Deep Image Prior for photoacoustic tomography can mitigate limited-view artifacts

Hanna Pulkkinen; Jenni Poimala; Leonid Kunyansky; Janek Gröhl; Andreas Hauptmann

eess.IVApr 21, 2026

Deep Image Prior for photoacoustic tomography can mitigate limited-view artifacts

Authors: Hanna Pulkkinen, Jenni Poimala, Leonid Kunyansky, Janek Gröhl, Andreas Hauptmann

Organizations: 1Research Unit of Mathematical Sciences, University of Oulu, Finland · Department of Technical Physics, University of Eastern Finland, Finland · Department of Mathematics, University of Arizona, USA · 4ENI-G, a Joint Initiative of the University Medical Center Göttingen and the Max Planck Institute for Multidisciplinary Sciences, Germany · Department of Computer Science, University College London, U.K

Abstract

We study the deep image prior (DIP) framework applied to photoacoustic tomography (PAT) as an unsupervised reconstruction approach to mitigate limited-view artifacts and noise commonly encountered in experimental settings. Efficient implementation is achieved by employing recently published fast forward and adjoint algorithms for circular measurement geometries. Initialization via a fast inverse and total variation (TV) regularization are applied to further suppress noise and mitigate overfitting. For comparison, we compute a classical TV reconstruction. Our experiments comprise simulated PAT measurements under limited-view geometries and varying levels of added noise as well as experimental measurements together with using a digital twin for quality assessment. Our findings suggest that DIP framework provides an effective unsupervised strategy for robust PAT reconstruction even in the challenging case of a limited view geometry providing improvement in several quantitative measures over total variation reconstructions.

Explore similar work

Self-Supervised Angular Deblurring in Photoacoustic Reconstruction via Noisier2Inverse
Apr 17, 2026Markus Haltmeier, Nadja Gruber, Gyeongha HwangImage Reconstruction Self-Supervised Reconstruction Method
Matrix-Free Photoacoustic Image Reconstruction via Sensor-Token Self-Attention
Jul 28, 2026Mary John, Shibili Said, Imad Barhumi +2Image Reconstruction Sparse Recovery
Unsupervised Deep Image Prior for Sparse-View and Limited-Angle Electron Tomography
May 26, 2026Serge Brosset, Daniel del Pozo Bueno, Thomas David +3Tomography Unsupervised

Apr 17, 2026 · cs.CVJ/K move · Enter open · S save

Self-Supervised Angular Deblurring in Photoacoustic Reconstruction via Noisier2Inverse

Markus Haltmeier, Nadja Gruber, Gyeongha Hwang

Department of Mathematics, University of Innsbruck Technikerstrasse 13, 6020 Innsbruck, Austria · Department of Computer Science, University of Innsbruck Technikerstrasse 21a, 6020 Innsbruck, Austria · Department of Mathematics, Yeungnam University 280 Daehak-Ro, Gyeongsan, Gyeongbuk 38541, South Korea

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.

Image Reconstruction Self-Supervised Reconstruction Method Motion Blur

Open paper Ask about it PDF

Abstract

Explore similar work

Self-Supervised Angular Deblurring in Photoacoustic Reconstruction via Noisier2Inverse

Matrix-Free Photoacoustic Image Reconstruction via Sensor-Token Self-Attention

Unsupervised Deep Image Prior for Sparse-View and Limited-Angle Electron Tomography