Published April 2024
| Published
Conference Paper
Score-based Diffusion Models for Photoacoustic Tomography Image Reconstruction
Abstract
Photoacoustic tomography (PAT) is a rapidly-evolving medical imaging modality that combines optical absorption contrast with ultrasound imaging depth. One challenge in PAT is image reconstruction with inadequate acoustic signals due to limited sensor coverage or due to the density of the transducer array. Such cases call for solving an ill-posed inverse reconstruction problem. In this work, we use score-based diffusion models to solve the inverse problem of reconstructing an image from limited PAT measurements. The proposed approach allows us to incorporate an expressive prior learned by a diffusion model on simulated vessel structures while still being robust to varying transducer sparsity conditions.
Copyright and License
© 2024 IEEE.
Acknowledgement
This work was supported in part by a Heritage Medical Research Fellowship award, National Institutes of Health grants U01 EB029823 (BRAIN Initiastive( and R35 CA220436 (Outstanding Investigator Award). L.W. has a financial interest in Microphotoacoustics, Inc., CalPACT, LLC, and Union Photoacoustic Technologies, Ltd., which however, did not support this work. B.T.F. is supported by the NSF GRFP. M.C. would like to thank Yousef Aborahama for fruitful discussions.
Additional details
- California Institute of Technology
- Heritage Medical Research Institute
- National Institutes of Health
- U01 EB029823
- National Institutes of Health
- R35 CA220436
- National Science Foundation
- NSF Graduate Research Fellowship
- Caltech groups
- Tianqiao and Chrissy Chen Institute for Neuroscience, Heritage Medical Research Institute