English

Diffusion-based Sinogram Interpolation for Limited Angle PET

Machine Learning 2025-11-13 v1

Abstract

Accurate PET imaging increasingly requires methods that support unconstrained detector layouts from walk-through designs to long-axial rings where gaps and open sides lead to severely undersampled sinograms. Instead of constraining the hardware to form complete cylinders, we propose treating the missing lines-of-responses as a learnable prior. Data-driven approaches, particularly generative models, offer a promising pathway to recover this missing information. In this work, we explore the use of conditional diffusion models to interpolate sparsely sampled sinograms, paving the way for novel, cost-efficient, and patient-friendly PET geometries in real clinical settings.

Keywords

Cite

@article{arxiv.2511.09383,
  title  = {Diffusion-based Sinogram Interpolation for Limited Angle PET},
  author = {Rüveyda Yilmaz and Julian Thull and Johannes Stegmaier and Volkmar Schulz},
  journal= {arXiv preprint arXiv:2511.09383},
  year   = {2025}
}
R2 v1 2026-07-01T07:34:02.619Z