B1864
Title: Supervised learning for unmixing biological data with sparse and low-rank Poisson regression
Authors: Ruogu Wang - University at Albany, SUNY (United States) [presenting]
Abstract: Multispectral biological fluorescence microscopy has enabled the identification of multiple targets in complex samples. The accuracy in the unmixing result degrades (i) as the number of fluorophores used in any experiment increases and (ii) as the signal-to-noise ratio in the recorded images decreases. Further, the availability of prior knowledge regarding the expected spatial distributions of fluorophores in images of labelled cells provides an opportunity to improve the accuracy of fluorophore identification and abundance. A regularized sparse and low-rank Poisson regression unmixing approach (SL-PRU) is proposed to deconvolve spectral images labelled with highly overlapping fluorophores which are recorded in low signal-to-noise regimes. First, SL-PRU implements multi-penalty terms when pursuing sparseness and spatial correlation of the resulting abundances in small neighbourhoods simultaneously. Second, SL-PRU makes use of Poisson regression for unmixing instead of least squares regression to better estimate photon abundance. Third, a method is proposed to tune the SL-PRU parameters involved in the unmixing procedure in the absence of knowledge of the ground truth abundance information in a recorded image. By validating simulated and real-world images, it is shown that the proposed method leads to improved accuracy in unmixing fluorophores with highly overlapping spectra.
