Self-Supervised Angular Deblurring in Photoacoustic Reconstruction via Noisier2Inverse

2026-04-17

AI Summary

This work addresses the systematic blurring in photoacoustic tomography reconstructions caused by finite-sized detectors, a challenge exacerbated by the scarcity of ground-truth labels required by existing supervised methods. The authors formulate the problem as an angular deblurring task in the polar domain and propose a self-supervised reconstruction framework based on the Noisier2Noise paradigm, leveraging a known angular point spread function. Key contributions include a novel self-supervised model tailored for photoacoustic imaging, a polar-domain adaptation of the Noisier2Noise formulation, and a statistically motivated early-stopping strategy. Experimental results demonstrate that the proposed method significantly outperforms current unsupervised approaches without requiring ground-truth data and achieves performance approaching that of supervised benchmarks, making it well-suited for practical limited-aperture detection scenarios.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Unsupervised & Self-Supervised Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

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.

Problem

• Photoacoustic tomography
• finite-size detectors
• image deblurring
• self-supervised learning
• image reconstruction

Innovation

• self-supervised learning
• angular deblurring
• Noisier2Inverse
• photoacoustic tomography
• finite-size detector