Search papers, labs, and topics across Lattice.
This paper introduces PAGS, a novel differentiable framework for blind autofocusing in photoacoustic computed tomography (PACT) that addresses the challenge of speed-of-sound (SoS) heterogeneity, which typically causes defocusing artifacts. By utilizing a compact anisotropic path-averaged SoS field parameterized by spherical harmonic probes, PAGS streamlines the reconstruction process without the need for calibrated acoustic priors. Experimental results show that PAGS significantly enhances reconstruction sharpness and robustness in heterogeneous media while also improving computational efficiency through an analytic Gaussian projection method.
PAGS achieves sharper reconstructions in photoacoustic tomography by eliminating the need for calibrated speed-of-sound priors, even in heterogeneous media.
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.
