Accurate segmentation of localized corrosion in structural alloys via deep learning

Abstract This study presents a deep learning-based approach for the automated segmentation of corrosion damage in scanning electron microscopy (SEM) images. The proposed method enables rapid and accurate segmentation of corrosion features in these SEM images, making it highly suitable for real-time...

Full description

Saved in:
Bibliographic Details
Main Authors: Liang Zhao, Jenifer Locke, Fei Xu, Tiankai Yao, Xiaolei Guo
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:npj Materials Degradation
Online Access:https://doi.org/10.1038/s41529-025-00633-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849402016741195776
author Liang Zhao
Jenifer Locke
Fei Xu
Tiankai Yao
Xiaolei Guo
author_facet Liang Zhao
Jenifer Locke
Fei Xu
Tiankai Yao
Xiaolei Guo
author_sort Liang Zhao
collection DOAJ
description Abstract This study presents a deep learning-based approach for the automated segmentation of corrosion damage in scanning electron microscopy (SEM) images. The proposed method enables rapid and accurate segmentation of corrosion features in these SEM images, making it highly suitable for real-time applications such as automated microscopy. Specifically, a dedicated corrosion segmentation database tailored for this task is constructed. The newly constructed dataset, alongside data from two public databases, are employed to jointly train a deep learning-based model modified with a texture refinement module. Compared to the same model without the texture refinement module, the refined model substantially enhances the efficacy and efficiency of corrosion segmentation. Furthermore, the methodology developed here is extendable to segmentation tasks for other materials with similar resolution, texture, and contrast characteristics, thereby paving the way for accelerated and automated analysis in corrosion science and beyond.
format Article
id doaj-art-c1968addf8a04a6a84c830c8c955f42a
institution Kabale University
issn 2397-2106
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series npj Materials Degradation
spelling doaj-art-c1968addf8a04a6a84c830c8c955f42a2025-08-20T03:37:38ZengNature Portfolionpj Materials Degradation2397-21062025-07-019111010.1038/s41529-025-00633-3Accurate segmentation of localized corrosion in structural alloys via deep learningLiang Zhao0Jenifer Locke1Fei Xu2Tiankai Yao3Xiaolei Guo4Idaho National LaboratoryDepartment of Materials Science and Engineering, The Ohio State UniversityIdaho National LaboratoryIdaho National LaboratoryDepartment of Metallurgical and Materials Engineering, Colorado School of MinesAbstract This study presents a deep learning-based approach for the automated segmentation of corrosion damage in scanning electron microscopy (SEM) images. The proposed method enables rapid and accurate segmentation of corrosion features in these SEM images, making it highly suitable for real-time applications such as automated microscopy. Specifically, a dedicated corrosion segmentation database tailored for this task is constructed. The newly constructed dataset, alongside data from two public databases, are employed to jointly train a deep learning-based model modified with a texture refinement module. Compared to the same model without the texture refinement module, the refined model substantially enhances the efficacy and efficiency of corrosion segmentation. Furthermore, the methodology developed here is extendable to segmentation tasks for other materials with similar resolution, texture, and contrast characteristics, thereby paving the way for accelerated and automated analysis in corrosion science and beyond.https://doi.org/10.1038/s41529-025-00633-3
spellingShingle Liang Zhao
Jenifer Locke
Fei Xu
Tiankai Yao
Xiaolei Guo
Accurate segmentation of localized corrosion in structural alloys via deep learning
npj Materials Degradation
title Accurate segmentation of localized corrosion in structural alloys via deep learning
title_full Accurate segmentation of localized corrosion in structural alloys via deep learning
title_fullStr Accurate segmentation of localized corrosion in structural alloys via deep learning
title_full_unstemmed Accurate segmentation of localized corrosion in structural alloys via deep learning
title_short Accurate segmentation of localized corrosion in structural alloys via deep learning
title_sort accurate segmentation of localized corrosion in structural alloys via deep learning
url https://doi.org/10.1038/s41529-025-00633-3
work_keys_str_mv AT liangzhao accuratesegmentationoflocalizedcorrosioninstructuralalloysviadeeplearning
AT jeniferlocke accuratesegmentationoflocalizedcorrosioninstructuralalloysviadeeplearning
AT feixu accuratesegmentationoflocalizedcorrosioninstructuralalloysviadeeplearning
AT tiankaiyao accuratesegmentationoflocalizedcorrosioninstructuralalloysviadeeplearning
AT xiaoleiguo accuratesegmentationoflocalizedcorrosioninstructuralalloysviadeeplearning