Oct 2026· Nature Communications· Vol 17· 0 citations· 40 references
Medicine
TL;DR
Two deep-learning methods for RESOLFT nanoscopy are used: HDN denoising enables five-fold longer live-cell imaging, while spatial upsampling with temporal context restores subsampled data for fourfold higher frame rates and reduced artifacts.
Abstract
Capturing the dynamic interplay of proteins and organelles within cells requires microscopy methods with high spatial and temporal resolution. Reversible Saturable OpticaL Fluorescent Transition (RESOLFT) demonstrated great potential for live cell nanoscopy by using patterned light and reversibly switching fluorescent probes. Despite the latest improvement in both switching probes and optical schemes, the duration and frame rate of the time-lapse are still limited by photobleaching and spatial sampling steps. Here, we present two distinct strategies based on deep learning to restore low signal-to-noise-ratio (SNR) or under-sampled images pushing the experimental boundaries of RESOLFT. We demonstrate the capability of Hierarchical DivNoising (HDN) to restore low-SNR RESOLFT data while maintaining full spatial resolution, both in supervised and unsupervised settings. This allows a 10-fold reduction of light dose per frame, and up to 5 times longer imaging. Then, we present Fast-MoNaLISA, a method that reduces the acquisition time of any point-scanning systems. This allows a 4-fold increase in frame rate, and a reduction of scanning artefacts. Overall, our methods open up possibilities for dynamic data acquisition at the sub-organelle level, such as vesicles budding in and out from intact mitochondria, or the actin meshwork formation and dissociation. The authors use two deep-learning methods for RESOLFT nanoscopy: HDN denoising enables five-fold longer live-cell imaging, while spatial upsampling with temporal context restores subsampled data for fourfold higher frame rates and reduced artifacts.
Optical-resolution photoacoustic microscopy (OR-PAM) enables label-free, subcellular-resolution microvascular imaging, but the speed-resolution trade-off remains a bottleneck. While sparse sampling accelerates acquisition, the disparity between OR-PAM’s tight optical focus and enlarged scanning steps causes irreversibl...
Ke-Xin Chen, Zhou-Yan Cao, Rui-Qin Li et al.· Photoacoustics· 0 citations
Fluorescence super-resolution microscopy has advanced optical imaging into the nanoscale regime, transforming biological and interdisciplinary research. However, wide-field super-resolution techniques often compromise temporal resolution, thereby limiting the capture of rapid and transient biological events in living s...
Wei Guo, L. Feletti, A. Radenović· Nature Methods· 1 citation
FLIMPSR, a deep learning-based pixel super-resolution framework for multi-channel FLIM that enhances resolution without requiring hardware modifications, enables accelerated FLIM imaging and supports translation toward compact and clinically relevant lifetime imaging systems.
Paloma Casteleiro Costa, Parnian Ghapandarkashani, Xu-Hui Liu et al.· Emerging Topics in Artificia...· 0 citations
Two-Photon microscopy (TPM) is an intravital imaging technique with deep tissue penetration, high three-dimensional resolution and low photobleaching. However, imaging speeds have traditionally been limited because images are generated by point scanning. Recently, Spectro-Temporal Laser Imaging by Diffractive Excitatio...
C. Stock, Gregory Berg, Matthea Thielking et al.· Frontiers in Photonics· 0 citations
The combination of stimulated emission depletion (STED) microscopy with fluorescence lifetime imaging microscopy (FLIM) offers a powerful route to functional super-resolution imaging, but remains technically challenging for lifetime-based sensing because of the complex interplay between stimulated emission, photon budg...
Julia Rubio-Loscertales, Jose Requejo-Isidro, Cristina Flors· Methods and Applications in...· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 9, 2026
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.