• Home
  • Search
  • Patch-Based convolutional neural networks for multiple microstructural features detection in FIB-SEM micrographs of irradiated nuclear fuel.
  • https://doi.org/10.1038/s41598-025-23606-7Copy DOI Icon

Patch-Based convolutional neural networks for multiple microstructural features detection in FIB-SEM micrographs of irradiated nuclear fuel.

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Focused ion beam scanning electron microscopy (FIB-SEM) tomography has increasingly been utilized for acquiring three-dimensional (3D) microstructure features at the sub-micron scale in irradiated nuclear materials. This technique involves sequential ion beam slicing followed by electron beam imaging and compositional mapping using energy dispersive spectroscopy (EDS). Despite its growing use, several challenges persist. These include the time-intensive nature of data collection of EDS data, difficulties in distinguishing between various microstructures, and issues with image alignment. These challenges currently limit the broader application of FIB-SEM tomography in the field. To overcome these limitations, we propose using convolutional neural networks (CNNs) to automate microstructure identification in SEM images. Our study introduces a new framework for identifying microstructures in irradiated U-10Zr (wt%) metallic fuel with limited annotated data. The framework includes the creation of a reliable annotated dataset with paired SEM and ground truth data from EDS maps, the applications of CNNs for microstructure identification, and the validation of model performance. Specifically, we employed the Segment Anything Model (SAM) to align SEM images with corresponding EDS maps and focused ion beam (FIB) tomography SEM data. We evaluate several models, including Patch-based U-Net, Attention U-Net, and Residual U-Net, finding that patch-based U-Net exhibits superior segmentation performance and consistency. This approach reduces reliance on EDS detectors and aids in accelerating nuclear material analysis process, highlighting the potential of advanced deep learning techniques to improve microstructural understanding in nuclear material. This is the first framework to integrate SAM and Patch-based CNN models for semantic segmentation of irradiated nuclear materials, with potential applicability to other tomography datasets.

Similar Papers
  • Research Article
  • Citations2

Unsupervised Generative Adversarial Network for 3-D Microstructure Synthesis from 2-D Image

  • Jul 23, 2021
  • Electrochemical Society Meeting Abstracts
  • Anna Sciazko +2
  • PDF
  • Research Article
  • Citations10

Three-Dimensional Visualization of APEX2-Tagged Erg11 in Saccharomyces cerevisiae Using Focused Ion Beam Scanning Electron Microscopy.

  • Feb 05, 2020
  • mSphere
  • Winnie Kerstens +5
  • Research Article
  • Citations8

Volumetric 3D reconstruction of plant leaf cells using SEM, ion milling, TEM, and serial sectioning.

  • May 06, 2022
  • Planta
  • Bernd Zechmann +2
  • PDF
  • Research Article
  • Citations61

AMST: Alignment to Median Smoothed Template for Focused Ion Beam Scanning Electron Microscopy Image Stacks

  • Feb 06, 2020
  • Scientific Reports
  • Julian Hennies +5
  • Book Chapter
  • Citations49

3D Imaging of Cells and Tissues by Focused Ion Beam/Scanning Electron Microscopy (FIB/SEM)

  • Sep 18, 2012
  • Damjana Drobne
  • Research Article
  • Citations8

Comparison of X-ray Nanotomography and FIB-SEM in Quantifying the Composite LSM/YSZ SOFC Cathode Microstructure

  • Apr 25, 2011
  • Electrochemical Society Transactions
  • George Nelson +12
  • Research Article
  • Citations1

Identification of solid phase speciation of trace elements in dust dry deposition using focused ion beam and selected area electron diffraction

  • Jun 07, 2024
  • Journal of Trace Elements and Minerals
  • Pyeong-Koo Lee +1
  • PDF
  • Research Article
  • Citations1

Relationship between Reflectivity, Chemical Composition and Mechanical Behaviour of Orthodontic Bonding Nanofiller Resin Materials: A Proposal of an Alternative Method of Investigation

  • Dec 07, 2022
  • Applied Sciences
  • Roberta Condò +12
  • Research Article

Application of Advanced Microscopy Techniques to the Characterization of Mixed Matrix Membranes.

  • Nov 13, 2024
  • Chemistry (Weinheim an der Bergstrasse, Germany)
  • Daria Poloneeva +1
  • Research Article
  • Citations32

Improving the electrochemical performances of Li-rich Li1.2Ni0.13Co0.13Mn0.54O2 through cooperative doping of Na+ and Mg2+

  • Mar 07, 2022
  • Electrochimica Acta
  • Yanxia Sun +9
  • Research Article
  • Citations13

Focused ion beam-scanning electron microscopy provides novel insights of drug delivery phenomena

  • Jan 05, 2024
  • Journal of Controlled Release
  • Thilo Faber +2
  • PDF
  • Research Article
  • Citations72

Mapping the Complex Morphology of Cell Interactions with Nanowire Substrates Using FIB-SEM

  • Jan 09, 2013
  • PLoS ONE
  • Rafał Wierzbicki +8
  • Research Article
  • Citations46

Rapid screening of Zr-containing particles from Chang’e-5 lunar soil samples for isotope geochronology: Technical roadmap for future study

  • Jan 28, 2022
  • Geoscience Frontiers
  • Jin-Hua Li +18
  • Research Article
  • Citations17

Biological Sample Preparation by High-pressure Freezing, Microwave-assisted Contrast Enhancement, and Minimal Resin Embedding for Volume Imaging.

  • Mar 19, 2019
  • Journal of Visualized Experiments
  • Anna M Steyer +2
  • Research Article

Volume Electron Microscopy: Imaging Principles, Computational Advances and Applications in Multi-Scale Biological System

  • Dec 24, 2025
  • Crystals
  • Bowen Shi +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.