In this paper we propose a novel microarray segmentationstrategy to separate background and foregroundsignals in microarray images making use of a neurofuzzyprocessing pipeline. In particular a Kohonen SelfOrganizing Map followed by a Fuzzy K-Mean classifierare employed to properly manage critical cases likesaturated spot and spike noise. To speed up the overallprocess a Hilbert sampling is performed together withan ad-hoc analysis of statistical distribution of signals.Experiments confirm the validity of the proposed techniqueboth in terms of measured and visual inspectionquality.
Neurofuzzy Segmentation of Microarray Images
BATTIATO, SEBASTIANO;FARINELLA, GIOVANNI MARIA;GALLO, Giovanni;
2008-01-01
Abstract
In this paper we propose a novel microarray segmentationstrategy to separate background and foregroundsignals in microarray images making use of a neurofuzzyprocessing pipeline. In particular a Kohonen SelfOrganizing Map followed by a Fuzzy K-Mean classifierare employed to properly manage critical cases likesaturated spot and spike noise. To speed up the overallprocess a Hilbert sampling is performed together withan ad-hoc analysis of statistical distribution of signals.Experiments confirm the validity of the proposed techniqueboth in terms of measured and visual inspectionquality.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.