Cargando…

Segmentation and Morphology Computation of a Spiky Nanoparticle Using the Hourglass Neural Network

[Image: see text] Morphological measurements of nanoparticles in electron microscopy images are tedious, laborious, and often succumb to human errors. Deep learning methods in artificial intelligence (AI) paved the way for automated image understanding. This work proposes a deep neural network (DNN)...

Descripción completa

Detalles Bibliográficos
Autores principales: Hussain, Muhammad Ishfaq, Rafique, Muhammad Aasim, Jung, Wan-Gil, Kim, Bong-Joong, Jeon, Moongu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2023
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10210197/
https://www.ncbi.nlm.nih.gov/pubmed/37251121
http://dx.doi.org/10.1021/acsomega.3c00783
_version_ 1785047017923280896
author Hussain, Muhammad Ishfaq
Rafique, Muhammad Aasim
Jung, Wan-Gil
Kim, Bong-Joong
Jeon, Moongu
author_facet Hussain, Muhammad Ishfaq
Rafique, Muhammad Aasim
Jung, Wan-Gil
Kim, Bong-Joong
Jeon, Moongu
author_sort Hussain, Muhammad Ishfaq
collection PubMed
description [Image: see text] Morphological measurements of nanoparticles in electron microscopy images are tedious, laborious, and often succumb to human errors. Deep learning methods in artificial intelligence (AI) paved the way for automated image understanding. This work proposes a deep neural network (DNN) for the automated segmentation of a Au spiky nanoparticle (SNP) in electron microscopic images, and the network is trained with a spike-focused loss function. The segmented images are used for the growth measurement of the Au SNP. The auxiliary loss function captures the spikes of the nanoparticle, which prioritizes the detection of spikes in the border regions. The growth of the particles measured by the proposed DNN is as good as the measurement in manually segmented images of the particles. The proposed DNN composition with the training methodology meticulously segments the particle and consequently provides accurate morphological analysis. Furthermore, the proposed network is tested on an embedded system for integration with the microscope hardware for real-time morphological analysis.
format Online
Article
Text
id pubmed-10210197
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher American Chemical Society
record_format MEDLINE/PubMed
spelling pubmed-102101972023-05-26 Segmentation and Morphology Computation of a Spiky Nanoparticle Using the Hourglass Neural Network Hussain, Muhammad Ishfaq Rafique, Muhammad Aasim Jung, Wan-Gil Kim, Bong-Joong Jeon, Moongu ACS Omega [Image: see text] Morphological measurements of nanoparticles in electron microscopy images are tedious, laborious, and often succumb to human errors. Deep learning methods in artificial intelligence (AI) paved the way for automated image understanding. This work proposes a deep neural network (DNN) for the automated segmentation of a Au spiky nanoparticle (SNP) in electron microscopic images, and the network is trained with a spike-focused loss function. The segmented images are used for the growth measurement of the Au SNP. The auxiliary loss function captures the spikes of the nanoparticle, which prioritizes the detection of spikes in the border regions. The growth of the particles measured by the proposed DNN is as good as the measurement in manually segmented images of the particles. The proposed DNN composition with the training methodology meticulously segments the particle and consequently provides accurate morphological analysis. Furthermore, the proposed network is tested on an embedded system for integration with the microscope hardware for real-time morphological analysis. American Chemical Society 2023-05-12 /pmc/articles/PMC10210197/ /pubmed/37251121 http://dx.doi.org/10.1021/acsomega.3c00783 Text en © 2023 The Authors. Published by American Chemical Society https://creativecommons.org/licenses/by-nc-nd/4.0/Permits non-commercial access and re-use, provided that author attribution and integrity are maintained; but does not permit creation of adaptations or other derivative works (https://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Hussain, Muhammad Ishfaq
Rafique, Muhammad Aasim
Jung, Wan-Gil
Kim, Bong-Joong
Jeon, Moongu
Segmentation and Morphology Computation of a Spiky Nanoparticle Using the Hourglass Neural Network
title Segmentation and Morphology Computation of a Spiky Nanoparticle Using the Hourglass Neural Network
title_full Segmentation and Morphology Computation of a Spiky Nanoparticle Using the Hourglass Neural Network
title_fullStr Segmentation and Morphology Computation of a Spiky Nanoparticle Using the Hourglass Neural Network
title_full_unstemmed Segmentation and Morphology Computation of a Spiky Nanoparticle Using the Hourglass Neural Network
title_short Segmentation and Morphology Computation of a Spiky Nanoparticle Using the Hourglass Neural Network
title_sort segmentation and morphology computation of a spiky nanoparticle using the hourglass neural network
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10210197/
https://www.ncbi.nlm.nih.gov/pubmed/37251121
http://dx.doi.org/10.1021/acsomega.3c00783
work_keys_str_mv AT hussainmuhammadishfaq segmentationandmorphologycomputationofaspikynanoparticleusingthehourglassneuralnetwork
AT rafiquemuhammadaasim segmentationandmorphologycomputationofaspikynanoparticleusingthehourglassneuralnetwork
AT jungwangil segmentationandmorphologycomputationofaspikynanoparticleusingthehourglassneuralnetwork
AT kimbongjoong segmentationandmorphologycomputationofaspikynanoparticleusingthehourglassneuralnetwork
AT jeonmoongu segmentationandmorphologycomputationofaspikynanoparticleusingthehourglassneuralnetwork