Learning to Harmonize Cross-vendor X-ray Images by Non-linear Image Dynamics Correction

2025-04-14

AI Summary

Multi-vendor X-ray images exhibit degraded model generalization due to vendor-specific nonlinear imaging dynamics, leading to exposure mismatch. Method: This paper formulates cross-vendor image harmonization as a nonlinear exposure correction task and proposes Global Deep Curve Estimation (GDCE). GDCE parameterizes the exposure mapping using an interpretable, predefined polynomial structure—replacing opaque black-box transformations—and integrates domain-discriminator-guided adversarial training within a transfer learning framework to learn robust domain-invariant representations. Contribution/Results: Experiments demonstrate that GDCE effectively mitigates exposure mismatch, outperforming conventional linear normalization and state-of-the-art deep harmonization methods in cross-vendor generalization across multiple X-ray classification and detection tasks. Moreover, GDCE enhances model transparency and clinical interpretability through its explicit, physics-informed parametric design.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Non-convex Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

In this paper, we explore how conventional image enhancement can improve model robustness in medical image analysis. By applying commonly used normalization methods to images from various vendors and studying their influence on model generalization in transfer learning, we show that the nonlinear characteristics of domain-specific image dynamics cannot be addressed by simple linear transforms. To tackle this issue, we reformulate the image harmonization task as an exposure correction problem and propose a method termed Global Deep Curve Estimation (GDCE) to reduce domain-specific exposure mismatch. GDCE performs enhancement via a pre-defined polynomial function and is trained with the help of a ``domain discriminator'', aiming to improve model transparency in downstream tasks compared to existing black-box methods.

Problem

• Address nonlinear domain-specific image dynamics in X-rays
• Harmonize cross-vendor X-ray images via exposure correction
• Improve model transparency with Global Deep Curve Estimation

Innovation

• Non-linear correction for X-ray image dynamics
• Global Deep Curve Estimation for harmonization
• Domain discriminator enhances model transparency