A pipeline to track unlabeled cells in wide migration chambers using pseudofluorescence

Cell migration is a pivotal biological process, whose dysregulation is found in many diseases including inflammation and cancer. Advances in microscopy technologies allow now to study cell migration in vitro, within microenvironments that resemble in vivo conditions. However, when cells are observed within large 3D migration chambers at low magnification and for extended periods of time, data analysis becomes difficult. Indeed, cell detection and tracking are hampered due to the large pixel size, the possible low signal-to-noise ratio and distortions in the cell shape due to changes in the z-axis position. Although fluorescent staining can be used to facilitate cell detection, it may alter cell behavior and suffer from fluorescence loss over time (photobleaching). Here we describe the application of an image analysis pipeline based on deep learning to convert the transmitted light signal from unlabeled lymphoma cells to pseudofluorescence. Such pipeline confers a significant improvement in tracking accuracy while not suffering from photobleaching. This is reflected in the possibility of tracking cells for three-fold longer periods of time.