Zitieren Sie bitte immer diese URN: urn:nbn:de:kobv:b43-522454

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

  • 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 minutes of hands-on time by a user and can typically be finished within less than 12 hours 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 usedWe 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 minutes of hands-on time by a user and can typically be finished within less than 12 hours 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.zeige mehrzeige weniger

Volltext Dateien herunterladen

Metadaten exportieren

Weitere Dienste

Teilen auf Twitter Suche bei Google Scholar
Metadaten
Autoren/innen:Bastian Rühle, Julian Frederic Krumrey, Vasile-Dan HodoroabaORCiD
Dokumenttyp:Zeitschriftenartikel
Veröffentlichungsform:Verlagsliteratur
Sprache:Englisch
Titel des übergeordneten Werkes (Englisch):Scientific reports
Jahr der Erstveröffentlichung:2021
Organisationseinheit der BAM:1 Analytische Chemie; Referenzmaterialien
1 Analytische Chemie; Referenzmaterialien / 1.2 Biophotonik
6 Materialchemie
6 Materialchemie / 6.1 Oberflächenanalytik und Grenzflächenchemie
Veröffentlichende Institution:Bundesanstalt für Materialforschung und -prüfung (BAM)
Verlag:Springer Nature
Jahrgang/Band:11
Ausgabe/Heft:1
Erste Seite:4942
DDC-Klassifikation:Naturwissenschaften und Mathematik / Chemie / Analytische Chemie
Technik, Medizin, angewandte Wissenschaften / Ingenieurwissenschaften / Ingenieurwissenschaften und zugeordnete Tätigkeiten
Freie Schlagwörter:Artificial intelligence; Automated image analysis; Electron microscopy; Image segmentation; Neural networks
Themenfelder/Aktivitätsfelder der BAM:Material
Analytical Sciences
Analytical Sciences / Qualitätssicherung und Data Science
Material / Nano@BAM
DOI:https://doi.org/10.1038/s41598-021-84287-6
URN:urn:nbn:de:kobv:b43-522454
Zugehöriger Identifikator:https://opus4.kobv.de/opus4-bam/frontdoor/index/index/docId/52246
Zugehöriger Identifikator:https://github.com/BAMresearch/automatic-sem-image-segmentation
Verfügbarkeit des Dokuments:Datei für die Öffentlichkeit verfügbar ("Open Access")
Lizenz (Deutsch):License LogoCreative Commons - CC BY - Namensnennung 4.0 International
Datum der Freischaltung:11.03.2021
Referierte Publikation:Ja
Datum der Eintragung als referierte Publikation:11.03.2021
Schriftenreihen ohne Nummerierung:Wissenschaftliche Artikel der BAM