Cargando…

Enhancing the signal-to-noise ratio and generating contrast for cryo-EM images with convolutional neural networks

In cryogenic electron microscopy (cryo-EM) of radiation-sensitive biological samples, both the signal-to-noise ratio (SNR) and the contrast of images are critically important in the image-processing pipeline. Classic methods improve low-frequency image contrast experimentally, by imaging with high d...

Descripción completa

Detalles Bibliográficos
Autores principales: Palovcak, Eugene, Asarnow, Daniel, Campbell, Melody G., Yu, Zanlin, Cheng, Yifan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: International Union of Crystallography 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7642784/
https://www.ncbi.nlm.nih.gov/pubmed/33209325
http://dx.doi.org/10.1107/S2052252520013184
_version_ 1783606151125925888
author Palovcak, Eugene
Asarnow, Daniel
Campbell, Melody G.
Yu, Zanlin
Cheng, Yifan
author_facet Palovcak, Eugene
Asarnow, Daniel
Campbell, Melody G.
Yu, Zanlin
Cheng, Yifan
author_sort Palovcak, Eugene
collection PubMed
description In cryogenic electron microscopy (cryo-EM) of radiation-sensitive biological samples, both the signal-to-noise ratio (SNR) and the contrast of images are critically important in the image-processing pipeline. Classic methods improve low-frequency image contrast experimentally, by imaging with high defocus, or computationally, by applying various types of low-pass filter. These contrast improvements typically come at the expense of the high-frequency SNR, which is suppressed by high-defocus imaging and removed by low-pass filtration. Recently, convolutional neural networks (CNNs) trained to denoise cryo-EM images have produced impressive gains in image contrast, but it is not clear how these algorithms affect the information content of the image. Here, a denoising CNN for cryo-EM images was implemented and a quantitative evaluation of SNR enhancement, induced bias and the effects of denoising on image processing and three-dimensional reconstructions was performed. The study suggests that besides improving the visual contrast of cryo-EM images, the enhanced SNR of denoised images may be used in other parts of the image-processing pipeline, such as classification and 3D alignment. These results lay the groundwork for the use of denoising CNNs in the cryo-EM image-processing pipeline beyond particle picking.
format Online
Article
Text
id pubmed-7642784
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher International Union of Crystallography
record_format MEDLINE/PubMed
spelling pubmed-76427842020-11-17 Enhancing the signal-to-noise ratio and generating contrast for cryo-EM images with convolutional neural networks Palovcak, Eugene Asarnow, Daniel Campbell, Melody G. Yu, Zanlin Cheng, Yifan IUCrJ Research Papers In cryogenic electron microscopy (cryo-EM) of radiation-sensitive biological samples, both the signal-to-noise ratio (SNR) and the contrast of images are critically important in the image-processing pipeline. Classic methods improve low-frequency image contrast experimentally, by imaging with high defocus, or computationally, by applying various types of low-pass filter. These contrast improvements typically come at the expense of the high-frequency SNR, which is suppressed by high-defocus imaging and removed by low-pass filtration. Recently, convolutional neural networks (CNNs) trained to denoise cryo-EM images have produced impressive gains in image contrast, but it is not clear how these algorithms affect the information content of the image. Here, a denoising CNN for cryo-EM images was implemented and a quantitative evaluation of SNR enhancement, induced bias and the effects of denoising on image processing and three-dimensional reconstructions was performed. The study suggests that besides improving the visual contrast of cryo-EM images, the enhanced SNR of denoised images may be used in other parts of the image-processing pipeline, such as classification and 3D alignment. These results lay the groundwork for the use of denoising CNNs in the cryo-EM image-processing pipeline beyond particle picking. International Union of Crystallography 2020-10-24 /pmc/articles/PMC7642784/ /pubmed/33209325 http://dx.doi.org/10.1107/S2052252520013184 Text en © Eugene Palovcak et al. 2020 http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution (CC-BY) Licence, which permits unrestricted use, distribution, and reproduction in any medium, provided the original authors and source are cited.http://creativecommons.org/licenses/by/4.0/
spellingShingle Research Papers
Palovcak, Eugene
Asarnow, Daniel
Campbell, Melody G.
Yu, Zanlin
Cheng, Yifan
Enhancing the signal-to-noise ratio and generating contrast for cryo-EM images with convolutional neural networks
title Enhancing the signal-to-noise ratio and generating contrast for cryo-EM images with convolutional neural networks
title_full Enhancing the signal-to-noise ratio and generating contrast for cryo-EM images with convolutional neural networks
title_fullStr Enhancing the signal-to-noise ratio and generating contrast for cryo-EM images with convolutional neural networks
title_full_unstemmed Enhancing the signal-to-noise ratio and generating contrast for cryo-EM images with convolutional neural networks
title_short Enhancing the signal-to-noise ratio and generating contrast for cryo-EM images with convolutional neural networks
title_sort enhancing the signal-to-noise ratio and generating contrast for cryo-em images with convolutional neural networks
topic Research Papers
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7642784/
https://www.ncbi.nlm.nih.gov/pubmed/33209325
http://dx.doi.org/10.1107/S2052252520013184
work_keys_str_mv AT palovcakeugene enhancingthesignaltonoiseratioandgeneratingcontrastforcryoemimageswithconvolutionalneuralnetworks
AT asarnowdaniel enhancingthesignaltonoiseratioandgeneratingcontrastforcryoemimageswithconvolutionalneuralnetworks
AT campbellmelodyg enhancingthesignaltonoiseratioandgeneratingcontrastforcryoemimageswithconvolutionalneuralnetworks
AT yuzanlin enhancingthesignaltonoiseratioandgeneratingcontrastforcryoemimageswithconvolutionalneuralnetworks
AT chengyifan enhancingthesignaltonoiseratioandgeneratingcontrastforcryoemimageswithconvolutionalneuralnetworks