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

Circadian disruption and cellular senescence: emerging perspectives in periodontitis.

Odontology·2026

Same author

Responses of soil labile organic carbon fractions and enzyme activity in Kubuqi Desert to different vegetation restoration measures.

Frontiers in plant science·2026

Same author

Integrative biomarker and drug target discovery in osteosarcoma: traditional experimental approaches and AI-enabled insights.

Frontiers in pharmacology·2026

Same author

Development of Quinoline-Amido and Hydrogenated Quinoline-Imino Hafnium Complexes and Their Olefin Polymerizations.

Inorganic chemistry·2026

Same author

Cross-trait genetic enrichment between GERD and psychiatric disorders in East Asian populations.

Frontiers in genetics·2026

Same author

A Tri-Factor Adaptive Federated Learning Framework for Parkinson's Disease Diagnosis via Multi-Source Facial Expression Analysis.

IEEE journal of biomedical and health informatics·2025

Search research articles

Related Experiment Video

Updated: Jan 10, 2026

Atom Probe Tomography Studies on the CuIn,GaSe2 Grain Boundaries

Atom Probe Tomography Studies on the CuIn,GaSe2 Grain Boundaries

Published on: April 22, 2013

Automated grain analysis via data augmentation and grain boundary detection.

Zhihao Gao¹, Yintao Zhou²

¹School of Jiluan Academy, Nanchang University, Nanchang, 330031, China.

Micron (Oxford, England : 1993)

|November 25, 2025

Summary

This study introduces an AI framework for quantitative metallographic analysis of pure iron. It overcomes data scarcity and manual analysis limitations using advanced data synthesis and deep learning for accurate grain size characterization.

Keywords:

Automated grain analysis Boundary detection Data augmentation Deep learning

More Related Videos

Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography

Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography

Published on: September 29, 2019

Untargeted Liquid Chromatography-Mass Spectrometry-Based Metabolomics Analysis of Wheat Grain

Untargeted Liquid Chromatography-Mass Spectrometry-Based Metabolomics Analysis of Wheat Grain

Published on: March 13, 2020

Related Experiment Videos

Last Updated: Jan 10, 2026

Atom Probe Tomography Studies on the CuIn,GaSe2 Grain Boundaries

Atom Probe Tomography Studies on the CuIn,GaSe2 Grain Boundaries

Published on: April 22, 2013

Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography

Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography

Published on: September 29, 2019

Untargeted Liquid Chromatography-Mass Spectrometry-Based Metabolomics Analysis of Wheat Grain

Untargeted Liquid Chromatography-Mass Spectrometry-Based Metabolomics Analysis of Wheat Grain

Published on: March 13, 2020

Area of Science:

Materials Science
Artificial Intelligence
Computational Methods

Background:

Manual grain size analysis in pure iron is inefficient and lacks reproducibility.
Existing computational methods struggle with limited data and incomplete grain boundary detection.

Purpose of the Study:

To develop an AI-enhanced framework for quantitative metallographic analysis of pure iron.
To address challenges of data scarcity and subjectivity in current methods.

Main Methods:

A three-stage data synthesis pipeline using denoising diffusion probabilistic models (DDPM) and conditional adversarial networks.
Training a U-Net based deep neural network on a paired and reconstructed dataset for topology-aware analysis.
Establishing an automated grain analysis system with whole-grain area quantification and twin-grain merging.

Main Results:

Generated physically consistent metallographic images through advanced data synthesis.
Achieved topology-awareness in grain analysis via data pairing and reconstruction objectives.
Developed a fully automated system resolving limitations in data scarcity and manual evaluation subjectivity.

Conclusions:

The AI-enhanced framework significantly improves quantitative metallographic analysis of pure iron.
The methodology offers a robust solution for data scarcity and subjectivity issues.
Enables more efficient and reproducible grain size characterization.