Local smoothing image segmentation for spotted microarray images

doi:10.1198/016214506000001158

Local smoothing image segmentation for spotted microarray images

2007-12-01

15

PRE

AI

DOI：10.1198/016214506000001158

原文链接

原文求助

摘要

En 中文

Gene microarray data are used in a wide variety of applications, including pharmaceutical and clinical research. By comparing gene expression in normal and abnormal cells, microarrays can be used to identify genes involved in particular diseases, and these genes then can be targeted by therapeutic drugs. Most gene expression data are produced from spotted microarray images. A spotted microarray image consists of thousands of spots, with individual DNA sequences first printed at each spot and then equal amounts of probes (e.g., cDNA samples) from treatment and control cells mixed and hybridized with the printed DNA sequences. To obtain gene expression data, the image first must be segmented to separate foregrounds from backgrounds for individual spots, after which averages of foreground pixels are used to compute the gene expression data. Thus image segmentation of microarray images is directly related to the reliability of gene expression data. Several image segmentation procedures have been suggested in the literature and included in software packages handling gene microarray data. This article proposes a new image segmentation methodology based on local smoothing. Theoretical arguments and numerical studies show that it has good statistical properties and should perform well in applications.

Keyword:

background

boundary curve

consistency

edge detection

foreground

gene expression data

gray level

image processing

image segmentation

jump location curve

local polynomial kernel smoothing

nonparametric regression

spots

Local smoothing image segmentation for spotted microarray images

摘要

AI总结

期刊

机构

引用论文