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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Heterogeneous catalysts possess complex surface and bulk structures,relatively poor intrinsic contrast, and often a sparse distribution of thecatalytic nanoparticles (NPs), posing a significant challenge for imagesegmentation, including the current state-of-the-art deep learning methods. Totackle this problem, we apply a deep learning-based approach for themulti-class semantic segmentation of a $\gamma$-Alumina/Pt catalytic materialin a class imbalance situation. Specifically, we used the weighted focal lossas a loss function and attached it to the U-Net's fully convolutional networkarchitecture. We assessed the accuracy of our results using Dice similaritycoefficient (DSC), recall, precision, and Hausdorff distance (HD) metrics onthe overlap between the ground-truth and predicted segmentations. Our adoptedU-Net model with the weighted focal loss function achieved an average DSC scoreof 0.96 $\pm$ 0.003 in the $\gamma$-Alumina support material and 0.84 $\pm$0.03 in the Pt NPs segmentation tasks. We report an average boundary-overlaperror of less than 2 nm at the 90th percentile of HD for $\gamma$-Alumina andPt NPs segmentations. The complex surface morphology of the $\gamma$-Aluminaand its relation to the Pt NPs were visualized in 3D by the deeplearning-assisted automatic segmentation of a large data set of high-angleannular dark-field (HAADF) scanning transmission electron microscopy (STEM)tomography reconstructions.

A Deep Learning Approach for Semantic Segmentation of Unbalanced Data in Electron Tomography of Catalytic Materials