Sulfur
is a high-potential candidate for next generation electrical
energy storage due to its abundance, low cost, and nontoxicity. The
electrically insulating property of sulfur and lithium sulfide and
the solubility of polysulfides in the electrolyte, however, pose great
challenges for the realization of long-lasting lithium–sulfur
batteries for commercial applications. In recent years, much attention
has been focused on mesoporous carbon–sulfur composites as
cathode material. Fundamental studies on the performance of such electrodes
correlated to systematic variations of structural and porosity characteristics
of the carbons remain elusive, however. In this work a variety of
block copolymer (BCP) derived mesoporous carbons were studied with
uniform and tunable pore sizes as sulfur hosts. Morphologies included
hexagonally packed cylinders and co-continuous gyroids, with one-
and three-dimensional porosity, respectively. Dependence of the cyclability
of carbon–sulfur composites was tested on mesopore size, morphology,
and carbonization temperatures of up to 1600 °C. Results demonstrate the significant impact of the carbon properties
related to the carbonization temperature, such as heteroatom content,
on the capacity retention of carbon–sulfur cathodes, while
morphological parameters and mesopore sizes (between 15 and 40 nm)
of carbons studied here have little influence on performance. The
high-temperature-derived gyroidal mesoporous carbons (1600 °C)
exhibited remarkable structural stability toward activation. This
allowed for the introduction of nanopores (<4 nm) with a large
pore volume of 0.8 cm3 g–1 in addition
to the BCP-derived mesopores (15–40 nm), with total pore volumes
over 2 cm3 g–1, surface areas over 2000
m2 g–1, and retention of the well-ordered
gyroidal morphology. Highly activated, gyroidal carbon–sulfur
composites showed good cyclability and rate capability with discharge
capacities after 100 cycles of 831 mAh g–1 at 0.1
C and 730 mAh g–1 at 1 C.
Citation: Islam MS, Wang J-K, Johnson SS, Thurtell MJ, Kardon RH, Garvin MK. A deep-learning approach for automated OCT en-face retinal vessel segmentation in cases of optic disc swelling using multiple en-face images as input. Trans Vis Sci Tech. 2020;9(2):17, https://doi.org/10. 1167/tvst.9.2.17 Purpose: In cases of optic disc swelling, segmentation of projected retinal blood vessels from optical coherence tomography (OCT) volumes is challenging due to swellingbased shadowing artifacts. Based on our hypothesis that simultaneously considering vessel information from multiple projected retinal layers can substantially increase vessel visibility, in this work, we propose a deep-learning-based approach to segment vessels involving the simultaneous use of three OCT en-face images as input.Methods: A human expert vessel tracing combining information from OCT en-face images of the retinal pigment epithelium (RPE), inner retina, and total retina as well as a registered fundus image served as the reference standard. The deep neural network was trained from the imaging data from 18 patients with optic disc swelling to output a vessel probability map from three OCT en-face input images. The vessels from the OCT en-face images were also manually traced in three separate stages to compare with the performance of the proposed approach.Results: On an independent volume-matched test set of 18 patients, the proposed deep-learning-based approach outperformed the three OCT-based manual tracing stages. The manual tracing based on three OCT en-face images also outperformed the manual tracing using only the traditional RPE en-face image.
Conclusions:In cases of optic disc swelling, use of multiple en-face images enables better vessel segmentation when compared with the traditional use of a single en-face image.Translational Relevance: Improved vessel segmentation approaches in cases of optic disc swelling can be used as features for an improved assessment of the severity and cause of the swelling.
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.