Rapid and flexible segmentation of electron microscopy data using few-shot machine learning

Abstract Automatic segmentation of key microstructural features in atomic-scale electron microscope images is critical to improved understanding of structure–property relationships in many important materials and chemical systems. However, the present paradigm involves time-intensive manual analysis...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sarah Akers, Elizabeth Kautz, Andrea Trevino-Gavito, Matthew Olszta, Bethany E. Matthews, Le Wang, Yingge Du, Steven R. Spurgeon
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/33d1bedf318a45748896921c9d1f1190
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:33d1bedf318a45748896921c9d1f1190
record_format	dspace
spelling	oai:doaj.org-article:33d1bedf318a45748896921c9d1f11902021-11-21T12:13:28ZRapid and flexible segmentation of electron microscopy data using few-shot machine learning10.1038/s41524-021-00652-z2057-3960https://doaj.org/article/33d1bedf318a45748896921c9d1f11902021-11-01T00:00:00Zhttps://doi.org/10.1038/s41524-021-00652-zhttps://doaj.org/toc/2057-3960Abstract Automatic segmentation of key microstructural features in atomic-scale electron microscope images is critical to improved understanding of structure–property relationships in many important materials and chemical systems. However, the present paradigm involves time-intensive manual analysis that is inherently biased, error-prone, and unable to accommodate the large volumes of data produced by modern instrumentation. While more automated approaches have been proposed, many are not robust to a high variety of data, and do not generalize well to diverse microstructural features and material systems. Here, we present a flexible, semi-supervised few-shot machine learning approach for segmentation of scanning transmission electron microscopy images of three oxide material systems: (1) epitaxial heterostructures of SrTiO3/Ge, (2) La0.8Sr0.2FeO3 thin films, and (3) MoO3 nanoparticles. We demonstrate that the few-shot learning method is more robust against noise, more reconfigurable, and requires less data than conventional image analysis methods. This approach can enable rapid image classification and microstructural feature mapping needed for emerging high-throughput characterization and autonomous microscope platforms.Sarah AkersElizabeth KautzAndrea Trevino-GavitoMatthew OlsztaBethany E. MatthewsLe WangYingge DuSteven R. SpurgeonNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492Computer softwareQA76.75-76.765ENnpj Computational Materials, Vol 7, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
spellingShingle	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765 Sarah Akers Elizabeth Kautz Andrea Trevino-Gavito Matthew Olszta Bethany E. Matthews Le Wang Yingge Du Steven R. Spurgeon Rapid and flexible segmentation of electron microscopy data using few-shot machine learning
description	Abstract Automatic segmentation of key microstructural features in atomic-scale electron microscope images is critical to improved understanding of structure–property relationships in many important materials and chemical systems. However, the present paradigm involves time-intensive manual analysis that is inherently biased, error-prone, and unable to accommodate the large volumes of data produced by modern instrumentation. While more automated approaches have been proposed, many are not robust to a high variety of data, and do not generalize well to diverse microstructural features and material systems. Here, we present a flexible, semi-supervised few-shot machine learning approach for segmentation of scanning transmission electron microscopy images of three oxide material systems: (1) epitaxial heterostructures of SrTiO3/Ge, (2) La0.8Sr0.2FeO3 thin films, and (3) MoO3 nanoparticles. We demonstrate that the few-shot learning method is more robust against noise, more reconfigurable, and requires less data than conventional image analysis methods. This approach can enable rapid image classification and microstructural feature mapping needed for emerging high-throughput characterization and autonomous microscope platforms.
format	article
author	Sarah Akers Elizabeth Kautz Andrea Trevino-Gavito Matthew Olszta Bethany E. Matthews Le Wang Yingge Du Steven R. Spurgeon
author_facet	Sarah Akers Elizabeth Kautz Andrea Trevino-Gavito Matthew Olszta Bethany E. Matthews Le Wang Yingge Du Steven R. Spurgeon
author_sort	Sarah Akers
title	Rapid and flexible segmentation of electron microscopy data using few-shot machine learning
title_short	Rapid and flexible segmentation of electron microscopy data using few-shot machine learning
title_full	Rapid and flexible segmentation of electron microscopy data using few-shot machine learning
title_fullStr	Rapid and flexible segmentation of electron microscopy data using few-shot machine learning
title_full_unstemmed	Rapid and flexible segmentation of electron microscopy data using few-shot machine learning
title_sort	rapid and flexible segmentation of electron microscopy data using few-shot machine learning
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/33d1bedf318a45748896921c9d1f1190
work_keys_str_mv	AT sarahakers rapidandflexiblesegmentationofelectronmicroscopydatausingfewshotmachinelearning AT elizabethkautz rapidandflexiblesegmentationofelectronmicroscopydatausingfewshotmachinelearning AT andreatrevinogavito rapidandflexiblesegmentationofelectronmicroscopydatausingfewshotmachinelearning AT matthewolszta rapidandflexiblesegmentationofelectronmicroscopydatausingfewshotmachinelearning AT bethanyematthews rapidandflexiblesegmentationofelectronmicroscopydatausingfewshotmachinelearning AT lewang rapidandflexiblesegmentationofelectronmicroscopydatausingfewshotmachinelearning AT yinggedu rapidandflexiblesegmentationofelectronmicroscopydatausingfewshotmachinelearning AT stevenrspurgeon rapidandflexiblesegmentationofelectronmicroscopydatausingfewshotmachinelearning
_version_	1718419115982454784

Rapid and flexible segmentation of electron microscopy data using few-shot machine learning

Ejemplares similares