WE-UNet: A Wavelet-enhanced U-Net framework for radiation dose reduction in chest radiography

Background

Reducing ionizing radiation exposure is a critical goal guided by the as-low-as-reasonably-achievable (ALARA) principle. Aggressively lowering radiation doses in radiography, however, amplifies image noise, compromising diagnostic quality.

Purpose

To evaluate a hybrid Wavelet Enhanced-UNet (WE-UNet) model for denoising chest radiographs (CXRs), enabling substantial radiation dose reduction while maximizing diagnostic utility.

Methods

A training dataset of 3000 images was created by simulating low-dose conditions (70%–90% dose reduction) on CXRs from a public NIH dataset using Poisson-Gaussian noise modeling. WE-UNet was compared against four established architectures (DnCNN, REDNet, U-Net, MWCNN) using quantitative metrics (MSE, MAE, PSNR, SSIM, edge preservation). Qualitative assessment was performed by two board-certified radiologists in a blinded review.

Results

Among five architectures, WE-UNet achieved the highest SSIM (0.963 ± 0.007) and edge preservation (0.740 ± 0.116; p < 0.001), while DnCNN showed comparable but not significantly better MSE and PSNR. Denoised images maintained PSNR of 35.23 ± 1.11 dB at 90% dose reduction. In blinded review, radiologist quality ratings for denoised images were statistically equivalent to original full-dose acquisitions (p = 0.029, non-significant after correction).

Conclusions

WE-UNet outperformed baseline models in structural preservation while maintaining image quality similar to standard-dose acquisitions across dose reductions of 70%–90%, supporting its potential for significant radiation dose reduction.