English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

A deep convolutional neural network has been developed to denoiseatomic-resolution TEM image datasets of nanoparticles acquired using directelectron counting detectors, for applications where the image signal isseverely limited by shot noise. The network was applied to a model system ofCeO2-supported Pt nanoparticles. We leverage multislice image simulations togenerate a large and flexible dataset for training and testing the network. Theproposed network outperforms state-of-the-art denoising methods by asignificant margin both on simulated and experimental test data. Factorscontributing to the performance are identified, including most importantly (a)the geometry of the images used during training and (b) the size of thenetwork's receptive field. Through a gradient-based analysis, we investigatethe mechanisms learned by the network to denoise experimental images. Thisshows that the network exploits global and local information in the noisymeasurements, for example, by adapting its filtering approach when itencounters atomic-level defects at the nanoparticle surface. Extensive analysishas been done to characterize the network's ability to correctly predict theexact atomic structure at the nanoparticle surface. Finally, we develop anapproach based on the log-likelihood ratio test that provides a quantitativemeasure of the agreement between the noisy observation and the atomic-levelstructure in the network-denoised image.

Developing and Evaluating Deep Neural Network-based Denoising for Nanoparticle TEM Images with Ultra-low Signal-to-Noise