Resolution enhancement in scanning electron microscopy using deep learning.

Sci Rep

Electrical and Computer Engineering Department, University of California, Los Angeles, CA, 90095, USA.

Published: August 2019

We report resolution enhancement in scanning electron microscopy (SEM) images using a generative adversarial network. We demonstrate the veracity of this deep learning-based super-resolution technique by inferring unresolved features in low-resolution SEM images and comparing them with the accurately co-registered high-resolution SEM images of the same samples. Through spatial frequency analysis, we also report that our method generates images with frequency spectra matching higher resolution SEM images of the same fields-of-view. By using this technique, higher resolution SEM images can be taken faster, while also reducing both electron charging and damage to the samples.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6700066PMC
http://dx.doi.org/10.1038/s41598-019-48444-2DOI Listing

Publication Analysis

Top Keywords

sem images
20
resolution enhancement
8
enhancement scanning
8
scanning electron
8
electron microscopy
8
higher resolution
8
resolution sem
8
images
6
sem
5
resolution
4

Similar Publications

Aims: This study aimed to develop Imatinib Mesylate (IMT)-loaded Poly Lactic-co-Glycolic Acid (PLGA)-D-α-tocopheryl polyethylene glycol succinate (TPGS)- Polyethylene glycol (PEG) hybrid nanoparticles (CSLHNPs) with optimized physicochemical properties for targeted delivery to glioblastoma multiforme.

Background: Glioblastoma multiforme (GBM) is the most destructive type of brain tumor with several complications. Currently, most treatments for drug delivery for this disease face challenges due to the poor blood-brain barrier (BBB) and lack of site-specific delivery.

View Article and Find Full Text PDF

The NASICON-type NaV(PO) (NVP) is recognized as a potential cathode material for Na-ion batteries (SIBs). Nevertheless, its inherent small electronic conductivity induces limited cycling stability and rate performance. Carbon coating, particularly N-doped carbon, has been identified as an effective strategy to address these challenges.

View Article and Find Full Text PDF

Objectives: This study aimed to compare the marginal adaptation of a cold ceramic (CC) sealer with the single-cone obturation technique with that of an AH-26 sealer with the lateral compaction technique in single-canal teeth.

Materials And Methods: In this in vitro experimental study, the root canals of 24 extracted single-rooted single-canal teeth were instrumented to F3 files by the crown-down technique and randomly assigned to 2 groups (n = 12). The root canals were obturated with a CC sealer and single-cone obturation technique with 4% gutta-percha in group 1 and with an AH-26 sealer and lateral compaction technique with 2% gutta-percha in group 2.

View Article and Find Full Text PDF

Femtosecond lasers represent a novel tool for tattoo removal as sources that can be operated at high power, potentially leading to different removal pathways and products. Consequently, the potential toxicity of its application also needs to be evaluated. In this framework, we present a comparative study of Ti:Sapphire femtosecond laser irradiation, as a function of laser power and exposure time, on water dispersions of Pigment Green 7 (PG7) and the green tattoo ink Green Concentrate (GC), which contains PG7 as its coloring agent.

View Article and Find Full Text PDF

Background: Antiseptic solutions are commonly utilized during total joint arthroplasty (TJA) to prevent and treat periprosthetic joint infection (PJI). The purpose of this study was to investigate which antiseptic solution is most effective against methicillin-sensitive Staphylococcus aureus (MSSA) and Escherichia coli biofilms established in vitro on orthopaedic surfaces commonly utilized in total knee arthroplasty: cobalt-chromium (CC), oxidized zirconium (OxZr), and polymethylmethacrylate (PMMA).

Methods: MSSA and E.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!