发表机构
Shanghai Jiao Tong University; Peking University; National Biomedical Imaging Center; Academy for Advanced Interdisciplinary Studies, Peking University; PKU–Nanjing Institute of Translational Medicine（上海交通大学; 北京大学; 国家生物医学成像中心; 北京大学前沿交叉学科研究院; 北京大学南京转化医学研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PAGS是基于声速自适应高斯溅射的可微分框架，无需声速先验，通过联合优化高斯光声源与声速场，提升了异质介质下光声断层扫描的重建清晰度与稀疏视图鲁棒性，且计算效率更高。
AI 中文摘要
光声计算机断层扫描（PACT）结合了光学吸收对比度与声学检测，用于高分辨率深层组织成像。一个长期存在的挑战是，未知的声速（SoS）异质性会改变声学飞行时间，当重建假设声速均匀时，会产生散焦伪影。现有的声速自适应方法要么依赖校准的声学先验，要么优化密集的物理介质模型，这在三维场景中成本高昂且难以扩展。我们提出PAGS，这是一个基于声速自适应高斯溅射的盲自动聚焦光声断层扫描可微分框架。PAGS用稀疏高斯光声（PA）源表示初始压力场，并用由球谐探针参数化的紧凑各向异性路径平均声速（ASoS）场替代显式介质恢复。该潜传播场直接控制源到换能器的到达时间对齐，而解析高斯声学投影将源表示高效映射到换能器信号。所得的闭环信号域优化从测量数据中联合更新高斯光声源参数和ASoS场，无需校准的声速先验。在模拟和物理体模数据上的实验表明，该方法在异质声学介质下的重建清晰度有所提升，对稀疏视图采样具有鲁棒性，且从解析高斯投影中获得了计算优势。
英文摘要
Photoacoustic computed tomography (PACT) combines optical absorption contrast with acoustic detection for high-resolution deep-tissue imaging. A persistent challenge is that unknown speed-of-sound (SoS) heterogeneity changes acoustic time-of-flight, causing defocusing artifacts when reconstruction assumes a uniform SoS. Existing SoS-adaptive methods either rely on calibrated acoustic priors or optimize dense physical medium models, which becomes expensive and difficult to scale in 3D. We propose PAGS, a differentiable framework for blind autofocusing PACT via speed-of-sound-adaptive Gaussian splatting. PAGS represents the initial pressure field with sparse Gaussian photoacoustic (PA) sources and replaces explicit medium recovery with a compact anisotropic path-averaged SoS (ASoS) field parameterized by spherical harmonic probes. This latent propagation field directly controls source-to-transducer arrival-time alignment, while an analytic Gaussian acoustic projection maps the source representation to transducer signals efficiently. The resulting closed-loop signal-domain optimization jointly updates the Gaussian PA source parameters and the ASoS field from measured data, without calibrated SoS priors. Experiments on simulated and physical phantom data demonstrate improved reconstruction sharpness under heterogeneous acoustic media, robustness to sparse-view sampling, and computational benefits from the analytic Gaussian projection.
Comments13 pages, 6 figures
