Learning end-to-end inversion of circular Radon transforms in the partial radial setup

TL;DR

This paper introduces a deep learning approach using a ResBlock U-Net to improve the inversion of circular Radon transforms in photoacoustic tomography, overcoming artifacts caused by traditional methods.

Contribution

The paper develops a novel deep learning algorithm that directly reconstructs the field from measured data, outperforming traditional SVD-based methods in noisy and limited data scenarios.

Findings

Deep learning method reduces artifacts in reconstructions.

Proposed algorithm outperforms traditional SVD-based methods.

Effective in noisy and limited view data conditions.

Abstract

We present a deep learning-based computational algorithm for inversion of circular Radon transforms in the partial radial setup, arising in photoacoustic tomography. We first demonstrate that the truncated singular value decomposition-based method, which is the only traditional algorithm available to solve this problem, leads to severe artifacts which renders the reconstructed field as unusable. With the objective of overcoming this computational bottleneck, we train a ResBlock based U-Net to recover the inferred field that directly operates on the measured data. Numerical results with augmented Shepp-Logan phantoms, in the presence of noisy full and limited view data, demonstrate the superiority of the proposed algorithm.