Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
153 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Diffusion assisted image reconstruction in optoacoustic tomography (2404.10239v1)

Published 16 Apr 2024 in eess.IV

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (60)
  1. Solving inverse problems with score-based generative priors learned from noisy data. arXiv. arXiv:2305.01166 [cs, eess].
  2. ARIA (2006). Automated retinal image analysis.
  3. On the adjoint operator in photoacoustic tomography. Inverse Problems, 32(11):115012.
  4. Deep neural network-based sinogram super-resolution and bandwidth enhancement for limited-data photoacoustic tomography. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 67(12):2660–2673.
  5. Acoustic wave field reconstruction from compressed measurements with application in photoacoustic tomography. IEEE Transactions on Computational Imaging, 3(4):710–721.
  6. Temporal back-projection algorithms for photoacoustic tomography with integrating line detectors. Inverse Problems, 23(6):S65–S80.
  7. Elements of Information Theory 2nd Edition. Wiley-Interscience, 2 edition.
  8. Spirit-diffusion: Self-consistency driven diffusion model for accelerated mri. arXiv. arXiv:2304.05060 [cs].
  9. Diffusion models beat gans on image synthesis. arXiv. arXiv:2105.05233 [cs, stat].
  10. Efficient non-negative constrained model-based inversion in optoacoustic tomography. Physics in Medicine and Biology, 60(17):6733–6750.
  11. DRIVE (2020). Digital retinal images for vessel extraction.
  12. Score-based diffusion models as principled priors for inverse imaging. arXiv. arXiv:2304.11751 [cs].
  13. Solving bayesian inverse problems via variational autoencoders. In Proceedings of the 2nd Mathematical and Scientific Machine Learning Conference, page 386–425. PMLR.
  14. Combining band-frequency separation and deep neural networks for optoacoustic imaging. Optics and Lasers in Engineering, 163:107471.
  15. Fully dense unet for 2d sparse photoacoustic tomography artifact removal. IEEE Journal of Biomedical and Health Informatics, 24:568–576.
  16. Fully dense unet for 2-d sparse photoacoustic tomography artifact removal. IEEE Journal of Biomedical and Health Informatics, 24(2):568–576.
  17. A sparsification and reconstruction strategy for compressed sensing photoacoustic tomography. The Journal of the Acoustical Society of America, 143(6):3838.
  18. RAVIR: A dataset and methodology for the semantic segmentation and quantitative analysis of retinal arteries and veins in infrared reflectance imaging. IEEE Journal of Biomedical and Health Informatics.
  19. Deep learning in photoacoustic tomography: current approaches and future directions. Journal of Biomedical Optics, 25(11):112903.
  20. Model-based learning for accelerated, limited-view 3-d photoacoustic tomography. IEEE Transactions on Medical Imaging, 37(6):1382–1393.
  21. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), page 770–778.
  22. On the robustness of model-based algorithms for photoacoustic tomography: Comparison between time and frequency domains. Review of Scientific Instruments, 92(11):114901.
  23. Denoising diffusion probabilistic models. In Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS’20, page 6840–6851, Red Hook, NY, USA. Curran Associates Inc.
  24. Cascaded diffusion models for high fidelity image generation. The Journal of Machine Learning Research, 23:2249–2281.
  25. Image reconstruction for photoacoustic scanning of tissue structures. Applied Optics, 39(31):5872–5883.
  26. Full-wave iterative image reconstruction in photoacoustic tomography with acoustically inhomogeneous media. IEEE Transactions on Medical Imaging, 32(6):1097–1110.
  27. Dielectric antenna effects in integrating line piezoelectric sensors for optoacoustic imaging. Measurement Science and Technology, 31(12):125103.
  28. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
  29. Auto-Encoding Variational Bayes. In 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings.
  30. Photoacoustic ultrasound (paus)—reconstruction tomography. Medical Physics, 22(10):1605–1609.
  31. Quantitative spatially resolved measurement of tissue chromophore concentrations using photoacoustic spectroscopy: application to the measurement of blood oxygenation and haemoglobin concentration. Physics in Medicine & Biology, 52(1):141.
  32. Deep learning. Nature, 521(7553):436–444.
  33. Optoacoustic imaging and tomography: reconstruction approaches and outstanding challenges in image performance and quantification. Sensors, 13:7345–7384.
  34. Improved denoising diffusion probabilistic models. In Proceedings of the 38th International Conference on Machine Learning, page 8162–8171. PMLR.
  35. Piezoelectric line detector array for photoacoustic tomography. Photoacoustics, 8:28–36.
  36. Modeling photoacoustic imaging with a scanning focused detector using monte carlo simulation of energy deposition. Journal of biomedical optics, 23(12).
  37. The application of compressed sensing for photo-acoustic tomography. IEEE Transactions on Medical Imaging, 28(4):585–594.
  38. Study and Development of a System for 2-D Ultrasonic Tomography. Elektron, 7(2):40–47.
  39. RITE (2013). Retinal images vessel tree extraction.
  40. High-resolution image synthesis with latent diffusion models. arXiv:2112.10752. arXiv:2112.10752 [cs].
  41. U-net: Convolutional networks for biomedical image segmentation. In Navab, N., Hornegger, J., Wells, W. M., and Frangi, A. F., editors, Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Lecture Notes in Computer Science, page 234–241, Cham. Springer International Publishing.
  42. Model-based optoacoustic inversion with arbitrary-shape detectors. Medical Physics, 38(7):4285–4295.
  43. Acoustic inversion in optoacoustic tomography: A review. Current Medical Imaging Reviews, 9:318–336.
  44. Fast semi-analytical model-based acoustic inversion for quantitative optoacoustic tomography. IEEE Transactions on Medical Imaging, 29(6):1275–1285.
  45. Modeling of errors due to uncertainties in ultrasound sensor locations in photoacoustic tomography. IEEE Transactions on Medical Imaging, 39(6):2140–2150.
  46. Utilizing variational autoencoders in the bayesian inverse problem of photoacoustic tomography. SIAM Journal on Imaging Sciences, 16(1):89–110.
  47. Model-based deep learning: Key approaches and design guidelines. In 2021 IEEE Data Science and Learning Workshop (DSLW), page 1–6.
  48. Deep unsupervised learning using nonequilibrium thermodynamics. In Proceedings of the 32nd International Conference on Machine Learning, page 2256–2265. PMLR.
  49. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502. arXiv:2010.02502 [cs].
  50. Solving inverse problems in medical imaging with score-based generative models. arXiv. arXiv:2111.08005 [cs, eess, stat].
  51. j-wave: An open-source differentiable wave simulator. SoftwareX, 22:101338.
  52. STARE (2000). Structured analysis of the retina.
  53. Impact of system factors on the performance of photoacoustic tomography scanners. Phys. Rev. Applied, 13:014001.
  54. Attention is all you need. In Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc.
  55. Invariant representations in deep learning for optoacoustic imaging. Rev. Sci. Instrum., 94(5):054904.
  56. Biomedical Optics: Principles and Imaging. Wiley-Interscience, Hoboken, N.J, 1 edition edition.
  57. Time-domain reconstruction for thermoacoustic tomography in a spherical geometry. IEEE Transactions on Medical Imaging, 21(7):814–822.
  58. Universal back-projection algorithm for photoacoustic computed tomography. Phys. Rev. E, 71:016706.
  59. Photoacoustic imaging in biomedicine. Rev. Sci. Instrum., 77:041101.
  60. Time-domain reconstruction algorithms and numerical simulations for thermoacoustic tomography in various geometries. IEEE Transactions on Biomedical Engineering, 50(9):1086–1099.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now