INRR3CT: CT Reconstruction from Few Planar X-Rays
with Application Towards Low-Resource Radiotherapy
MICCAI 2023 Deep Generative Models workshop (DGM4MICCAI)
- Yiran Sun Rice University
- Tucker Netherton MD Anderson Cancer Center
- Laurence Court MD Anderson Cancer Center
- Ashok Veeraraghavan Rice University
- Guha Balakrishnan Rice University
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.
INRR3CT
Qualitative Results
PSNR/SSIM/Dice Results on LIDC CTs
PSNR/SSIM/Dice Results on Thoracic CTs
Segmentation Results on Thoracic CTs
Quantitative Results
Example 3D Thoracic CT reconstruction results on two patients, with varying numbers of input views
Radiation Planning Visual Results
Treatment Plans on one synthetic 3D Thoracic CT from INRR3CT, with and without segmentation as guidance
Related links
INRR3CT was implemented on top of the NeRF and pixel-NeRF codebases.
Our follow up work, DIFR3CT: Latent Diffusion for Probabilistic 3D CT Reconstruction from Few Planar X-Rays, is here.
Citation
If you find the paper useful in your research, please cite the paper:
Acknowledgements
The website template was borrowed from Michaël Gharbi.