Saved in:
Bibliographic Details
Main Authors: Daouk, Mohammad, Becker, Jan Ulrich, Kambham, Neeraja, Chang, Anthony, Van Nguyen, Hien, Mohan, Chandra
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.07936
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908950357606400
author Daouk, Mohammad
Becker, Jan Ulrich
Kambham, Neeraja
Chang, Anthony
Van Nguyen, Hien
Mohan, Chandra
author_facet Daouk, Mohammad
Becker, Jan Ulrich
Kambham, Neeraja
Chang, Anthony
Van Nguyen, Hien
Mohan, Chandra
contents 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$224) from 365 WSIs across three centers and four stains (PAS, H&E, Jones, Trichrome), labeled as proliferative vs. non-proliferative. We evaluate Bayesian CNN and ViT backbones with Monte Carlo dropout in three settings: (1) stain-only classification; (2) a dual-head model jointly predicting lesion and stain with supervised stain loss; and (3) a dual-head model with label-free stain regularization via entropy maximization on the stain head. In (1), stain identity is trivially learnable, confirming a strong candidate shortcut. In (2), varying the strength and sign of stain supervision strongly modulates stain performance but leaves lesion metrics essentially unchanged, indicating no measurable stain-driven shortcut learning on this multi-stain, multi-center dataset, while overly adversarial stain penalties inflate predictive uncertainty. In (3), entropy-based regularization holds stain predictions near chance without degrading lesion accuracy or calibration. Overall, a carefully curated multi-stain dataset can be inherently robust to stain shortcuts, and a Bayesian dual-head architecture with label-free entropy regularization offers a simple, deployment-friendly safeguard against potential stain-related drift in glomerular AI.
format Preprint
id arxiv_https___arxiv_org_abs_2604_07936
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Shortcut Learning in Glomerular AI: Adversarial Penalties Hurt, Entropy Helps
Daouk, Mohammad
Becker, Jan Ulrich
Kambham, Neeraja
Chang, Anthony
Van Nguyen, Hien
Mohan, Chandra
Computer Vision and Pattern Recognition
Stain variability is a pervasive source of distribution shift and potential shortcut learning in renal pathology AI. We ask whether lupus nephritis glomerular lesion classifiers exploit stain as a shortcut, and how to mitigate such bias without stain or site labels. We curate a multi-center, multi-stain dataset of 9,674 glomerular patches (224$\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.
title Shortcut Learning in Glomerular AI: Adversarial Penalties Hurt, Entropy Helps
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.07936