Keyframe-aided resolution enhancement network for dynamic super-resolution structured illumination microscopy

Abstract

Deep learning has been used to reconstruct super-resolution structured illumination microscopy (SR-SIM) images with wide-field or fewer raw images, effectively reducing photobleaching and phototoxicity. However, the dependability of new structures or sample observation is still questioned using these methods. Here, we propose a dynamic SIM imaging strategy: the full raw images are recorded at the beginning to reconstruct the SR image as a keyframe, then only wide-field images are recorded. A deep-learning-based reconstruction algorithm, named KFA-RET, is developed to reconstruct the rest of the SR images for the whole dynamic process. With the structure at the keyframe as a reference and the temporal continuity of biological structures, KFA-RET greatly enhances the quality of reconstructed SR images while reducing photobleaching and phototoxicity. Moreover, KFA-RET has a strong transfer capability for observing new structures that were not included during network training.