Approximate k-space models and Deep Learning for fast photoacoustic reconstruction

Andreas Hauptmann; Ben Cox; Felix Lucka; Nam Huynh; Marta Betcke; Paul Beard; Simon Arridge

doi:10.1007/978-3-030-00129-2_12

Approximate k-space models and Deep Learning for fast photoacoustic reconstruction

Computer Vision and Pattern Recognition 2020-09-07 v1 Machine Learning Sound Audio and Speech Processing Optimization and Control

Authors: Andreas Hauptmann , Ben Cox , Felix Lucka , Nam Huynh , Marta Betcke , Paul Beard , Simon Arridge

View on arXiv ↗ PDF ↗ DOI ↗

Abstract

We present a framework for accelerated iterative reconstructions using a fast and approximate forward model that is based on k-space methods for photoacoustic tomography. The approximate model introduces aliasing artefacts in the gradient information for the iterative reconstruction, but these artefacts are highly structured and we can train a CNN that can use the approximate information to perform an iterative reconstruction. We show feasibility of the method for human in-vivo measurements in a limited-view geometry. The proposed method is able to produce superior results to total variation reconstructions with a speed-up of 32 times.

Keywords

image reconstruction 3d reconstruction medical image analysis

Cite

@article{arxiv.1807.03191,
  title  = {Approximate k-space models and Deep Learning for fast photoacoustic reconstruction},
  author = {Andreas Hauptmann and Ben Cox and Felix Lucka and Nam Huynh and Marta Betcke and Paul Beard and Simon Arridge},
  journal= {arXiv preprint arXiv:1807.03191},
  year   = {2020}
}

Approximate k-space models and Deep Learning for fast photoacoustic reconstruction

Abstract

Keywords

Cite

Related papers