Deep learning-based noise filtering toward millisecond order imaging by using scanning transmission electron microscopy

Simple item page
dc.contributor.authorIhara, Shiroen
dc.contributor.authorSaito, Hikaruen
dc.contributor.authorYoshinaga, Mizumoen
dc.contributor.authorAvala, Lavakumaren
dc.contributor.authorMurayama, Mitsuhiroen
dc.date.accessioned2022-10-19T14:23:16Zen
dc.date.available2022-10-19T14:23:16Zen
dc.date.issued2022-08-05en
dc.description.abstractApplication of scanning transmission electron microscopy (STEM) to in situ observation will be essential in the current and emerging data-driven materials science by taking STEM's high affinity with various analytical options into account. As is well known, STEM's image acquisition time needs to be further shortened to capture a targeted phenomenon in real-time as STEM's current temporal resolution is far below the conventional TEM's. However, rapid image acquisition in the millisecond per frame or faster generally causes image distortion, poor electron signals, and unidirectional blurring, which are obstacles for realizing video-rate STEM observation. Here we show an image correction framework integrating deep learning (DL)-based denoising and image distortion correction schemes optimized for STEM rapid image acquisition. By comparing a series of distortion corrected rapid scan images with corresponding regular scan speed images, the trained DL network is shown to remove not only the statistical noise but also the unidirectional blurring. This result demonstrates that rapid as well as high-quality image acquisition by STEM without hardware modification can be established by the DL. The DL-based noise filter could be applied to in-situ observation, such as dislocation activities under external stimuli, with high spatio-temporal resolution.en
dc.description.notesThis work was supported by R3QR Program (Qdai-jump Research Program) 01271 and JSPS KAKENHI Grant Number (JP21K20491, JP20K21093), Iketani science and technology foundation, Pan Omics Data-Driven Research Innovation Center and Five star Alliance. M.M. greatly appreciates the financial support by the JST CREST (JPMJCR1994), JSPS KAKENHI Grant Numbers (JP19H02029, JP20H02479), Virginia Tech National Center for Earth and Environmental Nanotechnology Infrastructure (NanoEarth), a member of the National Nanotechnology Coordinated Infrastructure (NNCI), supported by NSF (ECCS 1542100 and 2025151).en
dc.description.sponsorshipR3QR Program (Qdai-jump Research Program) [01271]; JSPS KAKENHI [JP21K20491, JP20K21093, JP19H02029, JP20H02479]; Iketani science and technology foundation; Pan Omics Data-Driven Research Innovation Center; Five star Alliance; JST CREST [JPMJCR1994]; Virginia Tech National Center for Earth and Environmental Nanotechnology Infrastructure by NSF [ECCS 1542100, 2025151]en
dc.description.versionPublished versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.doihttps://doi.org/10.1038/s41598-022-17360-3en
dc.identifier.issn2045-2322en
dc.identifier.issue1en
dc.identifier.other13462en
dc.identifier.pmid35931705en
dc.identifier.urihttp://hdl.handle.net/10919/112200en
dc.identifier.volume12en
dc.language.isoenen
dc.publisherNature Portfolioen
dc.rightsCreative Commons Attribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectcontrasten
dc.subjectsegmentationen
dc.subjectholderen
dc.subjectangleen
dc.subjectstemen
dc.titleDeep learning-based noise filtering toward millisecond order imaging by using scanning transmission electron microscopyen
dc.title.serialScientific Reportsen
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
s41598-022-17360-3.pdf
Size:
2.61 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download

Collections

Scholarly Works, Materials Science and Engineering (MSE)