cs.CVNov 9, 2026

Domain-Adversarial Adaptation from MURA to In-House Radiographs for Improved Adult Elbow Fracture Classification

Authors: M. Bolhassani, W. Furtado, D. Duvall, MJ Negahdar, J. Joshi, S. Contractor, A. Amini

Organizations: Department of Electrical and Computer Engineering, University of Louisville, KY · Radiology Department, University of Louisville, Louisville, KY

Abstract

We studied domain shift in adult elbow fracture classification from radiographs when training on a large public dataset and deploying on a small, institution-specific dataset (UofL). We implemented a domain-adversarial neural network (DANN) to align feature distributions across source (MURA) and target (UofL) domains while optimizing fracture classification. A pretrained convolutional backbone was adapted to grayscale inputs; the task head predicts fracture presence, and a gradient-reversal-based domain head encourages domain-invariant features via adversarial learning. We compared four settings: (1) Source-only, (2) Target-only (limited labels), (3) Naive merge (pooled training), and (4) DANN (MURA to UofL). Evaluation on UofL test data uses AUC-ROC, and accuracy. DANN outperformed Source-only and Naive merge baselines by reducing domain bias without overfitting to the small target set. Ablations showed that progressive adversarial weight, dataset-size-aware domain loss, and domain-balanced sampling improved stability and target performance. Results demonstrated that domain alignment is a practical path to robust clinical generalization from public to local data.

Explore similar work

CardsList
  1. Unsupervised Domain Adaptation for Calcification Classification in Mammography Across Multi-Site Datasets

    Jul 7, 2026Xuan Liu, Derek L. Nguyen, Emily C. Barre +7Unsupervised Domain AdaptationMammography

  2. Improving Generalizability of Hip Fracture Risk Prediction via Domain Adaptation Across Multiple Cohorts

    Feb 20, 2026Shuo Sun, Meiling Zhou, Chen Zhao +8Cross-Dataset GeneralizationClinical Risk Prediction

  3. Ranking-Guided Semi-Supervised Domain Adaptation for Severity Classification

    Apr 2, 2026Shota Harada, Ryoma Bise, Kiyohito Tanaka +1Medical Image ClassificationDistribution Matching