CT Reconstruction from Few Planar X-rays with Application towards Low-resource Radiotherapy

TL;DR

This paper introduces a deep generative model that reconstructs 3D CT scans from fewer than five planar X-ray images, enabling effective radiotherapy planning in low-resource settings where traditional CT scanners are unavailable.

Contribution

It presents the first clinical evaluation of CT reconstruction from minimal X-ray views using a neural implicit model with anatomical guidance, improving radiotherapy planning accuracy.

Findings

Achieved <1% error in radiation dose calculation on reconstructed scans.

Outperformed recent sparse CT reconstruction methods on the LIDC dataset.

Enabled effective radiotherapy planning with fewer X-ray views.

Abstract

CT scans are the standard-of-care for many clinical ailments, and are needed for treatments like external beam radiotherapy. Unfortunately, CT scanners are rare in low and mid-resource settings due to their costs. Planar X-ray radiography units, in comparison, are far more prevalent, but can only provide limited 2D observations of the 3D anatomy. In this work, we propose a method to generate CT volumes from few (<5) planar X-ray observations using a prior data distribution, and perform the first evaluation of such a reconstruction algorithm for a clinical application: radiotherapy planning. We propose a deep generative model, building on advances in neural implicit representations to synthesize volumetric CT scans from few input planar X-ray images at different angles. To focus the generation task on clinically-relevant features, our model can also leverage anatomical guidance during training (via segmentation masks). We generated 2-field opposed, palliative radiotherapy plans on thoracic CTs reconstructed by our method, and found that isocenter radiation dose on reconstructed scans have <1% error with respect to the dose calculated on clinically acquired CTs using <=4 X-ray views. In addition, our method is better than recent sparse CT reconstruction baselines in terms of standard pixel and structure-level metrics (PSNR, SSIM, Dice score) on the public LIDC lung CT dataset. Code is available at: https://github.com/wanderinrain/Xray2CT.