Speeding up Photoacoustic Imaging using Diffusion Models
Abstract: Background: Photoacoustic Microscopy (PAM) integrates optical and acoustic imaging, offering enhanced penetration depth for detecting optical-absorbing components in tissues. Nonetheless, challenges arise in scanning large areas with high spatial resolution. With speed limitations imposed by laser pulse repetition rates, the potential role of computational methods is highlighted in accelerating PAM imaging. Purpose: We are proposing a novel and highly adaptable DiffPam algorithm that utilizes diffusion models for speeding up the photoacoustic imaging process. Method: We leveraged a diffusion model trained exclusively on natural images, comparing its performance with an in-domain trained U-Net model using a dataset focused on PAM images of mice brain microvasculature. Results: Our findings indicate that DiffPam achieves comparable performance to a dedicated U-Net model, without the need for a large dataset or training a deep learning model. The study also introduces the efficacy of shortened diffusion processes for reducing computing time without compromising accuracy. Conclusion: This study underscores the significance of DiffPam as a practical algorithm for reconstructing undersampled PAM images, particularly for researchers with limited AI expertise and computational resources.
- Photoacoustic microscopy and computed tomography: from bench to bedside. Annu Rev Biomed Eng, 16:155–185, May 2014.
- Paul Beard. Biomedical photoacoustic imaging. Interface focus, 1(4):602–631, 2011.
- Soon-Woo Cho et al. High-speed photoacoustic microscopy: A review dedicated on light sources. Photoacoustics, 24:100291, 2021a. ISSN 2213-5979. https://doi.org/10.1016/j.pacs.2021.100291.
- Huangxuan Zhao et al. Deep learning enables superior photoacoustic imaging at ultralow laser dosages. Advanced Science, 8(3):2003097, 2021. https://doi.org/10.1002/advs.202003097.
- Convolutional neural network for resolution enhancement and noise reduction in acoustic resolution photoacoustic microscopy. Biomed Opt Express, 11(12):6826–6839, November 2020.
- Anthony DiSpirito et al. Reconstructing undersampled photoacoustic microscopy images using deep learning. IEEE Trans Med Imaging, 40(2):562–570, February 2021.
- Tri Vu et al. Deep image prior for undersampling high-speed photoacoustic microscopy. Photoacoustics, 22:100266, 2021b. ISSN 2213-5979. https://doi.org/10.1016/j.pacs.2021.100266.
- Dmitry Ulyanov et al. Deep image prior. arXiv:1711.10925, 2017.
- Xin Li et al. Diffusion models for image restoration and enhancement – a comprehensive survey, 2023.
- Jascha Sohl-Dickstein et al. Deep unsupervised learning using nonequilibrium thermodynamics, 2015.
- Jonathan Ho et al. Denoising diffusion probabilistic models. arXiv preprint arxiv:2006.11239, 2020.
- Diffusion models beat gans on image synthesis, 2021.
- Jooyoung Choi et al. Ilvr: Conditioning method for denoising diffusion probabilistic models. arXiv preprint arXiv:2108.02938, 2021.
- Hyungjin Chung et al. Improving diffusion models for inverse problems using manifold constraints. 2022a.
- Hyungjin Chung et al. Diffusion posterior sampling for general noisy inverse problems. In The Eleventh International Conference on Learning Representations, 2023. URL https://openreview.net/forum?id=OnD9zGAGT0k.
- Hyungjin Chung et al. Come-closer-diffuse-faster: Accelerating conditional diffusion models for inverse problems through stochastic contraction, 2022b.
- Open ai guided diffusion, 2021. URL https://github.com/openai/guided-diffusion. Accessed: 2023-08-30.
- Jia Deng et al. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009.
- Anthony DiSpirito III. Duke pam dataset, 2020. URL https://doi.org/10.5281/zenodo.4042171.
- Assaf Shocher. Resizer: Only way to resize, 2018. URL https://github.com/assafshocher/resizer.
- Adam: A method for stochastic optimization, 2017.
- Image quality metrics: Psnr vs. ssim. In 2010 20th International Conference on Pattern Recognition, pages 2366–2369, 2010. 10.1109/ICPR.2010.579.
- Richard Zhang et al. The unreasonable effectiveness of deep features as a perceptual metric. In CVPR, 2018.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
