Deep learning permits imaging of multiple structures with the same fluorophores

Abstract

Fluorescence microscopy is a powerful tool for life sciences, which employs fluorescent tags to label and observe cellular structures and their dynamics. However, due to the spectral overlap between different dyes, a limited number of structures can be separately labeled and imaged for live cell applications. Here we propose a novel double-structure network (DBSN) that consists of multiple connected models, which can extract six subcellular structures from three images with only two separate fluorescent labels. DBSN combines the intensity-balance models to compensate for uneven fluorescent labels for different structures and the structure-separation models to extract multiple different structures with the same fluorescent labels. Therefore, DBSN permits the imaging of multiple structures with only one fluorescent label. It significantly reduces photobleaching, breaks the bottleneck of the existing technologies, and would have vast applications in cell biology.