A deep
learning approach has been taken to improve detection characteristics
of surface plasmon microscopy (SPM) of light scattering. Deep learning
based on the convolutional neural network algorithm was used to estimate
the effect of scattering parameters, mainly the number of scatterers.
The improvement was assessed on a quantitative basis by applying the
approach to SPM images formed by coherent interference of scatterers.
It was found that deep learning significantly improves the accuracy
over conventional detection: the enhancement in the accuracy was shown
to be significantly higher by almost 6 times and useful for scattering
by polydisperse mixtures. This suggests that deep learning can be
used to find scattering objects effectively in the noisy environment.
Furthermore, deep learning can be extended directly to label-free
molecular detection assays and provide considerably improved detection
in imaging and microscopy techniques.
We investigated the transport of
neuronal mitochondria using superlocalized near-fields with plasmonic
nanohole arrays (PNAs). Compared to traditional imaging techniques,
PNAs create a massive array of superlocalized light beams and allow
3D mitochondrial dynamics to be sampled and extracted almost in real
time. In this work, mitochondrial fluorescence excited by the PNAs
was captured by an optical microscope using dual objective lenses,
which produced superlocalized dynamics while minimizing light scattering
by the plasmonic substrate. It was found that mitochondria move with
an average velocity 0.33 ± 0.26 μm/s, a significant part
of which, by almost 50%, was contributed by the movement along the
depth axis (z-axis). Mitochondrial positions were
acquired with superlocalized precision (σ
x
= 5.7 nm and σ
y
= 11.8 nm)
in the lateral plane and σ
z
= 78.7
nm in the z-axis, which presents an enhancement by
12.7-fold in resolution compared to confocal fluorescence microscopy.
The approach is expected to serve as a way to provide 3D information
on molecular dynamics in real time.
Despite of high quantum efficiency of solar energy conversion by photosynthesis, practical development of photosynthetic solar energy has been limited so far. One of the main challenges is relatively poor...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.