DiffuX2CT: Diffusion Learning to Reconstruct CT Images from Biplanar X-Rays

TL;DR

DiffuX2CT introduces a diffusion-based method for reconstructing 3D CT images from two orthogonal X-ray views, enabling structure-controllable, high-fidelity reconstructions without direct CT scans.

Contribution

It proposes a novel diffusion model with an implicit conditioning mechanism for 3D CT reconstruction from biplanar X-rays, and introduces LumbarV, a new real-world dataset for evaluation.

Findings

Effective reconstruction demonstrated on LumbarV and other datasets.

Structure-controllable CT reconstruction achieved.

High-quality, faithful textures in reconstructed CT images.

Abstract

Computed tomography (CT) is widely utilized in clinical settings because it delivers detailed 3D images of the human body. However, performing CT scans is not always feasible due to radiation exposure and limitations in certain surgical environments. As an alternative, reconstructing CT images from ultra-sparse X-rays offers a valuable solution and has gained significant interest in scientific research and medical applications. However, it presents great challenges as it is inherently an ill-posed problem, often compromised by artifacts resulting from overlapping structures in X-ray images. In this paper, we propose DiffuX2CT, which models CT reconstruction from orthogonal biplanar X-rays as a conditional diffusion process. DiffuX2CT is established with a 3D global coherence denoising model with a new, implicit conditioning mechanism. We realize the conditioning mechanism by a newly designed tri-plane decoupling generator and an implicit neural decoder. By doing so, DiffuX2CT achieves structure-controllable reconstruction, which enables 3D structural information to be recovered from 2D X-rays, therefore producing faithful textures in CT images. As an extra contribution, we collect a real-world lumbar CT dataset, called LumbarV, as a new benchmark to verify the clinical significance and performance of CT reconstruction from X-rays. Extensive experiments on this dataset and three more publicly available datasets demonstrate the effectiveness of our proposal.