Gambini, Laura and Mullarkey, Tiarnan and Jones, Lewys and Sanvito, Stefano (2023) Machine-learning approach for quantified resolvability enhancement of low-dose STEM data. Machine Learning: Science and Technology, 4 (1). 015025. ISSN 2632-2153
![[thumbnail of Gambini_2023_Mach._Learn.__Sci._Technol._4_015025.pdf]](http://ebooks.pubstmlibrary.com/style/images/fileicons/text.png)
Gambini_2023_Mach._Learn.__Sci._Technol._4_015025.pdf - Published Version
Download (3MB)
Abstract
High-resolution electron microscopy is achievable only when a high electron dose is employed, a practice that may cause damage to the specimen and, in general, affects the observation. This drawback sets some limitations on the range of applications of high-resolution electron microscopy. Our work proposes a strategy, based on machine learning, which enables a significant improvement in the quality of Scanning Transmission Electron Microscope images generated at low electron dose, strongly affected by Poisson noise. In particular, we develop an autoencoder, trained on a large database of images, which is thoroughly tested on both synthetic and actual microscopy data. The algorithm is demonstrated to drastically reduce the noise level and approach ground-truth precision over a broad range of electron beam intensities. Importantly, it does not require human data pre-processing or the explicit knowledge of the dose level employed and can run at a speed compatible with live data acquisition. Furthermore, a quantitative unbiased benchmarking protocol is proposed to compare different denoising workflows.
Item Type: | Article |
---|---|
Subjects: | ArticleGate > Multidisciplinary |
Depositing User: | Managing Editor |
Date Deposited: | 17 Jul 2023 05:23 |
Last Modified: | 03 Jun 2024 12:29 |
URI: | http://ebooks.pubstmlibrary.com/id/eprint/3128 |