Neurofuzzy segmentation of microarray images

In this paper we propose a novel microarray segmentation strategy to separate background and foreground signals in microarray images making use of a neurofuzzy processing pipeline. In particular a Kohonen Self Organizing Map followed by a Fuzzy K-Mean classifier are employed to properly manage critical cases like saturated spot and spike noise. To speed up the overall process a Hilbert sampling is performed together with an ad-hoc analysis of statistical distribution of signals. Experiments confirm the validity of the proposed technique both in terms of measured and visual inspection quality.