Search arXiv⌕ Search

arXiv · 2611.10197

Physics-Based Differentiable Beamforming for Deep Learning-Based Contrast Enhanced Ultrasound Super-Resolution Imaging

Abstract

Ultrasound is widely used for vascular imaging because it is non-invasive, real-time, and cost-effective. However, its spatial resolution remains limited by diffraction to an order of the acoustic wavelength. This limitation is particularly restrictive for imaging of the microvasculature and high-resolution vector-flow-imaging. In this work, we present a multi-channel physics-based deep learning approach to super-resolve monodisperse microbubbles directly from multi-channel radio-frequency (RF) data. We also present a novel image-based metric for model evaluation. The proposed pipeline combines a learnable deconvolution network with a differentiable beamforming layer, enabling a direct deconvolution of the microbubble (MB) signature prior to image formation. By operating on multi-channel RF data, the method aims to improve localization robustness in the presence of dense microbubble populations and deconvolve the lateral direction in a relatively low-frequency regime (1.7 MHz) where MBs exhibit nonlinear behavior. The model is trained and evaluated on simulated data using monodisperse lipid-coated MBs over a broad range of acoustic pressures and microbubble densities. The proposed method improves the signal-to-noise ratio (SNR) compared to the single-channel approach. It achieves sub-wavelength axial and lateral resolution while slightly improving robustness to dense microbubble populations outside the training domain. It also demonstrates generalizability across transmit configurations without requiring explicit training on each transmit configuration.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Anass Hameddine, Bram de Wilde, Michel Versluis, Jelmer M. Wolterink, Guillaume Lajoinie. 2026-11-06. Physics-Based Differentiable Beamforming for Deep Learning-Based Contrast Enhanced Ultrasound Super-Resolution Imaging. https://arxiv.org/abs/2611.10197

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

Continuous 3-D Latent Diffusion for Medical Image Generation and Reconstruction

High-resolution three-dimensional (3-D) medical latent diffusion remains limited by the cost of decoding full volumes, which existing latent autoencoders (AEs) handle through overlapping sub-volume decoding. We propose a continuous 3-D latent diffusion model framework for computed tomography (CT) and magnetic resonance imaging (MRI) generation and measurement-guided reconstruction, built on a coordinate-rendering autoencoder (CoRe-AE). Its decoder applies its convolutional stage once on the compact latent grid and renders voxel intensities from spatial coordinates through a lightweight implicit head, evaluated in memory-bounded chunks. This design avoids overlapping sub-volumes and remains differentiable with respect to the latent, so that the decoder can be used inside measurement-guided reconstruction. The framework was evaluated on CT volumes of 512\textsuperscript{3} voxels and MRI volumes of 256\textsuperscript{3} voxels. At 512\textsuperscript{3}, the decoder was 4--18 times faster than the MAISI and 3D MedDiffusion AEs and required the lowest peak graphics processing unit (GPU) memory, including when its gradient was computed. CoRe-AE also achieved the highest peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) among the evaluated AEs on both modalities. The resulting frozen 3-D latent prior generated full volumes without patch seams and, without retraining, reconstructed sparse-view CT and accelerated MRI through hard data consistency, within 2.4--4.9 dB PSNR of the pixel-domain decomposed diffusion sampler (DDS). A single volumetric latent prior thus supports both generation and reconstruction of high-resolution medical volumes on one GPU. Our code and pretrained weights are available at https://github.com/Mellak/continuous-3d-latent-diffusion.

physics.med-ph↗

Dual-energy cardiac DSA imaging using a dual-layer flat-panel detector: in vivo validation study

Background: The temporal misregistration in conventional X-ray digital subtraction angiography (DSA) remains a key challenge for its practical application in cardiac catheterization, leading to incomplete separation of cardiac vessels from background anatomical structures. Purpose: In this study, the X-ray spectral information is unveiled for DSA imaging to generate better visualization of cardiac vessels with negligible anatomical background. Methods: A dedicated dual-energy DSA imaging model is proposed based on the subtraction residuals between pre-contrast and post-contrast spectral projections, enabling accurate material decomposition without requiring precise scatter correction. Specifically, a dual-layer flat-panel detector (DL-FPD) is assumed to acquire the needed temporally registered low-energy and high-energy projections. Moreover, a penalized likelihood material decomposition algorithm is proposed to enhance the material decomposition performance. To validate, in vivo swine experiments were conducted for the first time on a clinical DSA system equipped with a DL-FPD. Results: Monte Carlo simulation results demonstrated that the impact of scatter on the subtraction residuals can be reduced by more than 80%, substantially improving material decomposition accuracy. Compared with analytical material decomposition, the penalized-likelihood material decomposition algorithm significantly improves image contrast-to-noise ratio (CNR), enabling the visualization of small vessels and even the myocardial blush effect. Furthermore, compared with conventional dual-energy subtraction, the penalized-likelihood approach provides more quantitative material maps with fewer overlapping anatomical background artifacts. Conclusion: This preliminary study verifies that dual-energy DSA imaging method is able to generate high-quality cardiovascular imaging results.

physics.med-ph↗

Smart Spectral Doppler Ultrasound Imaging using Motion Tracking based on Wide-beam transmission and Neural Networks: Preliminary Results

Ultrasound spectral Doppler imaging provides quantitative blood flow information for vascular diagnosis, but its accuracy is limited by the one-dimensional (1D) sample volume (SV). Motion from respiration, patient movement, and probe manipulation can move the target vessel out of the SV, causing spectral broadening, signal reduction, or loss of the spectrum. A two-dimensional (2D) SV can address this, but sequential focused-beam transmission reduces the pulse-repetition frequency (PRF), and plane-wave transmission lowers the signal-to-noise ratio (SNR). In this study, we propose a wide-beam transmission method that acquires a 2D SV from a single transmit event while preserving the PRF. A Hamming network, which requires no prior training, tracks axial and lateral motion within the 2D SV and updates the position of an adaptive 1D SV for each frame. Field II simulations showed that the wide-beam transmission had a spectral SNR comparable to that of focused-beam transmission and approximately 10 dB higher than that of plane-wave transmission. The motion tracking correctly detected the target position in over 93% of frames for vessel radii greater than 1 mm, and in 100% of frames for radii greater than 2 mm. In vivo studies of a carotid artery (linear array) and a hepatic vein (convex array) showed that the proposed method recovered obscured spectra and increased the spectral SNR by 9.3 dB and 4.5 dB, respectively. These results demonstrate that the proposed wide-beam transmission with Hamming network-based tracking can improve the accuracy of spectral Doppler imaging under tissue motion. Moreover, we anticipate that the proposed approach can be implemented in real-time due to its single transmission and simple two-layer architecture with low computational complexity.

physics.med-ph↗