Deep-SMOLM: deep learning resolves the 3D orientations and 2D positions of overlapping single molecules with optimal nanoscale resolution

• Published in: Optics express Vol. 30; no. 20; pp. 36761 - 36773
• Main Authors: Wu, Tingting, Lu, Peng, Rahman, Md Ashequr, Li, Xiao, Lew, Matthew D
• Format: Journal Article
• Language: English
• Published: United States Optica Publishing Group 26.09.2022
• Subjects: Amyloid; Deep Learning; Image Processing, Computer-Assisted; Microscopy - methods; Nanotechnology - methods
• ISSN: 1094-4087; 1094-4087
• DOI: 10.1364/OE.470146

Dipole-spread function (DSF) engineering reshapes the images of a microscope to maximize the sensitivity of measuring the 3D orientations of dipole-like emitters. However, severe Poisson shot noise, overlapping images, and simultaneously fitting high-dimensional information-both orientation and position-greatly complicates image analysis in single-molecule orientation-localization microscopy (SMOLM). Here, we report a deep-learning based estimator, termed Deep-SMOLM, that achieves superior 3D orientation and 2D position measurement precision within 3% of the theoretical limit (3.8° orientation, 0.32 sr wobble angle, and 8.5 nm lateral position using 1000 detected photons). Deep-SMOLM also demonstrates state-of-art estimation performance on overlapping images of emitters, e.g., a 0.95 Jaccard index for emitters separated by 139 nm, corresponding to a 43% image overlap. Deep-SMOLM accurately and precisely reconstructs 5D information of both simulated biological fibers and experimental amyloid fibrils from images containing highly overlapped DSFs at a speed ~10 times faster than iterative estimators.