Strategies for Training Stain Invariant CNNs

TL;DR

This paper proposes training strategies for CNNs to recognize tissue structures across different staining modalities in digital pathology, reducing the need for extensive annotations and improving stain invariance.

Contribution

It introduces unsupervised training strategies that enable CNNs to generalize across different tissue stainings, advancing stain invariant image analysis.

Findings

Significant improvement over standard training methods.

Effective cross-staining tissue structure recognition.

Reduced annotation requirements for training.

Abstract

An important part of Digital Pathology is the analysis of multiple digitised whole slide images from differently stained tissue sections. It is common practice to mount consecutive sections containing corresponding microscopic structures on glass slides, and to stain them differently to highlight specific tissue components. These multiple staining modalities result in very different images but include a significant amount of consistent image information. Deep learning approaches have recently been proposed to analyse these images in order to automatically identify objects of interest for pathologists. These supervised approaches require a vast amount of annotations, which are difficult and expensive to acquire---a problem that is multiplied with multiple stainings. This article presents several training strategies that make progress towards stain invariant 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 unsupervised strategies demonstrate significant improvements over standard training strategies.