Towards Histopathological Stain Invariance by Unsupervised Domain Augmentation using Generative Adversarial Networks
This work is significant for pathologists and researchers using deep learning in digital pathology, as it tackles the expensive and time-consuming problem of obtaining labels for each stain, making supervised methods more robust to stain variations.
This paper addresses the problem of domain shift in digital pathology due to varying staining protocols, which limits the application of supervised deep learning. The authors propose an unsupervised augmentation method using adversarial image-to-image translation, which significantly improves glomeruli segmentation across seven different staining modalities compared to other approaches.
The application of supervised deep learning methods in digital pathology is limited due to their sensitivity to domain shift. Digital Pathology is an area prone to high variability due to many sources, including the common practice of evaluating several consecutive tissue sections stained with different staining protocols. Obtaining labels for each stain is very expensive and time consuming as it requires a high level of domain knowledge. In this article, we propose an unsupervised augmentation approach based on adversarial image-to-image translation, which facilitates the training of stain invariant supervised convolutional neural networks. By training the network on one commonly used staining modality and applying it to images that include corresponding, but differently stained, tissue structures, the presented method demonstrates significant improvements over other approaches. These benefits are illustrated in the problem of glomeruli segmentation in seven different staining modalities (PAS, Jones H&E, CD68, Sirius Red, CD34, H&E and CD3) and analysis of the learned representations demonstrate their stain invariance.