# Feature-level Site Leakage Reduction for Cross-Hospital Chest X-ray Transfer via Self-Supervised Learning

Source: [Feature-level Site Leakage Reduction for Cross-Hospital Chest X-ray Transfer via Self-Supervised Learning](<https://www.sota2.com/research/paper/69cdf7f70636e5bf4afcc9da>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-03T05:00:04.568Z

Authors: Ayoub Louaye Bouaziz, Lokmane Chebouba

Published: 2026-03-31T21:44:29.000Z

## Abstract

Cross-hospital failure in chest X-ray models is often attributed to domain shift, yet most work assumes invariance without measuring it. This paper studies how to measure site leakage directly and how that measurement changes conclusions about transfer methods. We study multi-site self-supervised learning (SSL) and feature-level adversarial site confusion for cross-hospital transfer. We pretrain a ResNet-18 on NIH and CheXpert without pathology labels. We then freeze the encoder and train a linear pneumonia classifier on NIH only, evaluating transfer to RSNA. We quantify site leakage using a post hoc linear probe that predicts acquisition site from frozen backbone features $f$ and projection features $z$. Across 3 random seeds, multi-site SSL improves RSNA AUC from 0.6736 $\\pm$ 0.0148 (ImageNet initialization) to 0.7804 $\\pm$ 0.0197. Adding adversarial site confusion on $f$ reduces measured leakage but does not reliably improve AUC and increases variance. On $f$, site probe accuracy drops from 0.9890 $\\pm$ 0.0021 (SSL-only) to 0.8504 $\\pm$ 0.0051 (CanonicalF), where chance is 0.50. On $z$, probe accuracy drops from 0.8912 $\\pm$ 0.0092 to 0.7810 $\\pm$ 0.0250. These results show that measuring leakage changes how transfer methods should be interpreted: multi-site SSL drives transfer, while adversarial confusion exposes the limits of invariance assumptions.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.00263>)

[PDF](<https://arxiv.org/pdf/2604.00263.pdf>)
