Description
Optical monitoring of cell movement and activity in three-dimensional space over time (3D + T imaging) has become remarkably easier. However, the development of software for segregating cell regions from the background and for tracking their dynamic positions has lagged. Individual laboratories still need to develop their own software due to different optical systems and imaging conditions. We have developed a deep learning-based software pipeline, 3DeeCellTracker, for flexible segmentation and tracking of cells in 3D + T images of deforming organs. The data was used to evaluate the performance of 3DeeCellTracker.