DiffUS: Differentiable Ultrasound Rendering from Volumetric Imaging
This work addresses the problem of aligning preoperative MRI with intraoperative ultrasound for surgical guidance, representing an incremental improvement in medical imaging simulation.
The authors tackled the challenge of interpreting intraoperative ultrasound by developing DiffUS, a differentiable ultrasound renderer that synthesizes realistic B-mode images from volumetric MRI scans, achieving anatomically accurate results on the ReMIND dataset.
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.