Sinogram Enhancement with Generative Adversarial Networks using Shape Priors

TL;DR

This paper presents a novel approach to Limited Angle Tomography by employing a GAN with shape priors to infer missing measurements, reducing X-ray exposure while outperforming existing methods.

Contribution

It introduces a GAN-based method utilizing shape priors for completing missing tomography data, enhancing image quality and reducing radiation exposure.

Findings

Quantitative and qualitative improvements over state-of-the-art methods

Effective inference of multiple missing measurements

Potential to reduce X-ray exposure in tomography

Abstract

Compensating scarce measurements by inferring them from computational models is a way to address ill-posed inverse problems. We tackle Limited Angle Tomography by completing the set of acquisitions using a generative model and prior-knowledge about the scanned object. Using a Generative Adversarial Network as model and Computer-Assisted Design data as shape prior, we demonstrate a quantitative and qualitative advantage of our technique over other state-of-the-art methods. Inferring a substantial number of consecutive missing measurements, we offer an alternative to other image inpainting techniques that fall short of providing a satisfying answer to our research question: can X-Ray exposition be reduced by using generative models to infer lacking measurements?