mlsanityData to 14 Oct 2026

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

arXiv 2604.19176 ↗First posted 21 Apr 2026eess.IV cs.LG math.OCcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 46 references that are in the map. First posted on arXiv 21 Apr 2026.

Builds on

18 of 46 references.

References · 18

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2017Deep Image Priorcited by 1,098
  4. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 433
  5. 2020Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methodscited by 56
  6. 2017Model based learning for accelerated, limited-view 3D photoacoustic tomographycited by 45
  7. 2018Regularization by architecture: A deep prior approach for inverse problemscited by 26
  8. 2020Deep Learning in Photoacoustic Tomography: Current approaches and future directionscited by 25
  9. 2020Deep learning for biomedical photoacoustic imaging: A reviewcited by 21
  10. 2017Deep Learning for Photoacoustic Tomography from Sparse Datacited by 17
  11. 2024A study of why we need to reassess full reference image quality assessment with medical imagescited by 17
  12. 2021An Educated Warm Start For Deep Image Prior-Based Micro CT Reconstructioncited by 16
6 more
  1. 2019Limited View and Sparse Photoacoustic Tomography for Neuroimaging with Deep Learningcited by 11
  2. 2023Moving beyond simulation: data-driven quantitative photoacoustic imaging using tissue-mimicking phantomscited by 10
  3. 2025Digital twins enable full-reference quality assessment of photoacoustic image reconstructionscited by 4
  4. 2023Model-based reconstructions for quantitative imaging in photoacoustic tomographycited by 2
  5. 2024Distribution-informed and wavelength-flexible data-driven photoacoustic oximetrycited by 1
  6. 2025Fast algorithms enabling optimization and deep learning for photoacoustic tomography in a circular detection geometrycited by 1

Built on by

Not cited yet.