Advertisement

Physiological Parameter Estimation from Multispectral Images Unleashed

  • Sebastian J. WirkertEmail author
  • Anant S. Vemuri
  • Hannes G. Kenngott
  • Sara Moccia
  • Michael Götz
  • Benjamin F. B. Mayer
  • Klaus H. Maier-Hein
  • Daniel S. Elson
  • Lena Maier-Hein
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10435)

Abstract

Multispectral imaging in laparoscopy can provide tissue reflectance measurements for each point in the image at multiple wavelengths of light. These reflectances encode information on important physiological parameters not visible to the naked eye. Fast decoding of the data during surgery, however, remains challenging. While model-based methods suffer from inaccurate base assumptions, a major bottleneck related to competing machine learning-based solutions is the lack of labelled training data. In this paper, we address this issue with the first transfer learning-based method to physiological parameter estimation from multispectral images. It relies on a highly generic tissue model that aims to capture the full range of optical tissue parameters that can potentially be observed in vivo. Adaptation of the model to a specific clinical application based on unlabelled in vivo data is achieved using a new concept of domain adaptation that explicitly addresses the high variance often introduced by conventional covariance-shift correction methods. According to comprehensive in silico and in vivo experiments our approach enables accurate parameter estimation for various tissue types without the need for incorporating specific prior knowledge on optical properties and could thus pave the way for many exciting applications in multispectral laparoscopy.

Notes

Acknowledgement

Funding for this work was provided by the European Research Council (ERC) starting grant COMBIOSCOPY (637960).

References

  1. 1.
    Claridge, E., Hidovic-Rowe, D.: Model based inversion for deriving maps of histological parameters characteristic of cancer from ex-vivo multispectral images of the colon. IEEE TMI 33, 822–835 (2013)Google Scholar
  2. 2.
    Clancy, N.T., et al.: Intraoperative measurement of bowel oxygen saturation using a multispectral imaging laparoscope. Biomed. Opt. Express 6(10), 4179–4190 (2015)CrossRefGoogle Scholar
  3. 3.
    Wirkert, S.J.: others: Robust near real-time estimation of physiological parameters from megapixel multispectral images with inverse Monte Carlo and random forest regression. IJCARS 11(6), 909–917 (2016)Google Scholar
  4. 4.
    Styles, I.B., et al.: Quantitative analysis of multi-spectral fundus images. Med. Image Anal. 10(4), 578–597 (2006)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Jacques, S.L.: Optical properties of biological tissues: a review. Phys. Med. Biol. 58(11), R37 (2013)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Alerstam, E., et al.: Next-generation acceleration and code optimization for light transport in turbid media using GPUs. Biomed. Opt. Express 1(2), 658–675 (2010)CrossRefGoogle Scholar
  7. 7.
    Huang, J., et al.: Correcting sample selection bias by unlabeled data. In: Advances in Neural Information Processing Systems, vol. 19 (2007)Google Scholar
  8. 8.
    Heimann, T., et al.: Real-time ultrasound transducer localization in fluoroscopy images by transfer learning from synthetic training data. Med. Image Anal. 18(8), 1320–1328 (2014)CrossRefGoogle Scholar
  9. 9.
    Goetz, M., et al.: DALSA: domain adaptation for supervised learning from sparsely annotated MR images. IEEE TMI 35(1), 184–196 (2016)Google Scholar
  10. 10.
    Rahimi, A., et al.: Random features for large-scale kernel machines. In: NIPS, vol. 3 (2007)Google Scholar
  11. 11.
    Reddi, S.J., et al.: Doubly robust covariate shift correction. In: Twenty-Ninth AAAI Conference on Artificial Intelligence (2015)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Sebastian J. Wirkert
    • 1
    Email author
  • Anant S. Vemuri
    • 1
  • Hannes G. Kenngott
    • 2
  • Sara Moccia
    • 1
    • 3
    • 4
  • Michael Götz
    • 5
  • Benjamin F. B. Mayer
    • 2
  • Klaus H. Maier-Hein
    • 5
  • Daniel S. Elson
    • 6
    • 7
  • Lena Maier-Hein
    • 1
  1. 1.Division of Computer Assisted Medical InterventionsDKFZHeidelbergGermany
  2. 2.Department for General, Visceral and Transplantation SurgeryHeidelberg University HospitalHeidelbergGermany
  3. 3.Department of Advanced RoboticsIstituto Italiano di TecnologiaGenoaItaly
  4. 4.Department of Electronics, Information and BioengineeringPolitecnico di MilanoMilanItaly
  5. 5.Division for Medical and Biological InformaticsDKFZHeidelbergGermany
  6. 6.Hamlyn Centre for Robotic SurgeryImperial College LondonLondonUK
  7. 7.Department of Surgery and CancerImperial College LondonLondonUK

Personalised recommendations