An exploration of plug-and-play flow matching for full-waveform inversion on breast imaging
Abstract
Full-waveform inversion (FWI) reconstructs sound-speed fields from measured waveforms, by solving an optimization problem that minimizes the discrepancy between measured waveforms and those predicted by a numerical wave-propagation model. However, choosing suitable regularization for this optimization is challenging because it must stabilize the inversion while preserving relevant structures, prompting us to investigate whether priors learned from representative sound-speed images can improve reconstruction. In this work, we adapt plug-and-play flow matching (PnP-Flow) to FWI by alternating waveform-misfit updates with updates from a pretrained flow prior. We explore the effectiveness of PnP-Flow reconstruction by comparing it with total-variation (TV) regularization using noiseless transmission-only plane-wave data. Separate flow priors are trained on two circular-inclusion model families with constant and spatially varying backgrounds. We evaluate the method both on these in-distribution circle models and under substantial distribution shift by transferring the Gaussian-circle prior and reconstruction settings to breast phantom patches without retraining or retuning. Using the same number of waveform-misfit updates, the proposed PnP-Flow framework generally improves circle reconstruction accuracy and recovers breast lesion contrast more accurately than TV baselines.
Related
- Seismic Imaging of the Crust From Long‐Offset Ocean‐Bottom Seismometer Data Using Time‐Domain Extended‐Source Full‐Waveform Inversion: Application to the Eastern Nankai Trough, Japan
- Uncertainty Quantification in Full Waveform Inversion with Gradient Flows in Probability Space
- Structure-aware Bayesian full waveform inversion via diffusion-regularized Stein variational gradient descent
- Full cross-correlation inversion for quantitative passive imaging with time-harmonic acoustic waves
- Extending a new two-grid waveform relaxation on a spatial finite element discretization
BibTeX
@misc{garciacardona2026exploration,
title = {{An exploration of plug-and-play flow matching for full-waveform inversion on breast imaging}},
author = {Cristina Garcia-Cardona and Siting Liu and Fatma Terzioglu and Shanyin Tong and Lu Zhang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.32185},
eprint = {2610.32185},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.32185},
}
RIS
TY - UNPB
TI - An exploration of plug-and-play flow matching for full-waveform inversion on breast imaging
AU - Cristina Garcia-Cardona
AU - Siting Liu
AU - Fatma Terzioglu
AU - Shanyin Tong
AU - Lu Zhang
PY - 2026
DA - 2026/10/23
PB - arXiv
DO - 10.48550/arxiv.2610.32185
UR - https://arxiv.org/abs/2610.32185
AB - Full-waveform inversion (FWI) reconstructs sound-speed fields from measured waveforms, by solving an optimization problem that minimizes the discrepancy between measured waveforms and those predicted by a numerical wave-propagation model. However, choosing suitable regularization for this optimization is challenging because it must stabilize the inversion while preserving relevant structures, prompting us to investigate whether priors learned from representative sound-speed images can improve reconstruction. In this work, we adapt plug-and-play flow matching (PnP-Flow) to FWI by alternating waveform-misfit updates with updates from a pretrained flow prior. We explore the effectiveness of PnP-Flow reconstruction by comparing it with total-variation (TV) regularization using noiseless transmission-only plane-wave data. Separate flow priors are trained on two circular-inclusion model families with constant and spatially varying backgrounds. We evaluate the method both on these in-distribution circle models and under substantial distribution shift by transferring the Gaussian-circle prior and reconstruction settings to breast phantom patches without retraining or retuning. Using the same number of waveform-misfit updates, the proposed PnP-Flow framework generally improves circle reconstruction accuracy and recovers breast lesion contrast more accurately than TV baselines.
ER -