Localization of gene expression regions in Drosophila embryonic images

Abstract

Automatic localization of gene expression regions in Drosophila embryonic images is an important step in a computational system for the discovery of patterns of gene-gene interaction. In this paper, we propose a thresholding framework that selects an optimal threshold via a consistency criterion on good candidate thresholds provided by multiple response functions, including intensity histograms. In experiments, we test the proposed framework, being compared with four well-known methods, on images in Berkley Drosophila Genome Project (BDGP) dataset, and obtain promising results.