Accelerating 3D Photoacoustic Computed Tomography with End-to-End Physics-Aware Neural Operators

2025-09-11

AI Summary

To address the clinical deployment bottleneck of 3D photoacoustic computed tomography (PACT)—namely, its reliance on dense sensor arrays and prolonged acquisition times—this work proposes Pano, an end-to-end physics-informed neural operator. Pano integrates spherical discrete-continuous convolution to preserve sensor geometry, embeds the Helmholtz equation as a hard physical constraint to ensure acoustic consistency, and achieves resolution-agnostic and sparse-sampling generalization. Evaluated on both simulated and experimental data, Pano enables real-time, high-fidelity volumetric 3D reconstruction using only a small number of transducers and limited-view acquisitions, maintaining image quality while substantially reducing hardware cost. Its core contribution lies in the first rigorous unification of first-principles physical modeling with neural operators, enabling high-fidelity, low-sampling-rate, multi-scale inverse acoustic mapping.

Technology Category

• Computer Vision: 3D Computer Vision
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Security and Privacy: Data transparency and provenance
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Photoacoustic computed tomography (PACT) combines optical contrast with ultrasonic resolution, achieving deep-tissue imaging beyond the optical diffusion limit. While three-dimensional PACT systems enable high-resolution volumetric imaging for applications spanning transcranial to breast imaging, current implementations require dense transducer arrays and prolonged acquisition times, limiting clinical translation. We introduce Pano (PACT imaging neural operator), an end-to-end physics-aware model that directly learns the inverse acoustic mapping from sensor measurements to volumetric reconstructions. Unlike existing approaches (e.g. universal back-projection algorithm), Pano learns both physics and data priors while also being agnostic to the input data resolution. Pano employs spherical discrete-continuous convolutions to preserve hemispherical sensor geometry, incorporates Helmholtz equation constraints to ensure physical consistency and operates resolutionindependently across varying sensor configurations. We demonstrate the robustness and efficiency of Pano in reconstructing high-quality images from both simulated and real experimental data, achieving consistent performance even with significantly reduced transducer counts and limited-angle acquisition configurations. The framework maintains reconstruction fidelity across diverse sparse sampling patterns while enabling real-time volumetric imaging capabilities. This advancement establishes a practical pathway for making 3D PACT more accessible and feasible for both preclinical research and clinical applications, substantially reducing hardware requirements without compromising image reconstruction quality.

Problem

• Reducing transducer count and acquisition time in 3D PACT
• Learning inverse acoustic mapping from sensor to volumetric data
• Maintaining reconstruction quality with sparse sampling configurations

Innovation

• End-to-end physics-aware neural operator model
• Spherical discrete-continuous convolution operations
• Helmholtz equation constraints for physical consistency