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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pulkkinen, Hanna, Poimala, Jenni, Kunyansky, Leonid, Gröhl, Janek, Hauptmann, Andreas
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908983135043584
author Pulkkinen, Hanna
Poimala, Jenni
Kunyansky, Leonid
Gröhl, Janek
Hauptmann, Andreas
author_facet Pulkkinen, Hanna
Poimala, Jenni
Kunyansky, Leonid
Gröhl, Janek
Hauptmann, Andreas
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_19176
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Deep Image Prior for photoacoustic tomography can mitigate limited-view artifacts
Pulkkinen, Hanna
Poimala, Jenni
Kunyansky, Leonid
Gröhl, Janek
Hauptmann, Andreas
Image and Video Processing
Machine Learning
Optimization and Control
65N21, 65M32, 65F22, 68T07, 92C55
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.
title Deep Image Prior for photoacoustic tomography can mitigate limited-view artifacts
topic Image and Video Processing
Machine Learning
Optimization and Control
65N21, 65M32, 65F22, 68T07, 92C55
url https://arxiv.org/abs/2604.19176