Fluorescence microscopy image noise reduction using a stochastically-connected random field model

Fluorescence microscopy is an essential part in a biologist's toolkit, allowing assaying of many parameters like subcellular localization of proteins, changes in cytoskeletal dynamics, protein-protein interactions, and the concentration of specific cellular ions. A fundamental challenge with using fluorescence microscopy is noise caused by the inherent characteristics of the modality contaminating the images. This study introduces a novel approach to reducing noise artefacts in fluorescence microscopy images. The noise reduction problem is posed as a Maximum A Posteriori estimation problem, and solved using a novel random field model called stochastically-connected random field, which combines random graph and field theory. This random field model better accounts for abrupt data uncertainties while preserving structures in the estimation process. Experimental results using synthetic and real fluorescence microscopy data show the proposed approach achieved strong noise reduction performance when compared to several other noise reduction algorithms using quantitative metrics. SRF was able to achieve the highest peak signal to noise ratio in the synthetic results compared to the other tested algorithms, high signal to noise ratio and contrast to noise ratio in the real fluorescence microscopy data results, and was able to maintain cell structure and subtle details while reducing background and intra-cellular noise.