XTransCT: Ultra-Fast Volumetric CT Reconstruction using Two Orthogonal X-Ray Projections for Image-guided Radiation Therapy via a Transformer Network

TL;DR

XTransCT is a Transformer-based method that enables ultra-fast, real-time 3D CT reconstruction from only two X-ray projections, significantly reducing radiation dose and equipment complexity in image-guided radiation therapy.

Contribution

The paper introduces XTransCT, a novel Transformer architecture that reconstructs high-quality 3D CT images from just two X-ray images, outperforming existing methods in speed and accuracy.

Findings

Surpasses other methods in image quality and structural accuracy.

Achieves approximately 300% speed increase, reconstructing images in 44 ms.

Demonstrates strong generalizability across multiple datasets.

Abstract

Computed tomography (CT) scans offer a detailed, three-dimensional representation of patients' internal organs. However, conventional CT reconstruction techniques necessitate acquiring hundreds or thousands of x-ray projections through a complete rotational scan of the body, making navigation or positioning during surgery infeasible. In image-guided radiation therapy, a method that reconstructs ultra-sparse X-ray projections into CT images, we can exploit the substantially reduced radiation dose and minimize equipment burden for localization and navigation. In this study, we introduce a novel Transformer architecture, termed XTransCT, devised to facilitate real-time reconstruction of CT images from two-dimensional X-ray images. We assess our approach regarding image quality and structural reliability using a dataset of fifty patients, supplied by a hospital, as well as the larger public dataset LIDC-IDRI, which encompasses thousands of patients. Additionally, we validated our algorithm's generalizability on the LNDb dataset. Our findings indicate that our algorithm surpasses other methods in image quality, structural precision, and generalizability. Moreover, in comparison to previous 3D convolution-based approaches, we note a substantial speed increase of approximately 300 %, achieving 44 ms per 3D image reconstruction.