Quality Enhancement of Radiographic X-ray Images by Interpretable Mapping

2025-01-21

AI Summary

To address inconsistent brightness and contrast in X-ray images arising from varying acquisition conditions, this paper proposes an interpretable pixel-wise mapping enhancement method. The approach innovatively models the clinical windowing process, designing a deep learning network that jointly ensures global consistency and local adaptability for end-to-end, yet non-black-box, brightness–contrast correction. By explicitly incorporating clinical priors, the model’s decision-making process becomes traceable and verifiable, significantly enhancing clinician trust. Evaluated on real-world clinical datasets, the method achieves 24.75 dB PSNR and 0.8431 SSIM—substantially outperforming both conventional and state-of-the-art deep learning methods. It delivers high-quality, highly consistent, and fully interpretable image enhancement while preserving anatomical fidelity.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Transparent, Interpretable, Explainable ML
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Security and Privacy: Data transparency and provenance

Abstract

X-ray imaging is the most widely used medical imaging modality. However, in the common practice, inconsistency in the initial presentation of X-ray images is a common complaint by radiologists. Different patient positions, patient habitus and scanning protocols can lead to differences in image presentations, e.g., differences in brightness and contrast globally or regionally. To compensate for this, additional work will be executed by clinical experts to adjust the images to the desired presentation, which can be time-consuming. Existing deep-learning-based end-to-end solutions can automatically correct images with promising performances. Nevertheless, these methods are hard to be interpreted and difficult to be understood by clinical experts. In this manuscript, a novel interpretable mapping method by deep learning is proposed, which automatically enhances the image brightness and contrast globally and locally. Meanwhile, because the model is inspired by the workflow of the brightness and contrast manipulation, it can provide interpretable pixel maps for explaining the motivation of image enhancement. The experiment on the clinical datasets show the proposed method can provide consistent brightness and contrast correction on X-ray images with accuracy of 24.75 dB PSNR and 0.8431 SSIM.

Problem

• X-ray images
• contrast variation
• consistent quality

Innovation

• Deep Learning
• Image Enhancement
• Interpretable Algorithm