Shortcut Learning in Glomerular AI: Adversarial Penalties Hurt, Entropy Helps
This addresses potential bias in renal pathology AI for medical applications, but the findings are incremental as no measurable shortcut learning was detected in the dataset.
The study investigated whether lupus nephritis glomerular lesion classifiers exploit stain variability as a shortcut and found that a curated multi-stain dataset was inherently robust, with entropy regularization maintaining stain predictions near chance without degrading lesion accuracy.
Stain variability is a pervasive source of distribution shift and potential shortcut learning in renal pathology AI. We ask whether lupus nephritis glomerular lesion classifiers exploit stain as a shortcut, and how to mitigate such bias without stain or site labels. We curate a multi-center, multi-stain dataset of 9{,}674 glomerular patches (224$\times$224) from 365 WSIs across three centers and four stains (PAS, H\&E, Jones, Trichrome), labeled as proliferative vs.\ non-proliferative. We evaluate Bayesian CNN and ViT backbones with Monte Carlo dropout in three settings: (1) stain-only classification; (2) a dual-head model jointly predicting lesion and stain with supervised stain loss; and (3) a dual-head model with label-free stain regularization via entropy maximization on the stain head. In (1), stain identity is trivially learnable, confirming a strong candidate shortcut. In (2), varying the strength and sign of stain supervision strongly modulates stain performance but leaves lesion metrics essentially unchanged, indicating no measurable stain-driven shortcut learning on this multi-stain, multi-center dataset, while overly adversarial stain penalties inflate predictive uncertainty. In (3), entropy-based regularization holds stain predictions near chance without degrading lesion accuracy or calibration. Overall, a carefully curated multi-stain dataset can be inherently robust to stain shortcuts, and a Bayesian dual-head architecture with label-free entropy regularization offers a simple, deployment-friendly safeguard against potential stain-related drift in glomerular AI.