SCORPION: Addressing Scanner-Induced Variability in Histopathology

TL;DR

This paper introduces SCORPION, a dataset for evaluating model consistency across different digital scanners in histopathology, and proposes SimCons, a framework to improve scanner generalization without sacrificing accuracy.

Contribution

The paper presents SCORPION, a novel dataset for assessing scanner-induced variability, and introduces SimCons, a new method combining augmentation and consistency loss to enhance scanner generalization.

Findings

SimCons improves model consistency across scanners.

SCORPION enables rigorous evaluation of scanner variability.

Models trained with SimCons maintain task performance while increasing reliability.

Abstract

Ensuring reliable model performance across diverse domains is a critical challenge in computational pathology. A particular source of variability in Whole-Slide Images is introduced by differences in digital scanners, thus calling for better scanner generalization. This is critical for the real-world adoption of computational pathology, where the scanning devices may differ per institution or hospital, and the model should not be dependent on scanner-induced details, which can ultimately affect the patient's diagnosis and treatment planning. However, past efforts have primarily focused on standard domain generalization settings, evaluating on unseen scanners during training, without directly evaluating consistency across scanners for the same tissue. To overcome this limitation, we introduce SCORPION, a new dataset explicitly designed to evaluate model reliability under scanner variability. SCORPION includes 480 tissue samples, each scanned with 5 scanners, yielding 2,400 spatially aligned patches. This scanner-paired design allows for the isolation of scanner-induced variability, enabling a rigorous evaluation of model consistency while controlling for differences in tissue composition. Furthermore, we propose SimCons, a flexible framework that combines augmentation-based domain generalization techniques with a consistency loss to explicitly address scanner generalization. We empirically show that SimCons improves model consistency on varying scanners without compromising task-specific performance. By releasing the SCORPION dataset and proposing SimCons, we provide the research community with a crucial resource for evaluating and improving model consistency across diverse scanners, setting a new standard for reliability testing.