Computational Materials Science2022，Vol.2036.DOI:10.1016/j.commatsci.2021.111121

Design of a graphical user interface for few-shot machine learning classification of electron microscopy data

Doty, Christina Gallagher, Shaun Cui, Wenqi Chen, Wenya Bhushan, Shweta Oostrom, Marjolein Akers, Sarah Spurgeon, Steven R.
Computational Materials Science2022，Vol.2036.DOI:10.1016/j.commatsci.2021.111121
✕
  • NSTL
  • Elsevier

Design of a graphical user interface for few-shot machine learning classification of electron microscopy data

Doty, Christina 1Gallagher, Shaun 1Cui, Wenqi 1Chen, Wenya 1Bhushan, Shweta 1Oostrom, Marjolein 2Akers, Sarah 2Spurgeon, Steven R.2
扫码查看

作者信息

  • 1. Univ Washington
  • 2. Pacific Northwest Natl Lab
  • 折叠

Abstract

The recent growth in data volumes produced by modern electron microscopes requires rapid, scalable, and flexible approaches to image segmentation and analysis. Few-shot machine learning, which can richly classify images from a handful of user-provided examples, is a promising route to high-throughput analysis. However, current command-line implementations of such approaches can be slow and unintuitive to use, lacking the real-time feedback necessary to perform effective classification. Here we report on the development of a Python-based graphical user interface that enables end users to easily conduct and visualize the output of few-shot learning models. This interface is lightweight and can be hosted locally or on the web, providing the opportunity to reproducibly conduct, share, and crowd-source few-shot analyses.

Key words

Transmission electron microscopy/Machine learning/Sparse data analytics/Few-shot/Segmentation/Graphical user interface/REPRODUCIBILITY/DETECTOR

引用本文复制引用

出版年

2022
Computational Materials Science

Computational Materials Science

EISCI
ISSN：0927-0256
被引量4
参考文献量50
段落导航相关论文