DL-AO: Deep Learning driven Adaptive Optics
|
Deep learning-driven adaptive optics for SMLM to allow direct inference of wavefront distortion and near real-time compensation. The trained deep neural network monitors the individual emission patterns from single-molecule experiments, infers their shared wavefront distortion, feeds the estimates through a dynamic filter and drives a deformable mirror to compensate sample-induced aberrations. This method simultaneously estimates and compensates 28 wavefront deformation shapes and improves the resolution and fidelity of three-dimensional SMLM through >130-µm-thick brain tissue specimens.
Full Reference:P. Zhang, D. Ma, X. Cheng, A. P. Tsai, Y. Tang, H. Gao, L. Fang, C. Bi, G. E. Landreth, A. A. Chubykin, F. Huang, "Deep Learning-driven Adaptive Optics for Single-molecule Localization Microscopy" (2023) Nature Methods, 20, 1748–1758 |
|
INSPR: in situ Point Spread Function Retrieval
|
INSPR toolbox is developed for both biplane and astigmatism-based setups. It constructs an in situ 3D point spread function (PSF) directly from the obtained single molecule dataset and features an easy-to-use user interface including all steps of 3D single molecule localization from INSPR model generation, pupil-based 3D localization (supporting both GPU with cubic spline implementation and CPU versions), drift correction, volume alignment, to super-resolution image reconstruction. It also contains a small single molecule dataset for users to run as an example.
Full Reference: Fan Xu, Donghan Ma, Kathryn P. MacPherson, Sheng Liu, Ye Bu, Yu Wang, Yu Tang, Cheng Bi, Tim Kwok, Alexander A. Chubykin, Peng Yin, Sarah Calve, Gary E. Landreth, and Fang Huang, "Three-dimensional nanoscopy of whole cells and tissues with in situ point spread function retrieval" (2020) Nature Methods, 17(5): 531-540. |
|
NCS: Noise Correction Algorithm for sCMOS Cameras
|
NCS (noise correction algorithm for sCMOS (CMOS) cameras) is an algorithm that minimizes sCMOS noise (termed 'pixel-dependent noise') from microscopy images with arbitrary structures.
Full Reference: S. Liu, M. J. Mlodzianoski, Z. Hu, Y. Ren, K. McElmurry, D. M. Suter, F. Huang, "sCMOS noise-correction algorithm for microscopy images" (2017) Nature Methods, Vol. 14, 8, 760 - 761. |
|
Simplex AO: Simplex Algorithm based Adaptive Optics in Single Molecule Switching Nanoscopy
|
This package contains an example labview code module for implementing Nelder-Mead Simplex Algorithm for AO and adaptive PSF shaping in SMSN.
Big thanks for Edward Allgeyer and George Sirinakis, University of Cambridge for programming parts of subvis included in this module Full Reference: M. J. Mlodzianoski, P. J. Cheng-Hathaway, S. M. Bemiller, T. J. McCray, S. Liu, D. A. Miller, B. T. Lamb, G. E. Landreth, F. Huang, "Active PSF shaping and adaptive optics enable volumetric localization microscopy through brain sections" (2018) Nature Methods, Advance Online Publication, doi: 10.1038/s41592-018-0053-8 |
|
smNet: Deep Neural Network for Single Molecule and Super-Resolution Imaging
|
smNet: a deep neural network to retrieve multiple classes of information from single molecule emission patterns with precision approaching the theoretical limit.
PSF Toolbox: Pupil based PSF generator Full Reference: P. Zhang*, S. Liu*, A. Chaurasia, D. Ma, M. J. Mlodzianoski, E. Culurciello and F. Huang, "Analyzing complex single molecule emission patterns with deep learning"(2018) Nature Methods, doi: https://doi.org/10.1038/s41592-018-0153-5, *Equal Contribution |
|
