通过传感器令牌自注意力实现无矩阵光声图像重建
Matrix-Free Photoacoustic Image Reconstruction via Sensor-Token Self-Attention
浏览论文内容
中文总结 AI 辅助
研究针对光声断层扫描中从稀疏视图传感器测量恢复初始压力分布的不适定逆问题，提出基于Transformer的传感器注意力网络SAN，直接映射原始测量到重建图像，绕过系统矩阵，减少重建时间，实验证明其在多种指标上优于其他方法。
中文摘要 AI 辅助
光声断层扫描（PAT）结合了生物组织的光学吸收对比度和超声的空间分辨率，但从稀疏视图传感器测量中恢复初始压力分布仍然是一个不适定的逆问题。迭代压缩感知求解器和展开的深度网络在推理时都依赖系统矩阵，这使得实时临床重建在计算上成本高昂。本文提出了传感器注意力网络（SAN），这是一种基于Transformer的架构，将每个传感器的完整时间序列视为一个令牌，并在推理时直接将原始测量映射到重建图像，而无需调用系统矩阵。为了进行训练和基准测试，构建了一个解析k空间H矩阵，并在匹配几何条件下与k波伪谱求解器进行验证，平均每个传感器的皮尔逊相关系数为0.919±0.049。使用血管加权损失在488个增强样本上进行训练，并在46个保留样本上与ISTA、分裂Bregman总变差（SBTV）和学习ISTA（LISTA）进行评估，SAN获得了最高的平均结构相似性指数（SSIM）（0.522）和峰值信噪比（PSNR）（22.09 dB）以及最低的归一化均方误差（NMSE）（0.233）。配对t检验和Wilcoxon符号秩检验证实了SAN在PSNR、NMSE和皮尔逊相关系数方面优于LISTA（p<1e-8），在所有保真度指标方面优于ISTA和SBTV。通过在推理时绕过H矩阵，SAN将重建时间减少了至少一个数量级，支持实时PAT重建。
英文摘要
Photoacoustic tomography (PAT) combines the optical absorption contrast of biological tissue with the spatial resolution of ultrasound, yet recovering the initial pressure distribution from sparse-view sensor measurements remains an ill-posed inverse problem. Iterative compressive-sensing solvers and unrolled deep networks both retain a dependence on the system matrix at inference, which leaves real-time clinical reconstruction computationally expensive. This paper proposes the Sensor Attention Network (SAN), a Transformer-based architecture that treats the full time series of each sensor as a token and maps raw measurements directly to the reconstructed image without invoking the system matrix at inference. For training and benchmarking, an analytical k-space H-matrix is constructed and validated against the k-Wave pseudo-spectral solver under matched geometry, achieving a mean per-sensor Pearson correlation of 0.919 +/- 0.049, with k-space apodization and Gaussian temporal damping acting synergistically to reduce the energy-normalized mismatch by 49%. Trained with a vessel-weighted loss on 488 augmented samples and evaluated on 46 held-out samples against ISTA, split-Bregman total variation (SBTV), and learned ISTA (LISTA), SAN attains the highest mean SSIM (0.522) and PSNR (22.09 dB) and the lowest NMSE (0.233). Paired t-tests and Wilcoxon signed-rank tests confirm the superiority of SAN over LISTA on PSNR, NMSE, and Pearson correlation at p < 1e-8, and over ISTA and SBTV on all fidelity metrics. By bypassing the H-matrix at inference, SAN reduces reconstruction time by at least an order of magnitude, supporting real-time PAT reconstruction.
发表机构
- Abu Dhabi Polytechnic（阿布扎比理工学院）
- United Arab Emirates University（阿联酋大学）
机构由 AI 辅助整理，请以论文原文为准。
