EmbSAM: cell boundary localization and Segment Anything Model for fast images of developing embryos

Cellular shape dynamics are critical for understanding cell fate determination and organogenesis during development. However, fluorescence live-cell images of cell membranes frequently suffer from a low signal-to-noise ratio, especially during long-duration imaging with high spatiotemporal resolutions. The low ratio is caused by a tradeoff between embryo viability and phototoxicity and photobleaching of fluorescent markers, which hinders effective cell shape reconstruction, particularly in rapidly developing embryos. Here, we devise an integrative computational framework, EmbSAM, that incorporates a deep-learning-based cell boundary localization algorithm and the Segment Anything Model. EmbSAM enables accurate segmentation of three-dimensional cell membrane images for roundworm Caenorhabditis elegans embryos imaged with exceptional temporal resolution, i.e., every 10 seconds per stack. The resolved cell shapes prior to gastrulation quantitatively characterize a series of cell-division-coupled morphodynamics associated with cell position, cell division phase duration, cell division axis reorientation, cell identity, lineage, fate, among others, which can be accessed locally and online.