Trevor M. Mitcham | Searcharxiv

arXiv2026

Wave-Equation Migration Velocity Analysis for Multistatic Synthetic Aperture Ultrasound

Sound speed heterogeneities can create aberrations in B-mode ultrasound images by inducing tissue-dependent delays and diffractive effects that conventional beamforming does not incorporate. By using the Fourier split-step method to simulate pressure fields in heterogenous sound speed media, reverse-time migration (RTM) can reconstruct the B-mode image by cross-correlating transmitted and received pressure fields. As a result, RTM is differentiable with respect to sound speed. This enables the reconstruction of the sound speed profile that minimizes the aberration in the B-mode image. In seismic imaging, this form of diffraction tomography, known as wave-equation migration velocity analysis, can roughly be understood as a type of full-waveform inversion (FWI) that acts in the image domain rather than errors in the received channel data. This is the first work applying WEMVA to medical pulse-echo ultrasound imaging. Phantom experiments show dramatic improvements in image quality with measured improvements in point target resolution from 1.22$\pm$1.01 to 0.32$\pm$0.07 mm and lesion contrast from 3.05 to 4.39 dB.

physics.med-ph↗

arXiv2024

Investigating the Use of Traveltime and Reflection Tomography for Deep Learning-Based Sound-Speed Estimation in Ultrasound Computed Tomography

Ultrasound computed tomography (USCT) quantifies acoustic tissue properties such as the speed-of-sound (SOS). Although full-waveform inversion (FWI) is an effective method for accurate SOS reconstruction, it can be computationally challenging for large-scale problems. Deep learning-based image-to-image learned reconstruction (IILR) methods can offer computationally efficient alternatives. This study investigates the impact of the chosen input modalities on IILR methods for high-resolution SOS reconstruction in USCT. The selected modalities are traveltime tomography (TT) and reflection tomography (RT), which produce a low-resolution SOS map and a reflectivity map, respectively. These modalities have been chosen for their lower computational cost relative to FWI and their capacity to provide complementary information: TT offers a direct SOS measure, while RT reveals tissue boundary information. Systematic analyses were facilitated by employing a virtual USCT imaging system with anatomically realistic numerical breast phantoms. Within this testbed, a supervised convolutional neural network (CNN) was trained to map dual-channel (TT and RT images) to a high-resolution SOS map. Single-input CNNs were trained separately using inputs from each modality alone (TT or RT) for comparison. The accuracy of the methods was systematically assessed using normalized root mean squared error (NRMSE), structural similarity index measure (SSIM), and peak signal-to-noise ratio (PSNR). For tumor detection performance, receiver operating characteristic analysis was employed. The dual-channel IILR method was also tested on clinical human breast data. Ensemble average of the NRMSE, SSIM, and PSNR evaluated on this clinical dataset were 0.2355, 0.8845, and 28.33 dB, respectively.

eess.IV↗