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

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.

[1]  James O. Ramsay,et al.  Functional Data Analysis , 2005 .

[2]  Thomas Ach,et al.  Tensor decomposition of hyperspectral images to study autofluorescence in age-related macular degeneration , 2019, Medical Image Anal..

[3]  Guido Gerig,et al.  Unbiased diffeomorphic atlas construction for computational anatomy , 2004, NeuroImage.

[4]  Ana-Maria Staicu,et al.  A two‐sample distribution‐free test for functional data with application to a diffusion tensor imaging study of multiple sclerosis , 2016, Journal of the Royal Statistical Society. Series C, Applied statistics.

[5]  Jiashi Feng,et al.  Outlier-Robust Tensor PCA , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Rasmus Bro,et al.  Multi-way Analysis with Applications in the Chemical Sciences , 2004 .

[7]  G. Wetzstein,et al.  Attenuation-corrected fluorescence spectra unmixing for spectroscopy and microscopy. , 2014, Optics express.

[8]  S. Lam,et al.  Effect of formalin fixation on the near-infrared Raman spectroscopy of normal and cancerous human bronchial tissues. , 2003, International journal of oncology.

[9]  Nicolas Dobigeon,et al.  Nonlinear Hyperspectral Unmixing With Robust Nonnegative Matrix Factorization , 2014, IEEE Transactions on Image Processing.

[10]  Jennifer C. Waters,et al.  Accuracy and precision in quantitative fluorescence microscopy , 2009, The Journal of cell biology.

[11]  Fabian J Theis,et al.  Blind source separation techniques for the decomposition of multiply labeled fluorescence images. , 2009, Biophysical journal.

[12]  Brian B. Avants,et al.  Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain , 2008, Medical Image Anal..