Structure Preserving Stain Normalization of Histopathology Images Using Self-Supervised Semantic Guidance
arXiv:2008.02101
Abstract
Although generative adversarial network (GAN) based style transfer is state of the art in histopathology color-stain normalization, they do not explicitly integrate structural information of tissues. We propose a self-supervised approach to incorporate semantic guidance into a GAN based stain normalization framework and preserve detailed structural information. Our method does not require manual segmentation maps which is a significant advantage over existing methods. We integrate semantic information at different layers between a pre-trained semantic network and the stain color normalization network. The proposed scheme outperforms other color normalization methods leading to better classification and segmentation performance.
References in corpus (9)
- Generative Adversarial Network in Medical Imaging: A Review
- Semantically-Guided Representation Learning for Self-Supervised Monocular Depth
- Synergic Adversarial Label Learning for Grading Retinal Diseases via Knowledge Distillation and Multi-task Learning
- Retinal Vasculature Segmentation Using Local Saliency Maps and Generative Adversarial Networks For Image Super Resolution
- Night Time Haze and Glow Removal using Deep Dilated Convolutional Network
- Progressive Generative Adversarial Networks for Medical Image Super resolution
- Registration of Histopathogy Images Using Structural Information From Fine Grained Feature Maps
- sZoom: A Framework for Automatic Zoom into High Resolution Surveillance Videos
- Multi-scale Deep Learning Architecture for Nucleus Detection in Renal Cell Carcinoma Microscopy Image