Automatic Segmentation of Embryonic Heart in Time-Lapse Fluorescence Microscopy Image Sequences

Abstract

Embryos of animal models are becoming widely used to study cardiac development and genetics. However, the analysis of the embryonic heart is still mostly done manually. This is a very laborious and expensive task as each embryo has to be inspected visually by a biologist. We therefore propose to automatically segment the embryonic heart from high-speed fluorescence microscopy image sequences, allowing morphological and functional quantitative features of cardiac activity to be extracted. Several methods are presented and compared within a large range of images, varying in quality, acquisition parameters, and embryos position. Although manual control and visual assessment would still be necessary, the best of our methods has the potential to drastically reduce biologist workload by automating manual segmentation.