AUTHOR=Otálora Sebastian , Atzori Manfredo , Andrearczyk Vincent , Khan Amjad , Müller Henning 

TITLE=Staining Invariant Features for Improving Generalization of Deep Convolutional Neural Networks in Computational Pathology

JOURNAL=Frontiers in Bioengineering and Biotechnology

VOLUME=Volume 7 - 2019

YEAR=2019

URL=https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2019.00198

DOI=10.3389/fbioe.2019.00198

ISSN=2296-4185

ABSTRACT=One of the main obstacles for the implementation of deep convolutional neural networks (DCNNs) in the clinical pathology workflow is their low capability to overcome variability in slide preparation and scanner configuration, that leads to changes in tissue appearance. Some of these variations may not be included in the training data, which means that the models have a risk to not generalize well.
Addressing such variations and evaluating them in reproducible scenarios allows understanding of when the models generalize better, which is crucial for performance improvements and better DCNN models. 
Staining normalization techniques and color augmentation approaches have shown improvements in the generalization of the classification tasks for several tissue types. 
Domain-invariant training of DCNN's is also a promising technique to address the problem of training a single model for different domains, since it includes the source domain information to guide the training towards domain-invariant features, achieving state-of-the-art results in classification tasks. 
In this article, deep domain adaptation in convolutional networks (DANN) is applied to computational pathology and compared with widely used staining normalization and color augmentation methods in two challenging classification tasks.
The classification tasks rely on two openly accessible datasets, targeting  Gleason grading in prostate cancer and mitosis classification in breast tissue.
Quantitative and qualitative results show that the use of DANN helps model generalization to external datasets.  The combination of several techniques to manage color heterogeneity suggests that several methods together, such as color augmentation methods with DANN training, can generalize even further.
The results do not show a single best technique among the considered methods, even when combining them. However,  color augmentation and DANN training obtain most often the best results. The statistical significance of the results and the embeddings visualizations provide useful insights to design better DCNN. Furthermore, in this work, we release for the first time code for DANN evaluation in open access datasets for computational pathology (publicly available at\footnote{\url{https://github.com/sebastianffx/stain_adversarial_learning). This opens the possibility for further research on using DANN models together with techniques that can overcome the tissue preparation differences across datasets to tackle limited generalization.