CellCycleGAN: Spatiotemporal Microscopy Image Synthesis of Cell Populations using Statistical Shape Models and Conditional GANs
This work addresses the need for high-quality training data in microscopy image analysis for life sciences researchers, but it is incremental as it builds on existing statistical shape models and conditional GANs.
The authors tackled the problem of generating realistic synthetic 2D+t microscopy images of fluorescently labeled cellular nuclei to address the data scarcity in deep learning for life sciences, resulting in a method that provides instance-level control over cell cycle stage and fluorescence intensity for training and benchmarking segmentation and tracking approaches.
Automatic analysis of spatio-temporal microscopy images is inevitable for state-of-the-art research in the life sciences. Recent developments in deep learning provide powerful tools for automatic analyses of such image data, but heavily depend on the amount and quality of provided training data to perform well. To this end, we developed a new method for realistic generation of synthetic 2D+t microscopy image data of fluorescently labeled cellular nuclei. The method combines spatiotemporal statistical shape models of different cell cycle stages with a conditional GAN to generate time series of cell populations and provides instance-level control of cell cycle stage and the fluorescence intensity of generated cells. We show the effect of the GAN conditioning and create a set of synthetic images that can be readily used for training and benchmarking of cell segmentation and tracking approaches.