Back to Search
Start Over
CT reconstruction using diffusion posterior sampling conditioned on a nonlinear measurement model.
- Source :
-
Journal of medical imaging (Bellingham, Wash.) [J Med Imaging (Bellingham)] 2024 Jul; Vol. 11 (4), pp. 043504. Date of Electronic Publication: 2024 Aug 30. - Publication Year :
- 2024
-
Abstract
- Purpose: Recently, diffusion posterior sampling (DPS), where score-based diffusion priors are combined with likelihood models, has been used to produce high-quality computed tomography (CT) images given low-quality measurements. This technique permits one-time, unsupervised training of a CT prior, which can then be incorporated with an arbitrary data model. However, current methods rely on a linear model of X-ray CT physics to reconstruct. Although it is common to linearize the transmission tomography reconstruction problem, this is an approximation to the true and inherently nonlinear forward model. We propose a DPS method that integrates a general nonlinear measurement model.<br />Approach: We implement a traditional unconditional diffusion model by training a prior score function estimator and apply Bayes' rule to combine this prior with a measurement likelihood score function derived from the nonlinear physical model to arrive at a posterior score function that can be used to sample the reverse-time diffusion process. We develop computational enhancements for the approach and evaluate the reconstruction approach in several simulation studies.<br />Results: The proposed nonlinear DPS provides improved performance over traditional reconstruction methods and DPS with a linear model. Moreover, as compared with a conditionally trained deep learning approach, the nonlinear DPS approach shows a better ability to provide high-quality images for different acquisition protocols.<br />Conclusion: This plug-and-play method allows the incorporation of a diffusion-based prior with a general nonlinear CT measurement model. This permits the application of the approach to different systems, protocols, etc., without the need for any additional training.<br /> (© 2024 Society of Photo-Optical Instrumentation Engineers (SPIE).)
Details
- Language :
- English
- ISSN :
- 2329-4302
- Volume :
- 11
- Issue :
- 4
- Database :
- MEDLINE
- Journal :
- Journal of medical imaging (Bellingham, Wash.)
- Publication Type :
- Academic Journal
- Accession number :
- 39220597
- Full Text :
- https://doi.org/10.1117/1.JMI.11.4.043504