Limited-Angle Tomography Reconstruction via Deep End-To-End Learning on Synthetic Data

TL;DR

This paper introduces a deep learning method trained on synthetic data to improve limited-angle tomography reconstruction, achieving high-quality results with as little as 30 to 40 degrees of angular coverage.

Contribution

The authors develop a novel end-to-end deep neural network trained on synthetic data specifically for limited-angle CT reconstruction, outperforming traditional methods.

Findings

Won first place in Helsinki Tomography Challenge 2022

Effective reconstruction with as little as 30° or 40° sinograms

Deep learning approach surpasses classical algorithms in limited-angle scenarios

Abstract

Computed tomography (CT) has become an essential part of modern science and medicine. A CT scanner consists of an X-ray source that is spun around an object of interest. On the opposite end of the X-ray source, a detector captures X-rays that are not absorbed by the object. The reconstruction of an image is a linear inverse problem, which is usually solved by filtered back projection. However, when the number of measurements is small, the reconstruction problem is ill-posed. This is for example the case when the X-ray source is not spun completely around the object, but rather irradiates the object only from a limited angle. To tackle this problem, we present a deep neural network that is trained on a large amount of carefully-crafted synthetic data and can perform limited-angle tomography reconstruction even for only 30{\deg} or 40{\deg} sinograms. With our approach we won the first place in the Helsinki Tomography Challenge 2022.