DiffUS: Differentiable Ultrasound Rendering from Volumetric Imaging

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bertramo, Noe, Duguey, Gabriel, Gopalakrishnan, Vivek
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912529918197760
author Bertramo, Noe
Duguey, Gabriel
Gopalakrishnan, Vivek
author_facet Bertramo, Noe
Duguey, Gabriel
Gopalakrishnan, Vivek
contents Intraoperative ultrasound imaging provides real-time guidance during numerous surgical procedures, but its interpretation is complicated by noise, artifacts, and poor alignment with high-resolution preoperative MRI/CT scans. To bridge the gap between reoperative planning and intraoperative guidance, we present DiffUS, a physics-based, differentiable ultrasound renderer that synthesizes realistic B-mode images from volumetric imaging. DiffUS first converts MRI 3D scans into acoustic impedance volumes using a machine learning approach. Next, we simulate ultrasound beam propagation using ray tracing with coupled reflection-transmission equations. DiffUS formulates wave propagation as a sparse linear system that captures multiple internal reflections. Finally, we reconstruct B-mode images via depth-resolved echo extraction across fan-shaped acquisition geometry, incorporating realistic artifacts including speckle noise and depth-dependent degradation. DiffUS is entirely implemented as differentiable tensor operations in PyTorch, enabling gradient-based optimization for downstream applications such as slice-to-volume registration and volumetric reconstruction. Evaluation on the ReMIND dataset demonstrates DiffUS's ability to generate anatomically accurate ultrasound images from brain MRI data.
format Preprint
id arxiv_https___arxiv_org_abs_2508_06768
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DiffUS: Differentiable Ultrasound Rendering from Volumetric Imaging
Bertramo, Noe
Duguey, Gabriel
Gopalakrishnan, Vivek
Computer Vision and Pattern Recognition
Graphics
Intraoperative ultrasound imaging provides real-time guidance during numerous surgical procedures, but its interpretation is complicated by noise, artifacts, and poor alignment with high-resolution preoperative MRI/CT scans. To bridge the gap between reoperative planning and intraoperative guidance, we present DiffUS, a physics-based, differentiable ultrasound renderer that synthesizes realistic B-mode images from volumetric imaging. DiffUS first converts MRI 3D scans into acoustic impedance volumes using a machine learning approach. Next, we simulate ultrasound beam propagation using ray tracing with coupled reflection-transmission equations. DiffUS formulates wave propagation as a sparse linear system that captures multiple internal reflections. Finally, we reconstruct B-mode images via depth-resolved echo extraction across fan-shaped acquisition geometry, incorporating realistic artifacts including speckle noise and depth-dependent degradation. DiffUS is entirely implemented as differentiable tensor operations in PyTorch, enabling gradient-based optimization for downstream applications such as slice-to-volume registration and volumetric reconstruction. Evaluation on the ReMIND dataset demonstrates DiffUS's ability to generate anatomically accurate ultrasound images from brain MRI data.
title DiffUS: Differentiable Ultrasound Rendering from Volumetric Imaging
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2508.06768