TY  - JOUR
A1  - Berberich, Andreas
A1  - Kurz, Andreas
A1  - Reinhard, Sebastian
A1  - Paul, Torsten Johann
A1  - Burd, Paul Ray
A1  - Sauer, Markus
A1  - Kollmannsberger, Philip
T1  - Fourier Ring Correlation and anisotropic kernel density estimation improve deep learning based SMLM reconstruction of microtubules
JF  - Frontiers in Bioinformatics
N2  - Single-molecule super-resolution microscopy (SMLM) techniques like dSTORM can reveal biological structures down to the nanometer scale. The achievable resolution is not only defined by the localization precision of individual fluorescent molecules, but also by their density, which becomes a limiting factor e.g., in expansion microscopy. Artificial deep neural networks can learn to reconstruct dense super-resolved structures such as microtubules from a sparse, noisy set of data points. This approach requires a robust method to assess the quality of a predicted density image and to quantitatively compare it to a ground truth image. Such a quality measure needs to be differentiable to be applied as loss function in deep learning. We developed a new trainable quality measure based on Fourier Ring Correlation (FRC) and used it to train deep neural networks to map a small number of sampling points to an underlying density. Smooth ground truth images of microtubules were generated from localization coordinates using an anisotropic Gaussian kernel density estimator. We show that the FRC criterion ideally complements the existing state-of-the-art multiscale structural similarity index, since both are interpretable and there is no trade-off between them during optimization. The TensorFlow implementation of our FRC metric can easily be integrated into existing deep learning workflows.
KW  - dSTORM
KW  - deep learning–artificial neural network (DL-ANN)
KW  - single molecule localization microscopy
KW  - microtubule cytoskeleton
KW  - super-resolution
Y1  - 2021
U6  - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-261686
VL  - 1
ER  - 
TY  - JOUR
A1  - Endesfelder, Ulrike
A1  - Malkusch, Sebastian
A1  - Flottmann, Benjamin
A1  - Mondry, Justine
A1  - Liguzinski, Piotr
A1  - Verveer, Peter J.
A1  - Heilemann, Mike
T1  - Chemically Induced Photoswitching of Fluorescent Probes - A General Concept for Super-Resolution Microscopy
JF  - Molecules
N2  - We review fluorescent probes that can be photoswitched or photoactivated and are suited for single-molecule localization based super-resolution microscopy. We exploit the underlying photochemical mechanisms that allow photoswitching of many synthetic organic fluorophores in the presence of reducing agents, and study the impact of these on the photoswitching properties of various photoactivatable or photoconvertible fluorescent proteins. We have identified mEos2 as a fluorescent protein that exhibits reversible photoswitching under various imaging buffer conditions and present strategies to characterize reversible photoswitching. Finally, we discuss opportunities to combine fluorescent proteins with organic fluorophores for dual-color photoswitching microscopy.
KW  - Photoactivated localization microscopy
KW  - Fusion proteins
KW  - Molecules
KW  - Patterns
KW  - Switch
KW  - Limit
KW  - Time
KW  - photoswitchable organic fluorophores
KW  - fluorescent proteins
KW  - super-resolution
KW  - PALM
KW  - dSTORM
Y1  - 2011
U6  - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-134080
VL  - 16
IS  - 4
ER  - 
TY  - JOUR
A1  - Endesfelder, Ulrike
A1  - Malkusch, Sebastian
A1  - Flottmann, Benjamin
A1  - Mondry, Justine
A1  - Liguzinski, Piotr
A1  - Verveer, Peter J.
A1  - Heilemann, Mike
T1  - Chemically Induced Photoswitching of Fluorescent Probes - A General Concept for Super-Resolution Microscopy
N2  - We review fluorescent probes that can be photoswitched or photoactivated and are suited for single-molecule localization based super-resolution microscopy. We exploit the underlying photochemical mechanisms that allow photoswitching of many synthetic organic fluorophores in the presence of reducing agents, and study the impact of these on the photoswitching properties of various photoactivatable or photoconvertible fluorescent proteins. We have identified mEos2 as a fluorescent protein that exhibits reversible photoswitching under various imaging buffer conditions and present strategies to characterize reversible photoswitching. Finally, we discuss opportunities to combine fluorescent proteins with organic fluorophores for dual-color photoswitching microscopy.
KW  - Super-Resolution Microscopy
KW  - photoswitchable organic fluorophores
KW  - fluorescent proteins
KW  - super-resolution
KW  - PALM
KW  - dSTORM
Y1  - 2011
U6  - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-74896
ER  -