Self-Supervised Angular Deblurring in Photoacoustic Reconstruction via Noisier2Inverse

TL;DR

This paper introduces a self-supervised angular deblurring method for photoacoustic tomography that improves image quality without needing ground-truth data, leveraging a Noisier2Inverse approach and domain-specific modeling.

Contribution

It presents a novel self-supervised reconstruction technique tailored for finite-detector effects in PAT, using angular deblurring and a Noisier2Inverse framework in the polar domain.

Findings

Outperforms non-supervised methods in image quality

Achieves near-supervised benchmark performance

Operates effectively on real finite-size detector data

Abstract

Photoacoustic tomography (PAT) is an emerging imaging modality that combines the complementary strengths of optical contrast and ultrasonic resolution. A central task is image reconstruction, where measured acoustic signals are used to recover the initial pressure distribution. For ideal point-like or line-like detectors, several efficient and fast reconstruction algorithms exist, including Fourier methods, filtered backprojection, and time reversal. However, when applied to data acquired with finite-size detectors, these methods yield systematically blurred images. Although sharper images can be obtained by compensating for finite-detector effects, supervised learning approaches typically require ground-truth images that may not be available in practice. We propose a self-supervised reconstruction method based on Noisier2Inverse that addresses finite-size detector effects without requiring ground-truth data. Our approach operates directly on noisy measurements and learns to recover high-quality PAT images in a ground-truth-free manner. Its key components are: (i) PAT-specific modeling that recasts the problem as angular deblurring; (ii) a Noisier2Inverse formulation in the polar domain that leverages the known angular point-spread function; and (iii) a novel, statistically grounded early-stopping rule. In experiments, the proposed method consistently outperforms alternative approaches that do not use supervised data and achieves performance close to supervised benchmarks, while remaining practical for real acquisitions with finite-size detectors.