A Learning-based Framework for Spatial Impulse Response Compensation in 3D Photoacoustic Computed Tomography

TL;DR

3D PACT reconstruction quality is limited by the spatial impulse response (SIR) of large-aperture transducers, which introduces spatially varying blur if unmodeled. To address this, the authors present a data-domain learning framework that maps SIR-corrupted measurements to data corresponding to ideal point-like transducers, enabling standard, fast reconstructions that ignore SIR. They explore two architectures, a U-Net and a physics-inspired Deconv-Net, alongside a fast analytical training-data generation procedure. Virtual imaging studies demonstrate resolution gains and robustness to noise, object complexity, and sound-speed heterogeneity, while in vivo breast data show recovered fine structures, marking the first demonstration of learned SIR compensation in 3D PACT.

Abstract

Photoacoustic computed tomography (PACT) is a promising imaging modality that combines the advantages of optical contrast with ultrasound detection. Utilizing ultrasound transducers with larger surface areas can improve detection sensitivity. However, when computationally efficient analytic reconstruction methods that neglect the spatial impulse responses (SIRs) of the transducer are employed, the spatial resolution of the reconstructed images will be compromised. Although optimization-based reconstruction methods can explicitly account for SIR effects, their computational cost is generally high, particularly in three-dimensional (3D) applications. To address the need for accurate but rapid 3D PACT image reconstruction, this study presents a framework for establishing a learned SIR compensation method that operates in the data domain. The learned compensation method maps SIR-corrupted PACT measurement data to compensated data that would have been recorded by idealized point-like transducers. Subsequently, the compensated data can be used with a computationally efficient reconstruction method that neglects SIR effects. Two variants of the learned compensation model are investigated that employ a U-Net model and a specifically designed, physics-inspired model, referred to as Deconv-Net. A fast and analytical training data generation procedure is also a component of the presented framework. The framework is rigorously validated in virtual imaging studies, demonstrating resolution improvement and robustness to noise variations, object complexity, and sound speed heterogeneity. When applied to in-vivo breast imaging data, the learned compensation models revealed fine structures that had been obscured by SIR-induced artifacts. To our knowledge, this is the first demonstration of learned SIR compensation in 3D PACT imaging.