Advertisement

Robust Non-negative Tensor Factorization, Diffeomorphic Motion Correction, and Functional Statistics to Understand Fixation in Fluorescence Microscopy

  • Neel DeyEmail author
  • Jeffrey Messinger
  • R. Theodore Smith
  • Christine A. Curcio
  • Guido Gerig
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11764)

Abstract

Fixation is essential for preserving cellular morphology in biomedical research. However, it may also affect spectra captured in multispectral fluorescence microscopy, impacting molecular interpretations. To investigate fixation effects on tissue, multispectral fluorescence microscopy images of pairs of samples with and without fixation are captured. Each pixel might exhibit overlapping spectra, creating a blind source separation problem approachable with linear unmixing. With multiple excitation wavelengths, unmixing is intuitively extended to tensor factorizations. Yet these approaches are limited by nonlinear effects like attenuation. Further, light exposure during image acquisition introduces subtle Brownian motion between image channels of non-fixed tissue. Finally, hypothesis testing for spectral differences due to fixation is non-trivial as retrieved spectra are paired sequential samples. To these ends, we present three contributions, (1) a novel robust non-negative tensor factorization using the \(\beta \)-divergence and \(L_{2,1}\)-norm, which decomposes the data into a low-rank multilinear and group-sparse non-multilinear tensor without making any explicit nonlinear modeling choices or assumptions on noise statistics; (2) a diffeomorphic atlas-based strategy for motion correction; (3) a non-parametric hypothesis testing framework for paired sequential data using functional principal component analysis. PyTorch code for robust non-negative tensor factorization is available at https://github.com/neel-dey/robustNTF.

Notes

Acknowledgments

Author support and HPC provided by NIH R01EY027948 and NSF MRI-1229185, respectively. Validation data provided by Hayato Ikoma.

Supplementary material

486666_1_En_73_MOESM2_ESM.pdf (2.1 mb)
Supplementary material 2 (pdf 2103 KB)

References

  1. 1.
    Avants, B.B., Epstein, C.L., Grossman, M., Gee, J.C.: Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain. Med. Image Anal. 12(1), 26–41 (2008)CrossRefGoogle Scholar
  2. 2.
    Dey, N., et al.: Tensor decomposition of hyperspectral images to study autofluorescence in age-related macular degeneration. Med. Image Anal. 56, 96–109 (2019)CrossRefGoogle Scholar
  3. 3.
    Févotte, C., Dobigeon, N.: Nonlinear hyperspectral unmixing with robust nonnegative matrix factorization. IEEE Trans. Image Process. 24(12), 4810–4819 (2015)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Hong, D., Kolda, T.G., Duersch, J.A.: Generalized canonical polyadic tensor decomposition. arXiv preprint arXiv:1808.07452 (2018)
  5. 5.
    Huang, Z., et al.: Effect of formalin fixation on the near-infrared raman spectroscopy of normal and cancerous human bronchial tissues. Int. J. Oncol. 23(3), 649–655 (2003)Google Scholar
  6. 6.
    Ikoma, H., Heshmat, B., Wetzstein, G., Raskar, R.: Attenuation-corrected fluorescence spectra unmixing for spectroscopy and microscopy. Opt. Express 22(16), 19469–19483 (2014)CrossRefGoogle Scholar
  7. 7.
    Joshi, S., Davis, B., Jomier, M., Gerig, G.: Unbiased diffeomorphic atlas construction for computational anatomy. NeuroImage 23, S151–S160 (2004)CrossRefGoogle Scholar
  8. 8.
    Neher, R.A., Mitkovski, M., Kirchhoff, F., Neher, E., Theis, F.J., Zeug, A.: Blind source separation techniques for the decomposition of multiply labeled fluorescence images. Biophys. J. 96(9), 3791–3800 (2009)CrossRefGoogle Scholar
  9. 9.
    Pomann, G.M., Staicu, A.M., Ghosh, S.: A two-sample distribution-free test for functional data with application to a diffusion tensor imaging study of multiple sclerosis. J. Roy. Stat. Soc.: Ser. C (Appl. Stat.) 65(3), 395–414 (2016)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Ramsay, J.O.: Functional Data Analysis. Springer, New York (2005).  https://doi.org/10.1007/b98888CrossRefzbMATHGoogle Scholar
  11. 11.
    Smilde, A., Bro, R., Geladi, P.: Multi-way Analysis: Applications in the Chemical Sciences. Wiley, Hoboken (2005)Google Scholar
  12. 12.
    Waters, J.C.: Accuracy and precision in quantitative fluorescence microscopy. Rockefeller University Press (2009)Google Scholar
  13. 13.
    Zhou, P., Feng, J.: Outlier-robust tensor PCA. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2263–2271 (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Neel Dey
    • 1
    Email author
  • Jeffrey Messinger
    • 2
  • R. Theodore Smith
    • 3
  • Christine A. Curcio
    • 2
  • Guido Gerig
    • 1
  1. 1.Department of Computer Science and EngineeringNew York UniversityBrooklynUSA
  2. 2.Department of Ophthalmology and Visual SciencesUniversity of Alabama at BirminghamBirminghamUSA
  3. 3.Department of OphthalmologyIcahn School of Medicine at Mount SinaiNew YorkUSA

Personalised recommendations