GPAIR: Gaussian-Kernel-Based Ultrafast 3D Photoacoustic Iterative Reconstruction

2026-02-03

AI Summary

This study addresses the challenge of high computational complexity in iterative reconstruction for three-dimensional photoacoustic tomography, which hinders real-time clinical applications. To overcome this limitation, the authors propose an ultrafast reconstruction method based on a continuous isotropic Gaussian kernel. By analytically modeling the pressure wave propagation instead of relying on conventional discrete grid-based formulations, and integrating GPU-accelerated differentiable operators implemented in Triton, the approach achieves highly efficient computation. This work presents the first integration of an analytical Gaussian kernel with custom GPU operators, enabling sub-second 3D reconstruction on an animal dataset comprising 8.4 million voxels. The method accelerates reconstruction by more than one order of magnitude compared to traditional iterative algorithms, substantially advancing the feasibility of real-time 3D photoacoustic imaging in clinical settings.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Kernel Methods
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

Abstract

Although the iterative reconstruction (IR) algorithm can substantially correct reconstruction artifacts in photoacoustic (PA) computed tomography (PACT), it suffers from long reconstruction times, especially for large-scale three-dimensional (3D) imaging in which IR takes hundreds of seconds to hours. The computing burden severely limits the practical applicability of IR algorithms. In this work, we proposed an ultrafast IR method for 3D PACT, called Gaussian-kernel-based Ultrafast 3D Photoacoustic Iterative Reconstruction (GPAIR), which achieves orders-of-magnitude acceleration in computing. GPAIR transforms traditional spatial grids with continuous isotropic Gaussian kernels. By deriving analytical closed-form expression for pressure waves and implementing powerful GPU-accelerated differentiable Triton operators, GPAIR demonstrates extraordinary ultrafast sub-second reconstruction speed for 3D targets containing 8.4 million voxels in animal experiments. This revolutionary ultrafast image reconstruction enables near-real-time large-scale 3D PA reconstruction, significantly advancing 3D PACT toward clinical applications.

Problem

• iterative reconstruction
• photoacoustic computed tomography
• 3D imaging
• reconstruction time
• computational burden

Innovation

• Gaussian kernel
• ultrafast reconstruction
• photoacoustic computed tomography
• iterative reconstruction
• GPU acceleration