Abstract
Machine learning models can achieve strong test performance while relying on demographic or acquisition-related shortcuts. We propose counterfactual (CF) marginalisation as a test-time evaluation procedure for assessing robustness of classification models to such variables. Given a CF image generator, we intervene on nuisance parent variables such as age or sex, generate CF versions of each test image, and average predictions over a target intervention distribution. This produces intervention-aware predictions that marginalise demographic effects while preserving patient-specific latent information. We use these predictions to define metrics for CF risk, calibration, stability and worst-case sensitivity. We demonstrate this framework’s utility for quantitative robustness evaluation.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/UNSURE2026_035.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/profile?id=~Yasin_Ibrahim1
BibTex
@InProceedings{IbrYas_Counterfactual_MICCAISAT2026,
author = { Ibrahim, Yasin AND Warr, Hermione AND Evans, Robin J. AND Kamnitsas, Konstantinos},
title = { { Counterfactual Marginalisation: Framework for Evaluating Robustness to Nuisance Variables } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17260},
month = {pending},
page = {pending}
}