Dataset Open Access

Training Data and Models for the paper: Data-efficient U-Net for Segmentation of Carbide Microstructures in SEM Images of Steel Alloys

Chekhonin, Paul; Korten, Till; Gerçek, Alinda Ezgi; Hassan, Maleeha; Steinbach, Peter


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.14278/rodare.4124</identifier>
  <creators>
    <creator>
      <creatorName>Chekhonin, Paul</creatorName>
      <givenName>Paul</givenName>
      <familyName>Chekhonin</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0009-0005-5029-3061</nameIdentifier>
      <affiliation>Helmholtz Zentrum Dresden Rossendorf (HZDR)</affiliation>
    </creator>
    <creator>
      <creatorName>Korten, Till</creatorName>
      <givenName>Till</givenName>
      <familyName>Korten</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-2315-9247</nameIdentifier>
      <affiliation>Helmholtz Zentrum Dresden Rossendorf (HZDR)</affiliation>
    </creator>
    <creator>
      <creatorName>Gerçek, Alinda Ezgi</creatorName>
      <givenName>Alinda Ezgi</givenName>
      <familyName>Gerçek</familyName>
      <affiliation>Helmholtz Zentrum Dresden Rossendorf (HZDR)</affiliation>
    </creator>
    <creator>
      <creatorName>Hassan, Maleeha</creatorName>
      <givenName>Maleeha</givenName>
      <familyName>Hassan</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0009-0000-7917-7025</nameIdentifier>
      <affiliation>Helmholtz Zentrum Dresden Rossendorf (HZDR)</affiliation>
    </creator>
    <creator>
      <creatorName>Steinbach, Peter</creatorName>
      <givenName>Peter</givenName>
      <familyName>Steinbach</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-4974-230X</nameIdentifier>
      <affiliation>Helmholtz Zentrum Dresden Rossendorf (HZDR)</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Training Data and Models for the paper: Data-efficient U-Net for Segmentation of Carbide Microstructures in SEM Images of Steel Alloys</title>
  </titles>
  <publisher>Rodare</publisher>
  <publicationYear>2025</publicationYear>
  <subjects>
    <subject>machine learning</subject>
    <subject>SEM</subject>
    <subject>steel</subject>
    <subject>carbide</subject>
    <subject>segmentation</subject>
    <subject>image processing</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2025-11-14</date>
  </dates>
  <resourceType resourceTypeGeneral="Dataset"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://rodare.hzdr.de/record/4124</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsIdenticalTo">https://www.hzdr.de/publications/Publ-42225</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.14278/rodare.4123</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://rodare.hzdr.de/communities/rodare</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;This dataset contains scanning electron microscopy (SEM) images of steel alloys, including paired secondary electron (SE2) and in-lens (InLens) channels, with corresponding binary segmentation labels. The data supports full reproduction of results presented in the referenced manuscript.&lt;/p&gt;

&lt;p&gt;&amp;nbsp;&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;Dataset Description&lt;/strong&gt;&lt;/p&gt;

&lt;ul&gt;
	&lt;li&gt;&lt;strong&gt;Content:&lt;/strong&gt;&amp;nbsp;13 pairs of SEM images of two reactor pressure vessel (RPV) steels:

	&lt;ul&gt;
		&lt;li&gt;&lt;em&gt;JFL&lt;/em&gt;: IAEA reference RPV base metal steel&lt;/li&gt;
		&lt;li&gt;&lt;em&gt;ANP-10&lt;/em&gt;: Western type RPV steel&lt;/li&gt;
	&lt;/ul&gt;
	&lt;/li&gt;
	&lt;li&gt;&lt;strong&gt;Acquisition:&lt;/strong&gt;
	&lt;ul&gt;
		&lt;li&gt;&lt;em&gt;JFL&lt;/em&gt;: Zeiss NVision 40 microscope&lt;/li&gt;
		&lt;li&gt;&lt;em&gt;ANP-10&lt;/em&gt;: Zeiss Ultra 55 microscope&lt;/li&gt;
		&lt;li&gt;Both SE and InLens detectors used simultaneously.&lt;/li&gt;
	&lt;/ul&gt;
	&lt;/li&gt;
	&lt;li&gt;&lt;strong&gt;Resolution:&lt;/strong&gt;&amp;nbsp;2048 &amp;times; 1404 pixels per image
	&lt;ul&gt;
		&lt;li&gt;2048 px width corresponds to 14.3 &amp;micro;m (JFL) or 11.5 &amp;micro;m (ANP-10).&lt;/li&gt;
	&lt;/ul&gt;
	&lt;/li&gt;
&lt;/ul&gt;

&lt;p&gt;Using the dataset to reproduce the results of the manuscript&lt;/p&gt;

&lt;p&gt;Download the zip file into the&amp;nbsp;&lt;code&gt;data/&lt;/code&gt; subdirectory of the code repository and extract the archive:&lt;/p&gt;

&lt;pre&gt;&lt;code class="language-bash"&gt;cd data/
unzip data.zip&lt;/code&gt;&lt;/pre&gt;

&lt;p&gt;&lt;strong&gt;Dataset Structure&lt;/strong&gt;&lt;/p&gt;

&lt;p&gt;These directories contain the relevant data for the manuscript:&lt;/p&gt;

&lt;p&gt;&lt;code&gt;cloud/&lt;/code&gt;&lt;br&gt;
&lt;code&gt;├-─ preprocessed/&lt;/code&gt;&lt;br&gt;
&lt;code&gt;│ &amp;nbsp; ├── hold-out/&lt;/code&gt;&lt;br&gt;
&lt;code&gt;│ &amp;nbsp; ├── images/&lt;/code&gt;&lt;br&gt;
&lt;code&gt;│ &amp;nbsp; └── labels/&lt;/code&gt;&lt;br&gt;
&lt;code&gt;├── processed_tiles/&lt;/code&gt;&lt;br&gt;
&lt;code&gt;│ &amp;nbsp; ├── images/&lt;/code&gt;&lt;br&gt;
&lt;code&gt;│ &amp;nbsp; └── labels/&lt;/code&gt;&lt;br&gt;
&lt;code&gt;├── tb_logs/&lt;/code&gt;&lt;br&gt;
&lt;code&gt;│ &amp;nbsp; ├── unet_model/&lt;/code&gt;&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;Preprocessed&lt;/strong&gt;&lt;/p&gt;

&lt;p&gt;pre-processed whole images and corresponding labels&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;Processed Tiles&lt;/strong&gt;&lt;/p&gt;

&lt;p&gt;tiled images and labels&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;tb_logs&lt;/strong&gt;&lt;/p&gt;

&lt;p&gt;trained model weights&lt;/p&gt;</description>
  </descriptions>
</resource>
0
0
views
downloads
All versions This version
Views 00
Downloads 00
Data volume 0 Bytes0 Bytes
Unique views 00
Unique downloads 00

Share

Cite as