A dictionary-based approach to reduce noise in fluorescent microscopy images

Live imaging of cells and small organisms is an important step for understanding and analyzing biological functions via studying cellular dynamics. Cell segmentation and tracking in microscopy images are challenging tasks due mainly to embedded noise. We proposed to use an adaptive dictionary learning approach for filtering and reducing noise in fluorescent microscopy images. We applied our method to detect nuclei in noisy images from different types of datasets and the results demonstrated that our proposed algorithm had a satisfactory performance with an average sensitivity of 99.1%, precision of 92.4% and f-measure of 95.6%. As a result, this method is a promising preprocessing tool for detecting nuclei in noisy microscopy images.