Inter-Semantic Domain Adversarial in Histopathological Images

TL;DR

This paper investigates the use of domain adversarial methods to improve robustness against data shift in histopathological images, revealing their potential and pitfalls in medical image analysis.

Contribution

It demonstrates that domain adversarial techniques can transfer data shift invariance across different semantic datasets in histopathology.

Findings

Domain adversarial methods can be harmful if misapplied.

They effectively transfer data shift invariance between datasets with different semantics.

Performance is comparable between inter- and intra-semantical domain adversarial methods.

Abstract

In computer vision, data shift has proven to be a major barrier for safe and robust deep learning applications. In medical applications, histopathological images are often associated with data shift and they are hardly available. It is important to understand to what extent a model can be made robust against data shift using all available data. Here, we first show that domain adversarial methods can be very deleterious if they are wrongly used. We then use domain adversarial methods to transfer data shift invariance from one dataset to another dataset with different semantics and show that domain adversarial methods are efficient inter-semantically with similar performance than intra-semantical domain adversarial methods.