Search research articles

Search research articles

Related Experiment Video

Updated: Feb 20, 2026

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Neural Network for Nanoscience Scanning Electron Microscope Image Recognition.

Mohammad Hadi Modarres¹, Rossella Aversa², Stefano Cozzini^3,4

¹Institute for Manufacturing, Department of Engineering, University of Cambridge, 17 Charles Babbage Road, Cambridge, CB3 0FS, United Kingdom.

Scientific Reports

|October 18, 2017

Summary

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

Scalable, fast and accurate differential gene expression testing from millions of cells of multiple patients.

Nature communications·2026

Same author

Tuning the Selectivity of Methanol Decomposition to Syngas Exploiting the Surface Stability of Ni<sub>3</sub>Sn<sub>2</sub> Intermetallic Compounds.

ACS applied energy materials·2026

Same author

Stable n‑Type Conduction in WO <sub><i>x</i></sub> ‑CNT Hybrid Films.

ACS applied electronic materials·2025

Same author

Towards Health Status Determination and Local Weather Forecasts from <i>Vitis vinifera</i> Electrome.

Biomimetics (Basel, Switzerland)·2025

Same author

Strain-driven oxygen vacancy ordering in LaNiO<sub>3</sub> thin films revealed by integrated differential phase contrast imaging in scanning transmission electron microscopy.

Physical chemistry chemical physics : PCCP·2025

Same author

Optimization of In-Situ Growth of Superconducting Al/InAs Hybrid Systems on GaAs for the Development of Quantum Electronic Circuits.

Materials (Basel, Switzerland)·2025

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

This summary is machine-generated.

Transfer learning accurately classifies over 90% of scanning electron microscope (SEM) images in nanoscience. This deep learning approach enables automatic categorization and labeling of nano-images, aiding future research.

Area of Science:

Nanoscience and Materials Science
Computer Vision
Machine Learning

Background:

Automated analysis of Scanning Electron Microscope (SEM) images is crucial for nanoscience research.
Manual classification of large SEM datasets is time-consuming and prone to human error.
Deep learning offers potential for efficient and accurate image analysis in this domain.

Purpose of the Study:

To apply transfer learning techniques for automated image recognition, categorization, and labeling of SEM images.
To develop and compare convolutional neural network (CNN) models for nanoscience image analysis.
To create a semi-automatic workflow for classifying and labeling SEM-generated images.

Main Methods:

A dataset of approximately 20,000 SEM images was manually classified into 10 categories (0D, 1D, 2D, 3D nanostructures).

More Related Videos

Automated Analysis of C. elegans Fluorescence Images using SegElegans

Automated Analysis of C. elegans Fluorescence Images using SegElegans

Published on: October 10, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Related Experiment Videos

Last Updated: Feb 20, 2026

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Automated Analysis of C. elegans Fluorescence Images using SegElegans

Automated Analysis of C. elegans Fluorescence Images using SegElegans

Published on: October 10, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Transfer learning was employed to retrain CNN models (Inception-v3, Inception-v4, ResNet) on the SEM dataset.

Feature extraction and statistical analysis were performed on a separate test set to evaluate classifier performance.

Main Results:

The developed algorithm achieved approximately 90% accuracy in classifying SEM images.
Reduced accuracy was observed for images at category boundaries or containing multiple elements.
A semi-automatic workflow for image classification and labeling was successfully deployed.
A separate training successfully determined the volume fraction of aligned nanowires, comparable to the Local Gradient Orientation method.

Conclusions:

Transfer learning is a versatile and effective approach for automated image analysis in nanoscience.
Deep learning models can significantly enhance the efficiency and accuracy of SEM image categorization and labeling.
The developed methods show potential for various specific tasks in nanoscience applications, including quantitative analysis.