Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces the Sensor Attention Network (SAN), a Transformer-based architecture that reconstructs photoacoustic images directly from sensor measurements without relying on the system matrix during inference. By treating the time series of each sensor as a token, SAN achieves significant improvements in reconstruction fidelity, demonstrated by superior performance metrics compared to traditional methods like ISTA and SBTV. The results show that SAN not only enhances image quality but also reduces reconstruction time by over tenfold, making real-time clinical applications feasible.
Bypassing the system matrix at inference, SAN achieves real-time photoacoustic image reconstruction while significantly improving fidelity metrics over existing methods.
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.