Workflow towards automated segmentation of agglomerated, non-spherical particles from electron microscopy images using artificial neural networks

Abstract We present a workflow for obtaining fully trained artificial neural networks that can perform automatic particle segmentations of agglomerated, non-spherical nanoparticles from scanning electron microscopy images “from scratch”, without the need for large training data sets of manually anno...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Bastian Rühle, Julian Frederic Krumrey, Vasile-Dan Hodoroaba
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/5f1227f7c1114b9b8aea7aff6a12191a
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:5f1227f7c1114b9b8aea7aff6a12191a
record_format dspace
spelling oai:doaj.org-article:5f1227f7c1114b9b8aea7aff6a12191a2021-12-02T13:34:57ZWorkflow towards automated segmentation of agglomerated, non-spherical particles from electron microscopy images using artificial neural networks10.1038/s41598-021-84287-62045-2322https://doaj.org/article/5f1227f7c1114b9b8aea7aff6a12191a2021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-84287-6https://doaj.org/toc/2045-2322Abstract We present a workflow for obtaining fully trained artificial neural networks that can perform automatic particle segmentations of agglomerated, non-spherical nanoparticles from scanning electron microscopy images “from scratch”, without the need for large training data sets of manually annotated images. The whole process only requires about 15 min of hands-on time by a user and can typically be finished within less than 12 h when training on a single graphics card (GPU). After training, SEM image analysis can be carried out by the artificial neural network within seconds. This is achieved by using unsupervised learning for most of the training dataset generation, making heavy use of generative adversarial networks and especially unpaired image-to-image translation via cycle-consistent adversarial networks. We compare the segmentation masks obtained with our suggested workflow qualitatively and quantitatively to state-of-the-art methods using various metrics. Finally, we used the segmentation masks for automatically extracting particle size distributions from the SEM images of TiO2 particles, which were in excellent agreement with particle size distributions obtained manually but could be obtained in a fraction of the time.Bastian RühleJulian Frederic KrumreyVasile-Dan HodoroabaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Bastian Rühle
Julian Frederic Krumrey
Vasile-Dan Hodoroaba
Workflow towards automated segmentation of agglomerated, non-spherical particles from electron microscopy images using artificial neural networks
description Abstract We present a workflow for obtaining fully trained artificial neural networks that can perform automatic particle segmentations of agglomerated, non-spherical nanoparticles from scanning electron microscopy images “from scratch”, without the need for large training data sets of manually annotated images. The whole process only requires about 15 min of hands-on time by a user and can typically be finished within less than 12 h when training on a single graphics card (GPU). After training, SEM image analysis can be carried out by the artificial neural network within seconds. This is achieved by using unsupervised learning for most of the training dataset generation, making heavy use of generative adversarial networks and especially unpaired image-to-image translation via cycle-consistent adversarial networks. We compare the segmentation masks obtained with our suggested workflow qualitatively and quantitatively to state-of-the-art methods using various metrics. Finally, we used the segmentation masks for automatically extracting particle size distributions from the SEM images of TiO2 particles, which were in excellent agreement with particle size distributions obtained manually but could be obtained in a fraction of the time.
format article
author Bastian Rühle
Julian Frederic Krumrey
Vasile-Dan Hodoroaba
author_facet Bastian Rühle
Julian Frederic Krumrey
Vasile-Dan Hodoroaba
author_sort Bastian Rühle
title Workflow towards automated segmentation of agglomerated, non-spherical particles from electron microscopy images using artificial neural networks
title_short Workflow towards automated segmentation of agglomerated, non-spherical particles from electron microscopy images using artificial neural networks
title_full Workflow towards automated segmentation of agglomerated, non-spherical particles from electron microscopy images using artificial neural networks
title_fullStr Workflow towards automated segmentation of agglomerated, non-spherical particles from electron microscopy images using artificial neural networks
title_full_unstemmed Workflow towards automated segmentation of agglomerated, non-spherical particles from electron microscopy images using artificial neural networks
title_sort workflow towards automated segmentation of agglomerated, non-spherical particles from electron microscopy images using artificial neural networks
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/5f1227f7c1114b9b8aea7aff6a12191a
work_keys_str_mv AT bastianruhle workflowtowardsautomatedsegmentationofagglomeratednonsphericalparticlesfromelectronmicroscopyimagesusingartificialneuralnetworks
AT julianfrederickrumrey workflowtowardsautomatedsegmentationofagglomeratednonsphericalparticlesfromelectronmicroscopyimagesusingartificialneuralnetworks
AT vasiledanhodoroaba workflowtowardsautomatedsegmentationofagglomeratednonsphericalparticlesfromelectronmicroscopyimagesusingartificialneuralnetworks
_version_ 1718392738803613696