Symmetry-based detection of nuclei in microscopy images

Accurate detection of individual cell nuclei in microscopic images is an essential task for many biological studies. Blur, clutter, bleed through, imaging noise and touching and partially overlapping nuclei with varying sizes and shapes make automated detection of individual cell nuclei a challenging task using image analysis. In this paper we propose an automated method for robust detection of individual cell nuclei in fluorescence in-situ hybridization (FISH) images obtained via confocal microscopy. Our algorithm consists of the following steps: image denoising, binarization, detection of nuclear seed points combining the fast radial symmetric transform (FRST) and a distance-based non-maximum suppression. We show that our algorithm provides improved detection accuracy compared to the existing algorithms.