Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 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

Distribution-informed and wavelength-flexible data-driven photoacoustic oximetry (2403.14863v1)

Published 21 Mar 2024 in physics.med-ph, cs.CV, and cs.LG

Abstract: Significance: Photoacoustic imaging (PAI) promises to measure spatially-resolved blood oxygen saturation, but suffers from a lack of accurate and robust spectral unmixing methods to deliver on this promise. Accurate blood oxygenation estimation could have important clinical applications, from cancer detection to quantifying inflammation. Aim: This study addresses the inflexibility of existing data-driven methods for estimating blood oxygenation in PAI by introducing a recurrent neural network architecture. Approach: We created 25 simulated training dataset variations to assess neural network performance. We used a long short-term memory network to implement a wavelength-flexible network architecture and proposed the Jensen-Shannon divergence to predict the most suitable training dataset. Results: The network architecture can handle arbitrary input wavelengths and outperforms linear unmixing and the previously proposed learned spectral decolouring method. Small changes in the training data significantly affect the accuracy of our method, but we find that the Jensen-Shannon divergence correlates with the estimation error and is thus suitable for predicting the most appropriate training datasets for any given application. Conclusions: A flexible data-driven network architecture combined with the Jensen-Shannon Divergence to predict the best training data set provides a promising direction that might enable robust data-driven photoacoustic oximetry for clinical use cases.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (65)
  1. A. Fawzy, T. D. Wu, K. Wang, et al., “Racial and ethnic discrepancy in pulse oximetry and delayed identification of treatment eligibility among patients with covid-19,” JAMA internal medicine 182(7), 730–738 (2022).
  2. P. Beard, “Biomedical photoacoustic imaging,” Interface focus 1(4), 602–631 (2011).
  3. M. Li, Y. Tang, and J. Yao, “Photoacoustic tomography of blood oxygenation: a mini review,” Photoacoustics 10, 65–73 (2018).
  4. F. Knieling, C. Neufert, A. Hartmann, et al., “Multispectral optoacoustic tomography for assessment of crohn’s disease activity,” New England Journal of Medicine 376(13), 1292–1294 (2017).
  5. A. Karlas, N.-A. Fasoula, K. Paul-Yuan, et al., “Cardiovascular optoacoustics: From mice to men–a review,” Photoacoustics 14, 19–30 (2019).
  6. M. W. Dewhirst, Y. Cao, and B. Moeller, “Cycling hypoxia and free radicals regulate angiogenesis and radiotherapy response,” Nature Reviews Cancer 8(6), 425–437 (2008).
  7. D. Hanahan, “Hallmarks of cancer: new dimensions,” Cancer discovery 12(1), 31–46 (2022).
  8. J. Laufer, D. Delpy, C. Elwell, et al., “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 (2006).
  9. C. Bench and B. Cox, “Quantitative photoacoustic estimates of intervascular blood oxygenation differences using linear unmixing,” in Journal of Physics: Conference Series, 1761(1), 012001, IOP Publishing (2021).
  10. S. Tzoumas and V. Ntziachristos, “Spectral unmixing techniques for optoacoustic imaging of tissue pathophysiology,” Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 375(2107), 20170262 (2017).
  11. R. Hochuli, L. An, P. C. Beard, et al., “Estimating blood oxygenation from photoacoustic images: can a simple linear spectroscopic inversion ever work?,” Journal of biomedical optics 24(12), 121914–121914 (2019).
  12. B. Cox, J. G. Laufer, S. R. Arridge, et al., “Quantitative spectroscopic photoacoustic imaging: a review,” Journal of biomedical optics 17(6), 061202–061202 (2012).
  13. M. K. A. Singh, M. Jaeger, M. Frenz, et al., “In vivo demonstration of reflection artifact reduction in photoacoustic imaging using synthetic aperture photoacoustic-guided focused ultrasound (pafusion),” Biomedical optics express 7(8), 2955–2972 (2016).
  14. J. Jose, R. G. Willemink, W. Steenbergen, et al., “Speed-of-sound compensated photoacoustic tomography for accurate imaging,” Medical physics 39(12), 7262–7271 (2012).
  15. Y. Mantri and J. V. Jokerst, “Impact of skin tone on photoacoustic oximetry and tools to minimize bias,” Biomedical Optics Express 13(2), 875–887 (2022).
  16. T. R. Else, L. Hacker, J. Gröhl, et al., “The effects of skin tone on photoacoustic imaging and oximetry,” bioRxiv , 2023–08 (2023).
  17. G. P. Luke, K. Hoffer-Hawlik, A. C. Van Namen, et al., “O-net: a convolutional neural network for quantitative photoacoustic image segmentation and oximetry,” arXiv preprint arXiv:1911.01935 (2019).
  18. S. Agrawal, P. Gaddale, S. P. K. Karri, et al., “Learning optical scattering through symmetrical orthogonality enforced independent components for unmixing deep tissue photoacoustic signals,” IEEE Sensors Letters 5(5), 1–4 (2021).
  19. V. Grasso, R. Willumeit-Römer, and J. Jose, “Superpixel spectral unmixing framework for the volumetric assessment of tissue chromophores: A photoacoustic data-driven approach,” Photoacoustics 26, 100367 (2022).
  20. J. Gröhl, T. Kirchner, T. J. Adler, et al., “Learned spectral decoloring enables photoacoustic oximetry,” Scientific reports 11(1), 6565 (2021).
  21. J. Gröhl, M. Schellenberg, K. Dreher, et al., “Deep learning for biomedical photoacoustic imaging: A review,” Photoacoustics 22, 100241 (2021).
  22. H. Assi, R. Cao, M. Castelino, et al., “A review of a strategic roadmapping exercise to advance clinical translation of photoacoustic imaging: From current barriers to future adoption,” Photoacoustics , 100539 (2023).
  23. V. Sandfort, K. Yan, P. J. Pickhardt, et al., “Data augmentation using generative adversarial networks (cyclegan) to improve generalizability in ct segmentation tasks,” Scientific reports 9(1), 16884 (2019).
  24. L. Maier-Hein, M. Eisenmann, D. Sarikaya, et al., “Surgical data science–from concepts toward clinical translation,” Medical image analysis 76, 102306 (2022).
  25. L. Hacker, H. Wabnitz, A. Pifferi, et al., “Criteria for the design of tissue-mimicking phantoms for the standardization of biophotonic instrumentation,” Nature Biomedical Engineering 6(5), 541–558 (2022).
  26. J. Gröhl, T. R. Else, L. Hacker, et al., “Moving beyond simulation: data-driven quantitative photoacoustic imaging using tissue-mimicking phantoms,” arXiv preprint arXiv:2306.06748 (2023).
  27. A. K. Susmelj, B. Lafci, F. Ozdemir, et al., “Signal domain adaptation network for limited-view optoacoustic tomography,” Medical Image Analysis (2023).
  28. K. K. Dreher, L. Ayala, M. Schellenberg, et al., “Unsupervised domain transfer with conditional invertible neural networks,” arXiv preprint arXiv:2303.10191 (2023).
  29. C. Bench, A. Hauptmann, and B. Cox, “Toward accurate quantitative photoacoustic imaging: learning vascular blood oxygen saturation in three dimensions,” Journal of Biomedical Optics 25(8), 085003–085003 (2020).
  30. B. T. Cox, S. R. Arridge, and P. C. Beard, “Estimating chromophore distributions from multiwavelength photoacoustic images,” JOSA A 26(2), 443–455 (2009).
  31. S. Tzoumas, A. Nunes, I. Olefir, et al., “Eigenspectra optoacoustic tomography achieves quantitative blood oxygenation imaging deep in tissues,” Nature communications 7(1), 12121 (2016).
  32. T. Kirchner and M. Frenz, “Multiple illumination learned spectral decoloring for quantitative optoacoustic oximetry imaging,” Journal of biomedical optics 26(8), 085001–085001 (2021).
  33. S. Manohar, “” in gello” imaging,” (2023).
  34. J. Gröhl, K. K. Dreher, M. Schellenberg, et al., “Simpa: an open-source toolkit for simulation and image processing for photonics and acoustics,” Journal of biomedical optics 27(8), 083010–083010 (2022).
  35. Q. Fang and D. A. Boas, “Monte carlo simulation of photon migration in 3d turbid media accelerated by graphics processing units,” Optics express 17(22), 20178–20190 (2009).
  36. B. E. Treeby and B. T. Cox, “k-wave: Matlab toolbox for the simulation and reconstruction of photoacoustic wave fields,” Journal of biomedical optics 15(2), 021314–021314 (2010).
  37. C. Cai, K. Deng, C. Ma, et al., “End-to-end deep neural network for optical inversion in quantitative photoacoustic imaging,” Optics letters 43(12), 2752–2755 (2018).
  38. T. Chen, T. Lu, S. Song, et al., “A deep learning method based on u-net for quantitative photoacoustic imaging,” in Photons Plus Ultrasound: Imaging and Sensing 2020, 11240, 216–223, SPIE (2020).
  39. K. Hoffer-Hawlik and G. P. Luke, “Abso2luteu-net: tissue oxygenation calculation using photoacoustic imaging and convolutional neural networks,” Thesis (Bachelor’s) (2019).
  40. I. Olefir, S. Tzoumas, C. Restivo, et al., “Deep learning-based spectral unmixing for optoacoustic imaging of tissue oxygen saturation,” IEEE transactions on medical imaging 39(11), 3643–3654 (2020).
  41. D. G. Lyons, A. Parpaleix, M. Roche, et al., “Mapping oxygen concentration in the awake mouse brain,” Elife 5, e12024 (2016).
  42. M. Gehrung, S. E. Bohndiek, and J. Brunker, “Development of a blood oxygenation phantom for photoacoustic tomography combined with online po2 detection and flow spectrometry,” Journal of biomedical optics 24(12), 121908 (2019).
  43. A. Halevy, P. Norvig, and F. Pereira, “The unreasonable effectiveness of data,” IEEE intelligent systems 24(2), 8–12 (2009).
  44. F. Chollet et al., “Keras.” https://keras.io (2015).
  45. J. Joseph, M. R. Tomaszewski, I. Quiros-Gonzalez, et al., “Evaluation of precision in optoacoustic tomography for preclinical imaging in living subjects,” Journal of Nuclear Medicine 58(5), 807–814 (2017).
  46. I. Wolf, M. Vetter, I. Wegner, et al., “The medical imaging interaction toolkit,” Medical image analysis 9(6), 594–604 (2005).
  47. A. M. Loeven, C. N. Receno, C. M. Cunningham, et al., “Arterial blood sampling in male cd-1 and c57bl/6j mice with 1% isoflurane is similar to awake mice,” Journal of Applied Physiology 125(6), 1749–1759 (2018).
  48. H. Abramczyk, J. M. Surmacki, M. Kopeć, et al., “Hemoglobin and cytochrome c. reinterpreting the origins of oxygenation and oxidation in erythrocytes and in vivo cancer lung cells,” Scientific Reports 13(1), 14731 (2023).
  49. E. Dervieux, Q. Bodinier, W. Uhring, et al., “Measuring hemoglobin spectra: searching for carbamino-hemoglobin,” Journal of Biomedical Optics 25(10), 105001–105001 (2020).
  50. M. Taylor-Williams, G. Spicer, G. Bale, et al., “Noninvasive hemoglobin sensing and imaging: optical tools for disease diagnosis,” Journal of Biomedical Optics 27(8), 080901 (2022).
  51. P. R. Huber, M. E. Leimbach, W. L. Lewis, et al., “Co2 angiography,” Catheterization and cardiovascular interventions 55(3), 398–403 (2002).
  52. A. J. Williams, “Assessing and interpreting arterial blood gases and acid-base balance,” Bmj 317(7167), 1213–1216 (1998).
  53. J. Lin, “Divergence measures based on the shannon entropy,” IEEE Transactions on Information theory 37(1), 145–151 (1991).
  54. S. Kullback and R. A. Leibler, “On information and sufficiency,” The annals of mathematical statistics 22(1), 79–86 (1951).
  55. P. Virtanen, R. Gommers, T. E. Oliphant, et al., “SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python,” Nature Methods 17, 261–272 (2020).
  56. R. M. Schmidt, “Recurrent neural networks (rnns): A gentle introduction and overview,” arXiv preprint arXiv:1912.05911 (2019).
  57. L. McInnes, J. Healy, and J. Melville, “Umap: Uniform manifold approximation and projection for dimension reduction,” arXiv preprint arXiv:1802.03426 (2018).
  58. J. W. Severinghaus, “Simple, accurate equations for human blood o2 dissociation computations,” Journal of Applied Physiology 46(3), 599–602 (1979).
  59. M. N. Fadhel, E. Hysi, H. Assi, et al., “Fluence-matching technique using photoacoustic radiofrequency spectra for improving estimates of oxygen saturation,” Photoacoustics 19, 100182 (2020).
  60. T. Rix, K. K. Dreher, J.-H. Nölke, et al., “Efficient photoacoustic image synthesis with deep learning,” Sensors 23(16), 7085 (2023).
  61. R. Su, S. A. Ermiliov, A. V. Liopo, et al., “Optoacoustic 3d visualization of changes in physiological properties of mouse tissues from live to postmortem,” in Photons Plus Ultrasound: Imaging and Sensing 2012, 8223, 105–111, SPIE (2012).
  62. R. K. Saha and M. C. Kolios, “A simulation study on photoacoustic signals from red blood cells,” The Journal of the Acoustical Society of America 129(5), 2935–2943 (2011).
  63. A. T. Schäfer, “Colour measurements of pallor mortis,” International journal of legal medicine 113, 81–83 (2000).
  64. T. Else, J. Gröhl, L. Hacker, et al., “Patato: a python photoacoustic tomography analysis toolkit,” in Photons Plus Ultrasound: Imaging and Sensing 2023, PC123790T, SPIE (2023).
  65. J. Li, C. Wang, T. Chen, et al., “Deep learning-based quantitative optoacoustic tomography of deep tissues in the absence of labeled experimental data,” Optica 9(1), 32–41 (2022).
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
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets