English

Bayesian Experimental Design for Computed Tomography with the Linearised Deep Image Prior

Computer Vision and Pattern Recognition 2022-07-13 v1 Machine Learning

Abstract

We investigate adaptive design based on a single sparse pilot scan for generating effective scanning strategies for computed tomography reconstruction. We propose a novel approach using the linearised deep image prior. It allows incorporating information from the pilot measurements into the angle selection criteria, while maintaining the tractability of a conjugate Gaussian-linear model. On a synthetically generated dataset with preferential directions, linearised DIP design allows reducing the number of scans by up to 30% relative to an equidistant angle baseline.

Keywords

Cite

@article{arxiv.2207.05714,
  title  = {Bayesian Experimental Design for Computed Tomography with the Linearised Deep Image Prior},
  author = {Riccardo Barbano and Johannes Leuschner and Javier Antorán and Bangti Jin and José Miguel Hernández-Lobato},
  journal= {arXiv preprint arXiv:2207.05714},
  year   = {2022}
}
R2 v1 2026-06-25T00:51:29.937Z