Diffusion assisted image reconstruction in optoacoustic tomography

• Published in: Optics and lasers in engineering Vol. 178; p. 108242
• Main Authors: González, Martín G., Vera, Matias, Dreszman, Alan, Rey Vega, Leonardo J.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01-07-2024
• Subjects: Deep learning; Diffusion model; Image enhancement; Photoacoustic; Tomography; Photoacoustic; Deep learning; Tomography; Diffusion model; Image enhancement
• ISSN: 0143-8166; 1873-0302
• DOI: 10.1016/j.optlaseng.2024.108242

In this paper we consider the problem of acoustic inversion in the context of the optoacoustic tomography image reconstruction problem. By leveraging the ability of the recently proposed diffusion models for image generative tasks among others, we devise an image reconstruction architecture based on a conditional diffusion process. The scheme makes use of an initial image reconstruction, which is preprocessed by an autoencoder to generate an adequate representation. This representation is used as conditional information in a generative diffusion process. Although the computational requirements for training and implementing the architecture are not low, several design choices discussed in the work were made to keep them manageable. Numerical results show that the conditional information allows to properly bias the parameters of the diffusion model to improve the quality of the initial reconstructed image, eliminating artifacts or even reconstructing finer details of the ground-truth image that are not recoverable by the initial image reconstruction method. We also tested the proposal under experimental conditions and the obtained results were in line with those corresponding to the numerical simulations. Improvements in image quality up to 17% in terms of peak signal-to-noise ratio were observed.
•We consider the use of a conditional diffusion model architecture (DAR) for image enhancement in optoacoustic tomography.•DAR can be used in real-time image reconstruction since it only needs 25 inference steps (< 1 sec.).•Numerical and experimental results show that DAR achieves improvements in image quality up to 17% in terms of PSNR.