Segmentation of complementary dna microarray images using the fuzzy gaussian mixture model technique

 
This item is provided by the institution :
Technological Educational Institute of Athens
Repository :
Ypatia - Institutional Repository
see the original item page
in the repository's web site and access all digital files if the item*
share




2006 (EN)
Segmentation of complementary dna microarray images using the fuzzy gaussian mixture model technique (EN)

Σπυρίδωνος, Παναγιώτα Π. (EL)
Αθανασιάδης, Εμμανουήλ Ι. (EL)
Κάβουρας, Διονύσης Α. (EL)
Γκλώτσος, Δημήτριος (EL)
Καλατζής, Ιωάννης (EL)

Τ.Ε.Ι. Αθήνας. Σχολή Τεχνολογικών Εφαρμογών. Τμήμα Μηχανικών Βιοϊατρικής Τεχνολογίας Τ.Ε. (EL)
Νικηφορίδης, Γεώργιος Χ. (EL)

The objective of this work was to investigate the segmentation ability of the Fuzzy Gaussian Mixture Models (FGMM) clustering algorithm, applied on complementary DNA (cDNA) images. A Simulated Microarray image of 200 cells, each containing one spot, was produced following standard established procedure. An automatic gridding process was developed and applied on the microarray image for the task of locating spot borders and surrounding background in each cell. The FGMM and the Gaussian Mixture Model (GMM) algorithms were applied to each cell, with the purpose of discriminating foreground from background. The segmentation abilities of both algorithms were evaluated by means of the segmentation matching factor in respect to the actual classes (foreground-background pixels) of the simulated spots. The FGMM was found to perform better and with equal processing time, as compared to the GMM, rendering the FGMM algorithm an efficient alternative for segmenting cDNA microarray images. (EN)

full paper
conferenceItem

Microarray image (EN)
Segmentation (EN)
Εικόνες μικροσυστοιχιών (EN)
Κατάτμηση (EN)

ΤΕΙ Αθήνας (EL)
Technological Educational Institute of Athens (EN)

International Special Topic Conference on Information Technology in Biomedicine (EN)

English

2006




*Institutions are responsible for keeping their URLs functional (digital file, item page in repository site)