Deep preferential evolution guided by pairwise comparisons enables motion correction in photoacoustic tomography
Abstract
Motion artifacts in three-dimensional photoacoustic tomography (PAT), caused by extended mechanical scanning of sparse arrays, degrade image quality. Since sparse sampling results in low-quality sub-reconstructions, tracking motion directly is challenging. While final image quality could in principle guide artifact correction, conventional regularizers do not accurately reflect photoacoustic image quality. Here, we introduce deep preferential evolution (DPE), a derivative-free optimization framework where a learned image comparator guides evolutionary search over reconstruction parameters. By learning relative quality differences between same-target image pairs rather than absolute quality scores, the comparator generalized more robustly from simulation to in-vivo images (after unlabeled domain calibration) than an absolute scorer. Comparator-based DPE successfully corrected synthetic motion across diverse anatomies and backgrounds, and it mitigated artifacts from natural, unconstrained motion in human palm images. These results demonstrate that pairwise learned comparison can provide a transferable optimization objective for high-dimensional image restoration when labeled experimental training data are scarce.
Related
- A multimodal adjoint-state formulation of Quantitative Photoacoustic Tomography with external acoustic sources
- Hypoxia-correlated functional photoacoustic tomography enhances breast tumor detection
- An angular distortion matrix approach for joint wave-speed tomography and aberration correction in scattering media
- Uncovering Hidden Structural and Mechanical Contrast via Spectral Photoacoustic Imaging
- OGRR-Net: observation-guided residual refinement learning for photoacoustic imaging
BibTeX
@misc{sastry2026deep,
title = {{Deep preferential evolution guided by pairwise comparisons enables motion correction in photoacoustic tomography}},
author = {Karteekeya Sastry and Yousuf Aborahama and Junhao Zhu and Manxiu Cui and Lihong V. Wang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.12273},
eprint = {2610.12273},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.12273},
}
RIS
TY - UNPB
TI - Deep preferential evolution guided by pairwise comparisons enables motion correction in photoacoustic tomography
AU - Karteekeya Sastry
AU - Yousuf Aborahama
AU - Junhao Zhu
AU - Manxiu Cui
AU - Lihong V. Wang
PY - 2026
DA - 2026/10/08
PB - arXiv
DO - 10.48550/arxiv.2610.12273
UR - https://arxiv.org/abs/2610.12273
AB - Motion artifacts in three-dimensional photoacoustic tomography (PAT), caused by extended mechanical scanning of sparse arrays, degrade image quality. Since sparse sampling results in low-quality sub-reconstructions, tracking motion directly is challenging. While final image quality could in principle guide artifact correction, conventional regularizers do not accurately reflect photoacoustic image quality. Here, we introduce deep preferential evolution (DPE), a derivative-free optimization framework where a learned image comparator guides evolutionary search over reconstruction parameters. By learning relative quality differences between same-target image pairs rather than absolute quality scores, the comparator generalized more robustly from simulation to in-vivo images (after unlabeled domain calibration) than an absolute scorer. Comparator-based DPE successfully corrected synthetic motion across diverse anatomies and backgrounds, and it mitigated artifacts from natural, unconstrained motion in human palm images. These results demonstrate that pairwise learned comparison can provide a transferable optimization objective for high-dimensional image restoration when labeled experimental training data are scarce.
ER -