X2CT-GAN: Reconstructing CT from Biplanar X-Rays with Generative Adversarial Networks

TL;DR

This paper introduces X2CT-GAN, a novel method that reconstructs 3D CT images from just two orthogonal X-ray images using a specialized GAN, reducing radiation and cost while maintaining high-quality results.

Contribution

The paper presents a new GAN-based approach with a unique generator and feature fusion method to reconstruct 3D CT from two X-rays, addressing a gap in previous research.

Findings

Effective reconstruction of 3D CT from two X-rays demonstrated

High-quality CT volumes achieved both visually and quantitatively

Potential for low-cost, low-radiation medical imaging applications

Abstract

Computed tomography (CT) can provide a 3D view of the patient's internal organs, facilitating disease diagnosis, but it incurs more radiation dose to a patient and a CT scanner is much more cost prohibitive than an X-ray machine too. Traditional CT reconstruction methods require hundreds of X-ray projections through a full rotational scan of the body, which cannot be performed on a typical X-ray machine. In this work, we propose to reconstruct CT from two orthogonal X-rays using the generative adversarial network (GAN) framework. A specially designed generator network is exploited to increase data dimension from 2D (X-rays) to 3D (CT), which is not addressed in previous research of GAN. A novel feature fusion method is proposed to combine information from two X-rays.The mean squared error (MSE) loss and adversarial loss are combined to train the generator, resulting in a high-quality CT volume both visually and quantitatively. Extensive experiments on a publicly available chest CT dataset demonstrate the effectiveness of the proposed method. It could be a nice enhancement of a low-cost X-ray machine to provide physicians a CT-like 3D volume in several niche applications.