Miyase Tekpınar, Jelle Komen, Hana Valenta, Ran Huo, Klarinda de Zwaan, Peter Dedecker, Nergis Tomen, Kristin Grußmayer
Capturing dynamic cellular processes in live cells requires fast imaging with very high resolution beyond the diffraction limit. Fluctuation-based super-resolution techniques overcome this limit by exploiting correlations in fluorescence blinking, but they typically require hundreds of frames and computationally intensive post-processing, prohibiting real-time imaging of fast cellular events. Recent deep learning approaches aim to increase the temporal resolution; however, many rely on extensive pre-processing or large, complex models that increase training cost and inference latency, preventing real-time deployment. To address this, we employ a light-weight recurrent neural network model, which integrates sequential low-resolution frames to extract spatio-temporally correlated signals. It significantly improves temporal resolution by reducing the required number of frames down to as few as 8 frames while doubling the spatial resolution in an inference time below 30 ms. Furthermore, gentle imaging conditions are essential for extracting reliable biologically relevant information, especially in long-term experiments. Our method is suitable for live-cell imaging under extreme signal-to-noise ratio conditions, allowing imaging under very low laser intensities to prevent photo-damage. By combining simulation based training with an efficient network architecture, we introduce RESURF, a deep-learning based real-time super-resolution fluctuation imaging framework. We demonstrate that RESURF generalizes across different biological structures and can be readily adapted to various microscope setups using a small dataset for transfer learning. The accompanying dataset, comprising simulations and experiments across multiple subcellular structures and labeling strategies, establishes a benchmarking platform for fluctuation-based super-resolution techniques. RESURF offers a practical, low-latency deep-learning framework for high-throughput imaging and real-time, smart live-cell super-resolution imaging.