Data Alchemy: Mitigating Cross-Site Model Variability Through Test Time Data Calibration

TL;DR

Data Alchemy introduces an explainable stain normalization and test time data calibration method that effectively reduces cross-site variability in histopathology imaging, enhancing tumor classification performance without altering model weights.

Contribution

The paper presents a novel explainable stain normalization combined with test time calibration that handles unseen site shifts, improving multi-site tumor classification accuracy.

Findings

Boosts AUPR by 0.165 with normalization

Further improves AUPR to 0.852 after calibration

Reduces inter-site domain gap significantly

Abstract

Deploying deep learning-based imaging tools across various clinical sites poses significant challenges due to inherent domain shifts and regulatory hurdles associated with site-specific fine-tuning. For histopathology, stain normalization techniques can mitigate discrepancies, but they often fall short of eliminating inter-site variations. Therefore, we present Data Alchemy, an explainable stain normalization method combined with test time data calibration via a template learning framework to overcome barriers in cross-site analysis. Data Alchemy handles shifts inherent to multi-site data and minimizes them without needing to change the weights of the normalization or classifier networks. Our approach extends to unseen sites in various clinical settings where data domain discrepancies are unknown. Extensive experiments highlight the efficacy of our framework in tumor classification in hematoxylin and eosin-stained patches. Our explainable normalization method boosts classification tasks' area under the precision-recall curve(AUPR) by 0.165, 0.545 to 0.710. Additionally, Data Alchemy further reduces the multisite classification domain gap, by improving the 0.710 AUPR an additional 0.142, elevating classification performance further to 0.852, from 0.545. Our Data Alchemy framework can popularize precision medicine with minimal operational overhead by allowing for the seamless integration of pre-trained deep learning-based clinical tools across multiple sites.