While
the use of deep learning is a valuable technology for automatic
detection systems for medical data and images, the biofouling community
is still lacking an analytical tool for the detection and counting
of diatoms on samples after short-term field exposure. In this work,
a fully convolutional neural network was implemented as a fast and
simple approach to detect diatoms on two-channel (fluorescence and
phase-contrast) microscopy images by predicting bounding boxes. The
developed approach performs well with only a small number of trainable
parameters and a F1 score of 0.82. Counting diatoms was evaluated
on a data set of 600 microscopy images of three different surface
chemistries (hydrophilic and hydrophobic) and is very similar to counting
by humans while demanding only a fraction of the analysis time.
Polyelectrolyte
multilayer (PEM) assembly is a versatile
tool to construct low-fouling coatings. For application in the marine
environment, their structure needs to be stabilized by covalent linkage.
Here, we introduce an approach for spin coating of silane-based sol–gel
chemistries using layer-by-layer assembly of polysaccharide-based
hybrid polymer coatings (LBLHPs). The silane sol–gel chemistry
allows the films to be cross-linked under water-based and mild reaction
conditions. Two different silanes were used for this purpose, a conventional
triethoxymethyl silane and a de novo synthesized zwitterionic silane.
The polysaccharide–silane hybrid polymer coatings were thoroughly
characterized with spectroscopic ellipsometry, water contact angle
(WCA) goniometry, attenuated total reflection–Fourier transform
infrared spectroscopy, and atomic force microscopy. The coatings showed
good stability in seawater, smooth surfaces, a high degree of hydration,
and WCAs below or close to the Berg limit. LBLHPs showed low-fouling
properties in biological assays against nonspecific protein adsorption,
attachment of the diatom Navicula perminuta, and settlement of zoospores of the macroalga Ulva
linza.
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.