Blind Decomposition of Spectral Imaging Microscopy: A Study on Artificial and Real Test Data

@inproceedings{Theis2009BlindDO,
  title={Blind Decomposition of Spectral Imaging Microscopy: A Study on Artificial and Real Test Data},
  author={Fabian J Theis and Richard A. Neher and Andr{\'e} Zeug},
  booktitle={ICA},
  year={2009}
}
Recently, we have proposed a blind source separation algorithm to separate dyes in multiply labeled fluorescence microscopy images. Applying the algorithm, we are able to successfully extract the dye distributions from the images. It thereby solves an often challenging problem since the recorded emission spectra of fluorescent dyes are environment and instrument specific. The separation algorithm is based on nonnegative matrix factorization in a Poisson noise model and works well on many… 
A new method to estimate abundances of multiple components using multi-spectral Fluorescence Lifetime Imaging Microscopy
TLDR
A new method to estimate the abundances of multiple components present in a mixture measured using m-FLIM data is presented, which provides a closed-form solution under the fully constrained linear unmixing model and assuming the number of components as well as their ideal lifetime decays are known.
Blind End-Member and Abundance Extraction for Multispectral Fluorescence Lifetime Imaging Microscopy Data
TLDR
This paper proposes a new blind end-member and abundance extraction (BEAE) method for multispectral fluorescence lifetime imaging microscopy (m-FLIM) data based on a linear mixture model with positivity and sum-to-one restrictions on the abundances and end-members to compensate for signature variability.
Particle filter for spectral unmixing
The paper addresses the problem of identification of fluorescent molecules, or fluorophores, in biological samples obtained from time-resolved fluorescence microscopy. The contribution of this work
Review of spectral imaging technology in biomedical engineering: achievements and challenges
TLDR
This review introduces the basics of spectral imaging, imaging methods, current equipment, and recent advances in biomedical applications and highlights the benefits and development trends of biomedical spectral imaging.
Which Elements to Build Co-localization Workflows? From Metrology to Analysis.
TLDR
This chapter aims at deconstructing existing generic co-localization workflows, extracting elementary tools that may be reused and recombined to generate new workflows and providing the audience with the elementary bricks and methods to build their really own co- localization workflow.

References

SHOWING 1-6 OF 6 REFERENCES
Blind source separation techniques for the decomposition of multiply labeled fluorescence images.
The fundamental limitation of frequency domain blind source separation for convolutive mixtures of speech
TLDR
It is shown that there is an optimum frame size that is determined by the trade-off between maintaining the number of samples in each frequency bin to estimate statistics and covering the whole reverberation, and that it is not good to be constrained by the condition T>P.
Analysis of fMRI data by blind separation into independent spatial components
TLDR
This work decomposed eight fMRI data sets from 4 normal subjects performing Stroop color‐naming, the Brown and Peterson word/number task, and control tasks into spatially independent components, and found the ICA algorithm was superior to principal component analysis (PCA) in determining the spatial and temporal extent of task‐related activation.
Learning the parts of objects by non-negative matrix factorization
TLDR
An algorithm for non-negative matrix factorization is demonstrated that is able to learn parts of faces and semantic features of text and is in contrast to other methods that learn holistic, not parts-based, representations.
Algorithms for Non-negative Matrix Factorization
TLDR
Two different multiplicative algorithms for non-negative matrix factorization are analyzed and one algorithm can be shown to minimize the conventional least squares error while the other minimizes the generalized Kullback-Leibler divergence.
EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis