Towards Measuring Domain Shift in Histopathological Stain Translation in an Unsupervised Manner

Abstract

Domain shift in digital histopathology can occur when different stains or scanners are used, during stain translation, etc. A deep neural network trained on source data may not generalise well to data that has undergone some domain shift. An important step towards being robust to domain shift is the ability to detect and measure it. This article demonstrates that the PixelCNN and domain shift metric can be used to detect and quantify domain shift in digital histopathology, and they demonstrate a strong correlation with generalisation performance. These findings pave the way for a mechanism to infer the average performance of a model (trained on source data) on unseen and unlabelled target data.

Whole Slide Image Quality in Digital Pathology: Review and Perspectives

“…In [132], Aubreville et al showed that the influence of the color domain shift introduced by different scanners strongly affects the performance of CNN-based mitosis detection on histological H&E slides. In [133], Nisar et al have also shown that it is possible to detect and estimate the staining shift in digital histopathology. To that aim, they considered a domain shift metric measuring the differences between two domains' distributions using features extracted from pre-trained neural networks.…”