Building an Automatic Phenotyping System of Developing Embryos

This dissertation presents a learning-based system for the detection, identification, localization, and measurement of various sub-cellular structures in microscopic images of developing embryos. The system analyzes sequences if images obtained through DIC microscopy and detects cell nuclei, cytoplasm, and cell walls automatically. The system described in this dissertation is the key component of a fully automated phenotype analysis system. Our study primarily concerns the early stages of development of C. Elegans nematode embryos, from fertilization to the four-cell stage. The method proposed in this dissertation consists in learning the entire processing chain from end to end, from raw pixels to ultimate object categories. The system contains three modules: (1) a convolutional network trained to classify each pixel into five categories: cell wall, cytoplasm, nuclear membrane, nucleus, outside medium; (2) an Energy-Based Model which cleans up the output of the convolutional network by learning local consistency constraints that must be satisfied by label images; (3) A set of elastic models of the embryo at various stages of development that are matched to the label images. When observing normal (wild type) embryos it is possible to visualize important cellular functions such as nuclear movements and fusions, cytokinesis and the setting up of crucial cell-cell contacts. These events are highly reproducible from embryo to embryo. The events will deviate from normal behaviors when the function of a specific gene is perturbed, therefore allowing the association of a gene's activity with specific early embryonic events. One important goal of the system is to automatically detect whether the development is normal (and therefore, not particularly interesting), or abnormal and worth investigating. Another important goal is to automatically extract quantitative measurements such a the migration speed of the nuclei and the precise time of cell divisions.