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

TL;DR

This paper introduces a deep learning-enhanced iterative reconstruction framework for photoacoustic tomography that uses a fast approximate k-space model, significantly speeding up the process while maintaining high image quality.

Contribution

The authors develop a CNN-based method that leverages structured aliasing artifacts from an approximate k-space model to accelerate photoacoustic image reconstruction.

Findings

Achieves 32x faster reconstruction speed.

Produces superior images compared to total variation methods.

Validates the approach on in-vivo human measurements.

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.