{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T13:05:24Z","timestamp":1760101524237,"version":"3.40.4"},"reference-count":31,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"crossref","award":["SFB 986 - Project number 192346071"],"award-info":[{"award-number":["SFB 986 - Project number 192346071"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,6,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Accurate 3D reconstruction of the structure of nanomaterials is essential for studying their physical properties. Focused ion beam (FIB) tomography is a preferred method for creating 3D image stacks of micrometer-sized material volumes at nanometer resolution. To achieve valid 3D reconstructions from FIB tomography data, semantic segmentation of these images using machine learning-based methods is often beneficial. However, supervised machine learning requires a large amount of training data and ground truth, which is challenging because FIB tomography is a destructive technique. This motivates the use of synthetic training data generated with Monte Carlo simulations of the FIB tomography process. However, these simulations are computationally expensive, and the resulting synthetic imaging data still differs from real FIB tomography data in terms of the statistical distribution of various features. In this study, we propose a novel approach to overcome both problems, i.e. requiring high computation time and difference in data distribution, using generative adversarial networks.<\/jats:p>","DOI":"10.1088\/2632-2153\/adc870","type":"journal-article","created":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T22:56:21Z","timestamp":1743634581000},"page":"025023","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Generative adversarial networks for creating realistic training data for machine learning-based segmentation of FIB tomography data"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9915-3039","authenticated-orcid":true,"given":"Trushal","family":"Sardhara","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8264-0885","authenticated-orcid":true,"given":"Christian","family":"J Cyron","sequence":"additional","affiliation":[]},{"given":"Martin","family":"Ritter","sequence":"additional","affiliation":[]},{"given":"Roland","family":"C Aydin","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"mlstadc870bib1","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1166\/jnn.2002.151","article-title":"Nanoporous materials","volume":"2","author":"Polarz","year":"2002","journal-title":"J. Nanosci. Nanotechnol."},{"key":"mlstadc870bib2","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1126\/science.abd9391","article-title":"Scaling behavior of stiffness and strength of hierarchical network nanomaterials","volume":"371","author":"Shi","year":"2021","journal-title":"Science"},{"key":"mlstadc870bib3","doi-asserted-by":"publisher","first-page":"2959","DOI":"10.1523\/JNEUROSCI.3189-07.2008","article-title":"Serial section scanning electron microscopy of adult brain tissue using focused ion beam milling","volume":"28","author":"Knott","year":"2008","journal-title":"J. Neurosci."},{"article-title":"Cluster analysis for FIB tomography of nanoporous materials","year":"2019","author":"Rogge","key":"mlstadc870bib4"},{"key":"mlstadc870bib5","doi-asserted-by":"crossref","DOI":"10.1093\/micmic\/ozad067.257","article-title":"Towards an accurate 3D reconstruction of nano-porous structures using FIB tomography and Monte Carlo simulations with machine learning","author":"Sardhara","year":"2023"},{"key":"mlstadc870bib6","doi-asserted-by":"publisher","DOI":"10.3389\/fmats.2022.837006","article-title":"Training deep neural networks to reconstruct nanoporous structures from FIB tomography images using synthetic training data","volume":"9","author":"Sardhara","year":"2022","journal-title":"Frontiers in Materials"},{"volume":"vol 174","year":"2021","author":"Nikolenko","key":"mlstadc870bib7"},{"article-title":"Synthetic datasets for autonomous driving: a survey","year":"2023","author":"Song","key":"mlstadc870bib8"},{"key":"mlstadc870bib9","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1111\/jmi.12944","article-title":"Reconstruction of highly porous structures from FIB-SEM using a deep neural network trained on synthetic images","volume":"281","author":"Fend","year":"2021","journal-title":"J. Microsc."},{"key":"mlstadc870bib10","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1017\/S1431927609092423","article-title":"MC x-ray, a new Monte Carlo program for quantitative x-ray microanalysis of real materials","volume":"15","author":"Gauvin","year":"2009","journal-title":"Microsc. Microanal."},{"article-title":"Canada Object Research Systems (ORS) Inc, Montreal. Dragonfly 3.6 [computer software]","year":"2018","author":"","key":"mlstadc870bib11"},{"key":"mlstadc870bib12","doi-asserted-by":"publisher","first-page":"139","DOI":"10.21468\/SciPostPhys.10.6.139","article-title":"GANplifying event samples","volume":"10","author":"Butter","year":"2021","journal-title":"SciPost Phys."},{"article-title":"AI-based Monte Carlo event generator for electron-proton scattering","year":"2020","author":"Alanazi","key":"mlstadc870bib13"},{"key":"mlstadc870bib14","first-page":"pp 24","article-title":"3D-StyleGAN: a style-based generative adversarial network for generative modeling of three-dimensional medical images","volume":"vol 1","author":"Hong","year":"2021"},{"key":"mlstadc870bib15","first-page":"pp 8110","article-title":"Analyzing and improving the image quality of StyleGAN","author":"Karras","year":"2020"},{"key":"mlstadc870bib16","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1038\/s41524-023-01042-3","article-title":"Leveraging generative adversarial networks to create realistic scanning transmission electron microscopy images","volume":"9","author":"Khan","year":"2023","journal-title":"npj Comput. Mater."},{"author":"Kouw","key":"mlstadc870bib17","article-title":"An introduction to domain adaptation and transfer learning"},{"key":"mlstadc870bib18","doi-asserted-by":"publisher","first-page":"6452","DOI":"10.1109\/TIP.2020.2989100","article-title":"Learning from synthetic images via active pseudo-labeling","volume":"29","author":"Song","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"mlstadc870bib19","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1016\/j.actamat.2018.01.005","article-title":"3D stochastic bicontinuous microstructures: generation, topology and elasticity","volume":"149","author":"Soyarslan","year":"2018","journal-title":"Acta Mater."},{"key":"mlstadc870bib20","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1111\/jmi.12683","article-title":"Spin-coated epoxy resin embedding technique enables facile SEM\/FIB thickness determination of porous metal oxide ultra-thin films","volume":"270","author":"Pe\u00f1a","year":"2018","journal-title":"J. Microsc."},{"key":"mlstadc870bib21","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s41871-024-00223-y","article-title":"Enhancing 3D reconstruction accuracy of FIB tomography data using multi-voltage images and multimodal machine learning","volume":"7","author":"Sardhara","year":"2024","journal-title":"Nanomanuf. Metrol."},{"article-title":"Auto slice and view 4.0 [computer software]","year":"2017","author":"Thermo Fisher Scientific Inc","key":"mlstadc870bib22"},{"key":"mlstadc870bib23","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1017\/S1431927612014031","article-title":"Three-dimensional semiconductor device investigation using focused ion beam and scanning electron microscopy imaging (FIB\/SEM tomography)","volume":"19","author":"Lepinay","year":"2013","journal-title":"Microsc. Microanal."},{"key":"mlstadc870bib24","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.ultramic.2014.01.003","article-title":"Investigation of slice thickness and shape milled by a focused ion beam for three-dimensional reconstruction of microstructures","volume":"139","author":"Jones","year":"2014","journal-title":"Ultramicroscopy"},{"key":"mlstadc870bib25","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1007\/s41871-022-00134-w","article-title":"Slice thickness optimization for the focused ion beam-scanning electron microscopy 3D tomography of hierarchical nanoporous gold","volume":"5","author":"Shkurmanov","year":"2022","journal-title":"Nanomanuf. Metrol."},{"key":"mlstadc870bib26","first-page":"pp 2223","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","author":"Zhu","year":"2017"},{"key":"mlstadc870bib27","first-page":"pp 234","article-title":"U-Net: convolutional networks for biomedical image segmentation","volume":"vol 18","author":"Ronneberger","year":"2015"},{"key":"mlstadc870bib28","doi-asserted-by":"publisher","first-page":"K45","DOI":"10.1002\/pssa.2210560157","article-title":"Measurements of the electron backscattering coefficient for quantitative EPMA in the energy range of 4 to 40 keV","volume":"56","author":"Hunger","year":"1979","journal-title":"Phys. Status Solidi a"},{"key":"mlstadc870bib29","first-page":"pp 565","article-title":"V-Net: fully convolutional neural networks for volumetric medical image segmentation","author":"Milletari","year":"2016"},{"key":"mlstadc870bib30","doi-asserted-by":"publisher","first-page":"3322","DOI":"10.1080\/14786435.2016.1222087","article-title":"Nanoporous gold: 3D structural analyses of representative volumes and their implications on scaling relations of mechanical behaviour","volume":"96","author":"Hu","year":"2016","journal-title":"Phil. Mag."},{"key":"mlstadc870bib31","doi-asserted-by":"publisher","first-page":"5948","DOI":"10.1021\/nn4021345","article-title":"Hierarchical nested-network nanostructure by dealloying","volume":"7","author":"Qi","year":"2013","journal-title":"ACS Nano"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc870","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc870\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc870","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc870\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc870\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc870\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc870\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc870\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T07:29:43Z","timestamp":1745306983000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc870"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":31,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,4,22]]},"published-print":{"date-parts":[[2025,6,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/adc870","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"Generative adversarial networks for creating realistic training data for machine learning-based segmentation of FIB tomography data","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-01-23","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-04-01","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-04-22","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}