Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Relaxing Direct Ptychography Sampling Requirements via Parallax Imaging Insights.

Microscopy and microanalysis : the official journal of Microscopy Society of America, Microbeam Analysis Society, Microscopical Society of Canada·2026

Same author

Beyond Contrast Transfer: Spectral SNR as a Finite-Dose Metric for STEM Phase Retrieval.

Microscopy and microanalysis : the official journal of Microscopy Society of America, Microbeam Analysis Society, Microscopical Society of Canada·2026

Same author

Ultrathin Amorphous <i>p</i>-Type Tellurium Oxide Films Enabled by Cryogenic Deposition.

ACS nano·2026

Same author

Patterned, Low-Temperature Growth of Transition Metal Dichalcogenides for Low Resistance Raised Contacts.

ACS nano·2026

Same author

Expanding carrier screening: beyond the genes, to include underrepresented ancestries.

NPJ genomic medicine·2025

Same author

PhaseT3M: 3D imaging at 1.6 Å resolution via electron cryo-tomography with nonlinear phase retrieval.

Nature communications·2025

Search research articles

Related Experiment Video

Updated: Nov 6, 2025

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Machine Learning Pipeline for Segmentation and Defect Identification from High-Resolution Transmission Electron

Catherine K Groschner¹, Christina Choi¹, Mary C Scott^1,2

¹Department of Materials Science and Engineering, University of California Berkeley, Berkeley, CA94720, USA.

Microscopy and Microanalysis : the Official Journal of Microscopy Society of America, Microbeam Analysis Society, Microscopical Society of Canada

|May 6, 2021

Summary

This summary is machine-generated.

Machine learning accelerates transmission electron microscopy (TEM) data analysis. A new U-Net and random forest pipeline accurately segments nanoparticles and detects stacking faults, outperforming traditional methods.

Keywords:

HRTEM automated analysis deep learning segmentation structure classification

More Related Videos

Author Spotlight: A Machine-Vision Approach to Transmission Electron Microscopy Workflows, Results Analysis and Data Management

Author Spotlight: A Machine-Vision Approach to Transmission Electron Microscopy Workflows, Results Analysis and Data Management

Published on: June 23, 2023

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Related Experiment Videos

Last Updated: Nov 6, 2025

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Author Spotlight: A Machine-Vision Approach to Transmission Electron Microscopy Workflows, Results Analysis and Data Management

Author Spotlight: A Machine-Vision Approach to Transmission Electron Microscopy Workflows, Results Analysis and Data Management

Published on: June 23, 2023

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Area of Science:

Materials Science
Data Science
Microscopy

Background:

Transmission electron microscopy (TEM) data interpretation is often a bottleneck, requiring manual image processing tailored to specific datasets.
Machine learning (ML) presents a powerful solution for accelerating and improving the accuracy of TEM data analysis.

Purpose of the Study:

To develop and present a flexible, two-step machine learning pipeline for analyzing high-resolution TEM data.
To automate the segmentation of nanoparticle regions and the detection of stacking faults within these regions.

Main Methods:

A U-Net convolutional neural network was employed for segmenting nanoparticle regions from amorphous backgrounds.
A random forest classifier was subsequently used to detect the presence of stacking faults in the segmented nanoparticle regions.

Main Results:

The U-Net achieved a Dice coefficient of 0.8 for nanoparticle segmentation, surpassing traditional methods.
The random forest classifier accurately identified stacking faults in nanoparticles with 86% accuracy.
The pipeline provides statistical distributions of nanoparticle size, shape, and defect presence.

Conclusions:

This adaptable, open-source pipeline significantly enhances the efficiency and accuracy of TEM data analysis.
The tool enables the detection of correlations between nanoparticle characteristics and defect presence.
The developed method offers a valuable resource for the scientific community studying nanomaterials.