Blind Ultrasound Image Enhancement via Self-Supervised Physics-Guided Degradation Modeling

TL;DR

This work tackles ultrasound image degradation from speckle and PSF blur by proposing a blind, self-supervised enhancement framework that trains a Swin Convolutional U‑Net using a physics-guided degradation model to synthesize diverse artifacts without clean targets. The approach leverages a joint deconvolution–denoising objective, with ultrasound targets generated via non-local low-rank denoising and natural images using originals, enabling robust learning across datasets. Extensive experiments show consistent PSNR/SSIM gains under Gaussian and speckle noise, improved spatial resolution (FWHM and gradients), and meaningful improvements in downstream segmentation, establishing a practical, generalizable preprocessor for US pipelines. The method reduces dependence on scanner-specific calibrations and clean references, offering a scalable path toward reliable US enhancement across devices and degradation types.

Abstract

Ultrasound (US) interpretation is hampered by multiplicative speckle, acquisition blur from the point-spread function (PSF), and scanner- and operator-dependent artifacts. Supervised enhancement methods assume access to clean targets or known degradations; conditions rarely met in practice. We present a blind, self-supervised enhancement framework that jointly deconvolves and denoises B-mode images using a Swin Convolutional U-Net trained with a \emph{physics-guided} degradation model. From each training frame, we extract rotated/cropped patches and synthesize inputs by (i) convolving with a Gaussian PSF surrogate and (ii) injecting noise via either spatial additive Gaussian noise or complex Fourier-domain perturbations that emulate phase/magnitude distortions. For US scans, clean-like targets are obtained via non-local low-rank (NLLR) denoising, removing the need for ground truth; for natural images, the originals serve as targets. Trained and validated on UDIAT~B, JNU-IFM, and XPIE Set-P, and evaluated additionally on a 700-image PSFHS test set, the method achieves the highest PSNR/SSIM across Gaussian and speckle noise levels, with margins that widen under stronger corruption. Relative to MSANN, Restormer, and DnCNN, it typically preserves an extra $\sim$1--4\,dB PSNR and 0.05--0.15 SSIM in heavy Gaussian noise, and $\sim$2--5\,dB PSNR and 0.05--0.20 SSIM under severe speckle. Controlled PSF studies show reduced FWHM and higher peak gradients, evidence of resolution recovery without edge erosion. Used as a plug-and-play preprocessor, it consistently boosts Dice for fetal head and pubic symphysis segmentation. Overall, the approach offers a practical, assumption-light path to robust US enhancement that generalizes across datasets, scanners, and degradation types.

Figures (13)

• Figure 1: Physics-guided noise degradation pipeline used for training data augmentation.
• Figure 2: Hybrid Swin-Convolution block. Input channels are split evenly into a local conv path and a shifted–window attention path, fused with $1{\times}1$ projection, and added residually to the input.
• Figure 3: Overall Swin–Conv U–Net. Three encoder stages ($\downarrow$), bottleneck, and three decoder stages ($\uparrow$) with additive cross–scale fusions. Downsampling uses stride–2 conv; upsampling uses stride–2 transposed conv.
• Figure 4: Sample images from datasets: (a) UDIAT, (b) JNU-IFM, (c) XPIE Set-P, and (d) PSFHS Test.
• Figure 5: Resolution recovery under increasing PSF blur ($\sigma=0,3,7,15$). First/Third row: full frames; second row: ROI zoom-ins; fourth row: 1D intensity profiles comparing inputs vs. proposed method outputs.