Genes expression level quantification using a spot-based algorithmic pipeline

Author

Daskalakis, Antonis ; Cavouras, Dionisis ; Bougioukos, Panagiotis ; Kostopoulos, Spiros ; Georgiadis, Pantelis ; Kalatzis, Ioannis ; Kagadis, George ; Nikiforidis, George

Author_Institution

Medical Image Processing and Analysis Group (M.I.P.A.), Department of Medical Physics, School of Medicine, University of Patras, Rio, GR-26503 Greece. phone: 2610-995012; e-mail: daskalakis@med.upatras.gr

fYear

2007

fDate

22-26 Aug. 2007

Firstpage

1148

Lastpage

1151

Abstract

An efficient spot-based (SB) algorithmic pipeline of clustering, enhancement, and segmentation techniques was developed to quantify gene expression levels in microarray images. The SB-pipeline employed i/a griding procedure to locate spot-regions, ii/a clustering algorithm (enhanced fuzzy c- means or EnFCM) to roughly segment spots from background and estimate background noise and spot´s center, iii/an adaptive histogram modification technique to accentuate spot´s boundaries, and iv/a segmentation algorithm (Seeded Region Growing or SRG), to extract microarray spots´ intensities. Extracted intensities were comparatively evaluated in term of Mean Absolute Error (MAE) against the MAGIC TOOL´s SRG employing a dataset of 7 replicated microarray images (6400 spots each). MAE box-plots mean values were 0.254 and 0.630 for the SB-pipeline and the MAGIC TOOL respectively. Total processing times for the dataset evaluated (7 images) were 2100 seconds and 3410 seconds for the SB-pipeline and MAGIC TOOL respectively.

Keywords

arrays; biochemistry; biological techniques; biology computing; fuzzy set theory; genetics; image enhancement; image segmentation; pattern clustering; pipeline processing; adaptive histogram modification technique; clustering techniques; enhancement techniques; fuzzy c-means method; genes expression; griding procedure; mean absolute error term; microarray images; seeded region growing algorithm; segmentation techniques; spot-based algorithmic pipeline; Biomedical imaging; Clustering algorithms; DNA; Fluorescence; Genetic expression; Image analysis; Image segmentation; Noise shaping; Pipelines; Sequences; Algorithms; Gene Expression Profiling; Image Interpretation, Computer-Assisted; In Situ Hybridization, Fluorescence; Microscopy, Fluorescence; Oligonucleotide Array Sequence Analysis; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE

Conference_Location

Lyon

ISSN

1557-170X

Print_ISBN

978-1-4244-0787-3

Type

conf

DOI

10.1109/IEMBS.2007.4352499

Filename

4352499