Virtual Imaging-Guided Harmonization of Chest X-Rays Using a Generative Adversarial Neural Network
- 1 November 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (11) , 3612-3623
Abstract
To reduce variability in chest radiography (CXR) from acquisition and post-processing, and assess whether harmonization improves image quality and down-stream diagnostic performance. A generative adversarial network (GAN) was trained exclusively on virtual images produced by a Virtual Imaging Trial (VIT). The model maps non-harmonized CXRs to noise-free, unprocessed references using a dual U-Net with contrastive loss. Evaluation spanned virtual, physical-phantom, and clinical data using generic (GIQMs) and chest-specific (CIQMs) metrics. A phantom benchmark compared the method with ComBat harmonization and a conventional denoising algorithm. Clinical generalization was tested on VinDr-CXRs, examining feature compactness via Uniform Manifold Approximation and Projection (UMAP). We also assessed NIH-CXRs, quantifying diagnostic accuracy with bootstrap uncertainty. Compared with non-harmonized images, harmonized CXRs yielded approximately 89% lower NRMSE, 50% higher PSNR, and 86% higher SSIM. On phantom data, CIQM variability fell from 0.255 to 0.026 and was reduced more consistently than with ComBat or denoising. Clinical analyses on VinDr-CXRs showed tighter UMAP clusters for harmonized features, indicating suppression of acquisition-related variability. On NIH-CXRs, training and testing a classifier in the harmonized domain improved diagnostic accuracy over the non-harmonized domain and lowered cross-domain sensitivity; pleural and cardiac categories showed consistent gains, while texture-dependent labels exhibited task-dependent effects. VIT-guided training enables a GAN to harmonize CXRs toward a raw reference, improving quantification variability and harmonizing image representations across systems. The proposed virtual-to-clinical strategy is scalable and generalizable, offering a practical path to standardized CXR appearance and reliable downstream detection across institutions.Keywords
Funding Information
- National Institutes of Health (P41-EB028744)
This publication has 37 references indexed in Scilit:
- X-ray image decomposition for improved magnetic navigationInternational Journal of Computer Assisted Radiology and Surgery, 2023
- Emphysema Quantifications With CT ScanChest, 2022
- Wavelet subband discriminator for efficient unsupervised chest X‐ray image restorationMedical Physics, 2022
- Deep learning for chest X-ray analysis: A surveyMedical Image Analysis, 2021
- Methods for image denoising using convolutional neural network: a reviewComplex & Intelligent Systems, 2021
- Image-Level Harmonization of Multi-site Data Using Image-and-Spatial Transformer Networks2020
- Image Data Validation for Medical Systems2019
- Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentation2018
- Variability in the interpretation of chest radiographs for the diagnosis of pneumonia in childrenJournal of Hospital Medicine, 2011
- Contrast Limited Adaptive Histogram Equalization1994