X2CT-FLOW: Maximum a posteriori reconstruction using a progressive flow-based deep generative model for ultra sparse-view computed tomography in ultra low-dose protocols
This addresses the need to reduce radiation exposure for patients in medical imaging by improving reconstruction from sparse data, though it appears incremental as it builds on existing flow-based models.
The paper tackles the problem of reconstructing 3D chest CT images from very few 2D projections in ultra low-dose protocols, proposing X2CT-FLOW, a flow-based deep generative model for maximum a posteriori reconstruction, which achieved SSIM of 0.7675 and PSNR of 25.89 dB in standard-dose and SSIM of 0.7008 and PSNR of 23.58 dB in ultra low-dose settings.
Ultra sparse-view computed tomography (CT) algorithms can reduce radiation exposure of patients, but those algorithms lack an explicit cycle consistency loss minimization and an explicit log-likelihood maximization in testing. Here, we propose X2CT-FLOW for the maximum a posteriori (MAP) reconstruction of a three-dimensional (3D) chest CT image from a single or a few two-dimensional (2D) projection images using a progressive flow-based deep generative model, especially for ultra low-dose protocols. The MAP reconstruction can simultaneously optimize the cycle consistency loss and the log-likelihood. The proposed algorithm is built upon a newly developed progressive flow-based deep generative model, which is featured with exact log-likelihood estimation, efficient sampling, and progressive learning. We applied X2CT-FLOW to reconstruction of 3D chest CT images from biplanar projection images without noise contamination (assuming a standard-dose protocol) and with strong noise contamination (assuming an ultra low-dose protocol). With the standard-dose protocol, our images reconstructed from 2D projected images and 3D ground-truth CT images showed good agreement in terms of structural similarity (SSIM, 0.7675 on average), peak signal-to-noise ratio (PSNR, 25.89 dB on average), mean absolute error (MAE, 0.02364 on average), and normalized root mean square error (NRMSE, 0.05731 on average). Moreover, with the ultra low-dose protocol, our images reconstructed from 2D projected images and the 3D ground-truth CT images also showed good agreement in terms of SSIM (0.7008 on average), PSNR (23.58 dB on average), MAE (0.02991 on average), and NRMSE (0.07349 on average).