← Back to all news
arXiv AI

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

arXiv:2607. 25576v1 Announce Type: new 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.

Related stories

arXiv Machine Learning
1d ago

Initial condition recovery in nonlinear damped viscous photoacoustic tomography using a convolutional neural network-guided gradient-free optimization framework

The paper tackles the inverse problem of recovering the initial pressure distribution in photoacoustic tomography (PAT) when nonlinear acoustic propagation and viscous attenuation are present. It models these effects with a nonlinear damped viscoelastic wave equation and proves well‑posedness of the forward problem. For the inverse problem, the authors establish existence, uniqueness, and local uniqueness results, and then propose a hybrid reconstruction framework that uses a convolutional neural network to generate an initial guess followed by a gradient‑free sequential quadratic Hamiltonian optimization to enforce the PDE dynamics. Numerical experiments show that this hybrid approach yields better reconstruction quality, contrast, and robustness than either time‑reversal or CNN‑only methods.

By Madhu Gupta, Anwesa Dey, Prapti Tala, Souvik Roy
More like this →
arXiv Computer Vision
Aug 27

PAGS: Autofocusing Photoacoustic Tomography via Speed-of-Sound-Adaptive Gaussian Splatting

PAGS is a new differentiable framework for blind autofocusing in photoacoustic computed tomography (PACT). It represents the initial pressure field with sparse Gaussian photoacoustic sources and models the speed‑of‑sound heterogeneity using a compact anisotropic path‑averaged field parameterized by spherical harmonics. By jointly optimizing the Gaussian source parameters and the speed‑of‑sound field in a closed‑loop signal‑domain approach, PAGS achieves sharper reconstructions in heterogeneous media, remains robust to sparse‑view sampling, and offers computational advantages through an analytic Gaussian acoustic projection.

By Jiarui Ge, Jintao Ma, Bangxu Fan, Jinyan Zhang, Xiaokang Yang, Shuai Na, Xiaoyun Yuan
safety
More like this →