Determination of the Developmental Age of a Drosophila Embryo from Confocal Images of its Segmentation Gene Expression Patterns

Abstract

In the paper, we address the problem of the temporal characterization of Drosophila embryos. We have developed a method for automated staging of an embryo on the basis of a confocal image of its gene expression pattern. Phases of spectral Fourier coefficients were used as the features characterizing temporal changes in expression patterns. The age detection is implemented by applying support vector regression, which is a machine learning method for creating regression functions of arbitrary type from a set of training data. The training set is composed of embryos for which the precise developmental age was determined by measuring the degree of membrane invagination. Testing the quality of regression on the training set showed a good prediction accuracy.