Search research articles

Related Concept Videos

Preparation of Samples for Electron Microscopy

Preparation of Samples for Electron Microscopy

To be visualized by an electron microscope, either transmission or scanning, biological samples need to be fixed (stabilized) so the electron beam does not destroy them and dried thoroughly (desiccated/dehydrated) so the vacuum does not affect them. Fixation needs to be done as quickly as possible because the sample properties will start changing as soon as it is removed from its natural environment. For example, in a tissue sample, the oxygen levels begin decreasing, causing an altered...

You might also read

Related Articles

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

Sort by

Same author

Interpretable deep learning-based hippocampal sclerosis classification.

Epilepsia open·2022

Same journal

Lingual Surface Morphology in Delphinids: Structural Adaptations to Feeding Strategies.

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

Same journal

A Scalable Pathway for Plan-View TEM of 2D Materials and Surface Layers.

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

Same journal

Unsupervised Segmentation and Clustering Workflow for Efficient Processing of 4D-STEM and 5D-STEM Data.

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

Same journal

Development of an EDS-Based Grain Segmentation Method for MIMAS-MOX Nuclear Fuels.

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

Same journal

The Fabrication of Atom Probe Tomography Specimens From Mineral Nanoplates by Focused Ion Beam Redeposition.

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

Same journal

From Bone to Body: Qualitative Evaluation of Collagenous Tissues Using JFRL Staining in Normal and Pathological Conditions.

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

See all related 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

Search research articles

Related Experiment Video

Updated: Jan 14, 2026

Comprehensive Characterization of Extended Defects in Semiconductor Materials by a Scanning Electron Microscope

Comprehensive Characterization of Extended Defects in Semiconductor Materials by a Scanning Electron Microscope

Published on: May 28, 2016

Efficient and Robust SEM Image Denoising for Wafer Defect Inspection.

Hyunwoong Bae¹, Jaeseok Byun², Yongwoo Lee³

¹Interdisciplinary Program in Artificial Intelligence, Seoul National University, Gwanak-ro, South Seoul 08826, Korea.

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

|October 23, 2025

Summary

This summary is machine-generated.

We developed Relaxed Noise2Noise with Input dropout (ReNIn) for scanning electron microscopy (SEM) denoising. ReNIn offers efficient training and improved generalization for wafer defect inspection.

Keywords:

SEM deep learning denoising denoising for inspection

More Related Videos

Use of Sacrificial Nanoparticles to Remove the Effects of Shot-noise in Contact Holes Fabricated by E-beam Lithography

Use of Sacrificial Nanoparticles to Remove the Effects of Shot-noise in Contact Holes Fabricated by E-beam Lithography

Published on: February 12, 2017

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

Related Experiment Videos

Last Updated: Jan 14, 2026

Comprehensive Characterization of Extended Defects in Semiconductor Materials by a Scanning Electron Microscope

Comprehensive Characterization of Extended Defects in Semiconductor Materials by a Scanning Electron Microscope

Published on: May 28, 2016

Use of Sacrificial Nanoparticles to Remove the Effects of Shot-noise in Contact Holes Fabricated by E-beam Lithography

Use of Sacrificial Nanoparticles to Remove the Effects of Shot-noise in Contact Holes Fabricated by E-beam Lithography

Published on: February 12, 2017

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

Area of Science:

Materials Science
Computer Science
Image Processing

Background:

Scanning electron microscopy (SEM) noise hinders accurate wafer defect inspection.
Current deep learning denoising methods for SEM suffer from inefficiency and poor generalization to novel image structures.

Purpose of the Study:

To introduce an efficient and robust deep learning-based denoising method for SEM images.
To enhance the generalization capability of denoising models for unseen image structures.
To improve downstream wafer inspection tasks, such as circle detection.

Main Methods:

Proposed Relaxed Noise2Noise (ReNIn) framework combining a relaxed noise2noise approach with input dropout.
Relaxed Noise2Noise component optimizes the trade-off between denoising performance and data collection cost.
Input dropout technique enhances model generalization to diverse image structures.

Main Results:

ReNIn achieves competitive denoising performance with significantly reduced training data collection costs compared to supervised methods.
Input dropout improves performance on structurally novel images without degrading performance on familiar structures.
The method enhances circle detection accuracy in downstream inspection tasks.

Conclusions:

ReNIn offers an efficient solution for SEM image denoising, balancing performance and data acquisition costs.
The proposed method demonstrates superior generalization capabilities for SEM image analysis.
ReNIn effectively supports critical wafer inspection processes by improving defect detection accuracy.