Model based learning for accelerated, limited-view 3D photoacoustic tomography

TL;DR

This paper introduces a deep neural network tailored for high-resolution 3D photoacoustic image reconstruction from limited-view data, leveraging an iterative scheme and learned priors to improve image quality and reduce artifacts.

Contribution

The authors develop a novel deep learning approach that incorporates gradient information and learned priors, specifically designed for limited-view 3D photoacoustic tomography.

Findings

The method achieves high-quality 3D reconstructions from limited measurements.

It effectively reduces view artifacts compared to traditional methods.

The network generalizes well to in-vivo photoacoustic data.

Abstract

Recent advances in deep learning for tomographic reconstructions have shown great potential to create accurate and high quality images with a considerable speed-up. In this work we present a deep neural network that is specifically designed to provide high resolution 3D images from restricted photoacoustic measurements. The network is designed to represent an iterative scheme and incorporates gradient information of the data fit to compensate for limited view artefacts. Due to the high complexity of the photoacoustic forward operator, we separate training and computation of the gradient information. A suitable prior for the desired image structures is learned as part of the training. The resulting network is trained and tested on a set of segmented vessels from lung CT scans and then applied to in-vivo photoacoustic measurement data.