Matrix-Free Photoacoustic Image Reconstruction via Sensor-Token Self-Attention

• URL: http://arxiv.org/abs/2607.25576v1
• Date: Tue, 28 Jul 2026 11:00:28 GMT
• Title: Matrix-Free Photoacoustic Image Reconstruction via Sensor-Token Self-Attention
• Abstract summary: Photoacoustic tomography (PAT) combines the optical absorption contrast of biological tissue with the spatial resolution of ultrasound.<n>Iterative compressive-sensing solvers and unrolled deep networks retain a dependence on the system matrix at inference.<n>This paper proposes the Sensor Attention Network (SAN), a Transformer-based architecture that treats the full time series of each sensor as a token.
• Score: 0.9949801888214528
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Luminosity-Adaptive Contrast Enhancement Using CLAHE for Retinal Fundus Images with Quantitative Validation and Comparative Analysis [0.0]
  Clinical utility of fundus images is routinely compromised by non-uniform illumination, motion blur, and low contrast.<n>This study proposes a two-stage image enhancement pipeline combining luminosity correction via HSV colour space decomposition with Contrast Limited Adaptive Histogram Equalization.
  arXiv  Detail & Related papers  (2026-07-20T08:39:13Z)
• Multi-Contrast MRI Motion Correction via Parameter-Informed Disentanglement and Adaptive Experts [56.74856091904914]
  We propose a unified framework combining parameter-informed contrast disentanglement with severity-aware adaptive correction.<n>ScanCLIP derives contrast embeddings from acquisition parameters to disentangle contrast style from anatomical content, yielding contrast-free features.<n>A Vision Transformer then estimates motion severity and routes features through a Mixture-of-Experts network, enabling targeted artifact correction.
  arXiv  Detail & Related papers  (2026-05-29T02:48:23Z)
• Compressed BC-LISTA via Low-Rank Convolutional Decomposition [47.15001096567547]
  We study Sparse Signal Recovery (SSR) methods for multichannel imaging with compressed forward and backward operators.<n>We propose a Compressed Block-Convolutional (CBC) measurement model based on a low-rank Convolutional Network (CNN) decomposition.
  arXiv  Detail & Related papers  (2026-01-30T16:33:51Z)
• A Hybrid Deep Learning Model for Robust Biometric Authentication from Low-Frame-Rate PPG Signals [0.34376560669160394]
  Photoplethymography (volution) signals, which measure changes in blood volume in the skin using light, have recently gained attention in biometric authentication.<n>Photoplethymography signal quality is challenged by motion artifacts, illumination changes, and inter-subject physiological variability.<n>This study proposes a lightweight and cost-effective biometric authentication framework based on PPG signals extracted from low-frame-rate fingertip videos.
  arXiv  Detail & Related papers  (2025-11-06T04:16:13Z)
• Accelerating 3D Photoacoustic Computed Tomography with End-to-End Physics-Aware Neural Operators [74.65171736966131]
  Photoacoustic computed tomography (PACT) combines optical contrast with ultrasonic resolution, achieving deep-tissue imaging beyond the optical diffusion limit.<n>Current implementations require dense transducer arrays and prolonged acquisition times, limiting clinical translation.<n>We introduce Pano, an end-to-end physics-aware model that directly learns the inverse acoustic mapping from sensor measurements to volumetric reconstructions.
  arXiv  Detail & Related papers  (2025-09-11T23:12:55Z)
• Evaluation of Machine Learning Reconstruction Techniques for Accelerated Brain MRI Scans [0.0]
  DeepFoqus-Accelerate enables robust fourfold brain MRI acceleration with 75% reduced scan time.<n>These findings demonstrate that DeepFoqus-Accelerate enables robust fourfold brain MRI acceleration with 75% reduced scan time.
  arXiv  Detail & Related papers  (2025-09-08T20:20:24Z)
• JSover: Joint Spectrum Estimation and Multi-Material Decomposition from Single-Energy CT Projections [45.14515691206885]
  Multi-material decomposition (MMD) enables quantitative reconstruction of tissue compositions in the human body.<n>Traditional MMD typically requires spectral CT scanners and pre-measured X-ray energy spectra, significantly limiting clinical applicability.<n>This paper proposes JSover, a fundamentally reformulated one-step SEMMD framework that jointly reconstructs multi-material compositions and estimates the energy spectrum directly from SECT projections.
  arXiv  Detail & Related papers  (2025-05-12T23:32:21Z)
• Cycle-Constrained Adversarial Denoising Convolutional Network for PET Image Denoising: Multi-Dimensional Validation on Large Datasets with Reader Study and Real Low-Dose Data [9.160782425067712]
  We propose a Cycle-versa Adrial Denoising Convolutional Network (Cycle-DCN) to reconstruct full-dose-quality images from low-dose scans. Experiments were conducted on a large dataset consisting of raw PET brain data from 1,224 patients. Cycle-DCN significantly improves average Peak Signal-to-Noise Ratio (PSNR), SSIM, and Normalized Root Mean Square Error (NRMSE) across three dose levels.
  arXiv  Detail & Related papers  (2024-10-31T04:34:28Z)
• Learning-based sound speed estimation and aberration correction in linear-array photoacoustic imaging [3.190109710735486]
  Photoacoustic (PA) image reconstruction involves the specification of the speed of sound (SoS) within the medium of propagation. Due to the lack of information on the spatial distribution of the SoS within heterogeneous soft tissue, a homogeneous SoS distribution is typically assumed in PA image reconstruction. We introduce a deep learning framework for SoS estimation and subsequent aberration correction in a dual-modal PA/US imaging system.
  arXiv  Detail & Related papers  (2023-06-19T15:58:10Z)
• Generalizable synthetic MRI with physics-informed convolutional networks [57.628770497971246]
  We develop a physics-informed deep learning-based method to synthesize multiple brain magnetic resonance imaging (MRI) contrasts from a single five-minute acquisition. We investigate its ability to generalize to arbitrary contrasts to accelerate neuroimaging protocols.
  arXiv  Detail & Related papers  (2023-05-21T21:16:20Z)
• OCT-GAN: Single Step Shadow and Noise Removal from Optical Coherence Tomography Images of the Human Optic Nerve Head [47.812972855826985]
  We developed a single process that successfully removed both noise and retinal shadows from unseen single-frame B-scans within 10.4ms. The proposed algorithm reduces the necessity for long image acquisition times, minimizes expensive hardware requirements and reduces motion artifacts in OCT images.
  arXiv  Detail & Related papers  (2020-10-06T08:32:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.