and chroma-contrast features is preserved in color-normalized images. Particularly, the smart treat of chromatic image content in our DSCSI-GAN model helps to achieve noticeable normalization improvement in image regions where stains mix due to histological substances co-localization. Extensive experimentation on public histopathology image sets indicates that our methods outperform prior arts in terms of generating more stain-consistent images, better preserving histological information in images, and obtaining significantly higher learning efficiency. Our python implementation is published on https://github.com/hanwen0529/DSCSI-GAN.