Mind the Gap: Scanner-induced domain shifts pose challenges for representation learning in histopathology
This addresses domain shift challenges for computer-aided systems in histopathology, though it is incremental in understanding why self-supervised methods underperform in this domain compared to natural images.
The paper tackled scanner-induced domain shifts in histopathology by using self-supervised pre-training with Barlow Triplets to learn scanner-invariant representations for tumor segmentation, but found only limited benefit in downstream task performance.
Computer-aided systems in histopathology are often challenged by various sources of domain shift that impact the performance of these algorithms considerably. We investigated the potential of using self-supervised pre-training to overcome scanner-induced domain shifts for the downstream task of tumor segmentation. For this, we present the Barlow Triplets to learn scanner-invariant representations from a multi-scanner dataset with local image correspondences. We show that self-supervised pre-training successfully aligned different scanner representations, which, interestingly only results in a limited benefit for our downstream task. We thereby provide insights into the influence of scanner characteristics for downstream applications and contribute to a better understanding of why established self-supervised methods have not yet shown the same success on histopathology data as they have for natural images.