GenMC: Real-Time Generative Monte Carlo Surrogate for Quantitative Photoacoustic Imaging
Abstract
Photoacoustic (PA) imaging provides molecular and functional information about tissue, such as blood oxygen saturation (sO2), yet its clinical translation is hindered by inaccurate quantification. A major source of error is the spectral colouring effect, in which wavelength-dependent optical attenuation distorts the local optical fluence. Monte Carlo (MC) simulation is the gold standard for modelling light transport, but its computational demand precludes real-time use. Here, GenMC is presented, a deep generative framework based on a conditional generative adversarial network that estimates optical fluence distributions from tissue anatomy and literature-derived optical properties, with anatomical priors obtained from co-registered ultrasound images. Trained on MC-generated synthetic datasets, GenMC produces high-fidelity fluence maps in under 30 ms per frame, a four-orders-of-magnitude speed-up over conventional MC simulation, and reaches peak signal-to-noise ratios of up to 36.24 dB in vivo, outperforming UNet and Pix2Pix baselines. Validation in blood-mimicking phantoms and in 37 human volunteers spanning Fitzpatrick skin types III-V demonstrates improved accuracy, robustness, and physiological consistency of sO2 estimation. By enabling real-time, accurate, and reproducible quantification of tissue oxygenation, GenMC addresses a critical barrier to quantitative PA imaging and offers a general strategy for rapid, high-fidelity approximation of light transport in tissue.
Related
- Uncovering Hidden Structural and Mechanical Contrast via Spectral Photoacoustic Imaging
- OGRR-Net: observation-guided residual refinement learning for photoacoustic imaging
- A multimodal adjoint-state formulation of Quantitative Photoacoustic Tomography with external acoustic sources
- Photoacoustic imaging of human brain function through intact adult skulls
- Distinct responses of photoelastic coefficients to He+ ion implantation in LiNbO3 studied by ultrafast photoacoustic imaging
BibTeX
@misc{shi2026genmc,
title = {{GenMC: Real-Time Generative Monte Carlo Surrogate for Quantitative Photoacoustic Imaging}},
author = {Mengjie Shi and Feng He and Tom Vercauteren and Wenfeng Xia},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.28261},
eprint = {2609.28261},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.28261},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - GenMC: Real-Time Generative Monte Carlo Surrogate for Quantitative Photoacoustic Imaging
AU - Mengjie Shi
AU - Feng He
AU - Tom Vercauteren
AU - Wenfeng Xia
PY - 2026
DA - 2026/09/23
PB - arXiv
DO - 10.48550/arxiv.2609.28261
UR - https://arxiv.org/abs/2609.28261
AB - Photoacoustic (PA) imaging provides molecular and functional information about tissue, such as blood oxygen saturation (sO2), yet its clinical translation is hindered by inaccurate quantification. A major source of error is the spectral colouring effect, in which wavelength-dependent optical attenuation distorts the local optical fluence. Monte Carlo (MC) simulation is the gold standard for modelling light transport, but its computational demand precludes real-time use. Here, GenMC is presented, a deep generative framework based on a conditional generative adversarial network that estimates optical fluence distributions from tissue anatomy and literature-derived optical properties, with anatomical priors obtained from co-registered ultrasound images. Trained on MC-generated synthetic datasets, GenMC produces high-fidelity fluence maps in under 30 ms per frame, a four-orders-of-magnitude speed-up over conventional MC simulation, and reaches peak signal-to-noise ratios of up to 36.24 dB in vivo, outperforming UNet and Pix2Pix baselines. Validation in blood-mimicking phantoms and in 37 human volunteers spanning Fitzpatrick skin types III-V demonstrates improved accuracy, robustness, and physiological consistency of sO2 estimation. By enabling real-time, accurate, and reproducible quantification of tissue oxygenation, GenMC addresses a critical barrier to quantitative PA imaging and offers a general strategy for rapid, high-fidelity approximation of light transport in tissue.
ER -