Fast, Self Supervised, Fully Convolutional Color Normalization Of H&E Stained Images

  title={Fast, Self Supervised, Fully Convolutional Color Normalization Of H\&E Stained Images},
  author={Abhijeet Patil and Mohd Talha and Aniket Bhatia and Nikhil Cherian Kurian and Sammed Mangale and Sunil Patel and Amit Sethi},
  journal={2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)},
  • Abhijeet PatilM. Talha A. Sethi
  • Published 30 November 2020
  • Computer Science
  • 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)
Performance of deep learning algorithms decreases drastically if the data distributions of the training and testing sets are different. Due to variations in staining protocols, reagent brands, and habits of technicians, color variation in digital histopathology images is quite common. Color variation causes problems for the deployment of deep learning-based solutions for automatic diagnosis system in histopathology. Previously proposed color normalization methods consider a small patch as a… 

Figures and Tables from this paper

Robust Classification of Histology Images Exploiting Adversarial Auto Encoders

A novel method for robust feature generation using an adversarial autoencoder (AAE) and the likelihood of the features in the latent space of AAE as a criterion to weigh the training samples is proposed.

Recent Advances of Deep Learning for Computational Histopathology: Principles and Applications

A comprehensive up-to-date review of the deep learning methods for digital H&E-stained pathology image analysis, including color normalization, nuclei/tissue segmentation, and cancer diagnosis and prognosis.

The devil is in the details: Whole Slide Image acquisition and processing for artifacts detection, color variation, and data augmentation. A review.

A detailed study of the state-of-the-art in three different areas of WSI preprocessing: Artifacts detection, color variation, and the emerging field of pathology-specific data augmentation is presented.

Current Developments of Artificial Intelligence in Digital Pathology and Its Future Clinical Applications in Gastrointestinal Cancers

An overview of the current histological practices in AP laboratories with respect to challenges faced in image preprocessing, present the existing AI-based algorithms, discuss their limitations and present clinical insight with respectto the application of AI in early detection and diagnosis of GI cancer are provided.



Enhanced Cycle-Consistent Generative Adversarial Network for Color Normalization of H&E Stained Images

This work proposes an enhanced cycle-GAN based method with a novel auxiliary input for the generator by computing a stain color matrix for every H&E image in the training set, and thus stabilizes the cycle consistency loss.

Fast GPU-Enabled Color Normalization for Digital Pathology

This work completely rewrote the software of structure preserving color normalization such that it can automatically handle images of any size in popular WSI formats and utilizes GPU-acceleration and open-source libraries that are becoming ubiquitous with the advent of deep learning.

Staingan: Stain Style Transfer for Digital Histological Images

This work proposes a deep-learning solution inspired by CycleGANs that is trained end-to-end, eliminating the need for an expert to pick a representative reference slide, and showed superior results quantitatively and qualitatively against the state of the art methods.

Stain normalization of histopathology images using generative adversarial networks

A novel approach to computational histopathology by introducing a parametric, fully unsupervised generative model based on end-to-end machine learning in the framework of generative adversarial networks that outperforms most state-of-the-art methods.

Adversarial Stain Transfer for Histopathology Image Analysis

A discriminative image analysis model equipped with a stain normalization component that transfers stains across datasets is designed, which achieves superior results in terms of accuracy and quality of normalized images compared to various baselines.

Empirical comparison of color normalization methods for epithelial-stromal classification in H and E images

Color normalization can give a small incremental benefit when a super-pixel-based classification method is used with features that perform implicit color normalization while the gain is higher for patch- based classification methods for classifying epithelium versus stroma.

Classification of Breast Cancer Histology using Deep Learning

A deep learning-based method for classification of H&E stained breast tissue images released for BACH challenge 2018 by fine-tuning Inception-v3 convolutional neural network (CNN) proposed by Szegedy et al.

Self-Attentive Adversarial Stain Normalization

A Self-Attentive Adversarial Stain Normalization (SAASN) approach for the normalization of multiple stain appearances to a common domain that includes self-attention mechanism for synthesizing images with finer detail while preserving the structural consistency of the biopsy features during translation.

Structure Preserving Stain Normalization of Histopathology Images Using Self-Supervised Semantic Guidance

This work proposes a self-supervised approach to incorporate semantic guidance into a GAN based stain normalization framework and preserve detailed structural information, which outperforms other color normalization methods leading to better classification and segmentation performance.

Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning

A deep convolutional neural network model is trained on whole-slide images obtained from The Cancer Genome Atlas to accurately and automatically classify them into LUAD, LUSC or normal lung tissue and predicts the ten most commonly mutated genes in LUAD.