Autofluorescence Removal by Non-Negative Matrix Factorization

• Published in: IEEE transactions on image processing Vol. 20; no. 4; pp. 1085 - 1093
• Main Authors: Woolfe, Franco, Gerdes, Michael, Bello, Musodiq, Xiaodong Tao, Can, Ali
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.04.2011; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithm design and analysis; Algorithms; Applied sciences; Beads; Biological and medical sciences; Biomedical image processing; Computerized, statistical medical data processing and models in biomedicine; Dark current; Detection, estimation, filtering, equalization, prediction; Equations; Exact sciences and technology; Factorization; Fluorescence; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image processing; image reconstruction; Information, signal and communications theory; least squares methods; Mathematical model; Mathematical models; Medical management aid. Diagnosis aid; Medical sciences; Microscopy; Microscopy, Fluorescence - methods; Miscellaneous; molecular biomarker; multispectral imaging; Noise; Pattern Recognition, Automated - methods; Pixel; Principal components analysis; Sensitivity and Specificity; Signal and communications theory; Signal processing; Signal, noise; source separation; Spectra; State of the art; Studies; Subtraction Technique; Telecommunications and information theory; Performance evaluation; multispectral imaging; Parameter estimation; State of the art; Source separation; Image processing; Signal estimation; Spectral model; Image reconstruction; Least squares method; fluorescence; Imaging; molecular biomarker; Localization; Spectral method; Algorithm; Factorization; least squares methods; Statistical method; Non negative matrix; Microscopy; Signal processing; A priori estimation; Medical imagery; Biomedical image processing; Principal component analysis
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2010.2079810

This paper describes a new, physically interpretable, fully automatic algorithm for removal of tissue autofluorescence (AF) from fluorescence microscopy images, by non-negative matrix factorization. Measurement of signal intensities from the concentration of certain fluorescent reporter molecules at each location within a sample of biological tissue is confounded by fluorescence produced by the tissue itself (autofluorescence). Spectral mixing models use mixing coefficients to specify how much fluorescence from each source is present and unmixing algorithms separate the two fluorescent sources. Current spectral unmixing methods for AF removal often require a priori knowledge of mixing coefficients. Those which do not, such as principal component analysis, generate negative mixing coefficients that are not physically meaningful. Non-negative matrix factorization constrains mixing coefficients to be non-negative, and has been used for spectral unmixing, but not AF removal. This paper describes a novel non-negative matrix factorization algorithm which separates fluorescent images into true signal and AF components utilizing an estimate of the dark current. We also present a test-bed, based on fluorescent beads, to compare the performance of different AF removal algorithms. Our algorithm out-performed previous state of the art on validation images.