Segmentation of the body axis into a series of repeating units is a canonical strategy in morphogenesis, and evidence of this can be seen in the skeletal system of all vertebrates. In vertebrates (and even some insects), the developmental process of segmentation is characterized by the rhythmic and sequential addition of segments (called somites) to an elongating body axis, and is regulated by an oscillatory mechanism termed the segmentation clock.
Understanding the development of the body plan in zebrafish requires high-throughput microscopy and image analysis of mutant and transgenic fish. We are developing automated methods for identifying and segmenting the somites from time-lapse microscopy images. To model the developing somites, we use a constellation model where each individual part is represented locally by an active appearance model, and make use of fast random forest classifiers and inference on graphical models to initialize and solve for the best solution.