{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T14:22:16Z","timestamp":1792160536093,"version":"4.4.0"},"reference-count":52,"publisher":"Wiley","issue":"13","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["physoc.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["The Journal of Physiology"],"published-print":{"date-parts":[[2026,7]]},"abstract":"\n Abstract<\/jats:title>\n \n Segmentation of cardiomyocytes in microscopic 3D volumes is key to our understanding of cardiac (patho\u2010)physiology; however, it poses substantial experimental and analytical challenges. Therefore, researchers often resort to inferring 3D information from 2D segmentations, which can lead to biased and incorrect conclusions. Deep learning\u2010based methods are showing promise with respect to robustly segmenting objects in volumes acquired using various imaging modalities; yet, they have not been applied to high\u2010resolution 3D cardiomyocyte segmentations, and suitable open\u2010source tools and datasets are lacking. Here, we present a deep learning\u2010enabled toolkit for segmentation of individual cardiomyocytes in 3D confocal microscopy volumes. We include a dataset of 73 volumes with expert annotations, covering seven species, including mouse, human, and elephant, and containing samples generated under different experimental conditions, such as post\u2010myocardial infarction and\n ex vivo<\/jats:italic>\n slice cultures. The toolkit additionally contains an image restoration workflow to address imaging\u2010related artefacts, such as spatially varying blur. Our automatic cardiomyocyte segmentation workflow achieved an adapted Rand error of 0.063\u00a0\u00b1\u00a00.034 (\u223c94% voxel\u2010pair agreement) on the test set. Our semi\u2010automatic workflow reached a throughput of 3\u00a0cells\u00a0min\n \u22121<\/jats:sup>\n on a challenging, previously unseen dataset. The toolkit and data are open\u2010source and accessible through a dedicated graphical user interface. In summary, we provide an accessible toolkit enabling researchers to extract quantitative data on cardiomyocyte microstructure from 3D confocal image stacks of cardiac tissue. Given the size and diversity of our dataset, we expect our methods to perform well across species and experimental conditions, facilitating high\u2010quality 3D reconstructions of large numbers of individual cardiomyocytes.\n \n \n image<\/jats:alt-text>\n <\/jats:graphic>\n <\/jats:boxed-text>\n <\/jats:p>\n <\/jats:sec>\n \n Key points<\/jats:title>\n \n \n \n 3D cardiomyocyte microstructure is a key determinant of cardiac function in health and disease. However, reliable extraction and quantification of 3D cardiomyocyte cytoarchitecture pose significant experimental and computational challenges.<\/jats:p>\n <\/jats:list-item>\n \n We present an effective experimental protocol and a deep learning\u2010enabled toolkit for sample preparation and 3D analysis of cardiomyocyte morphology in ventricular myocardium.<\/jats:p>\n <\/jats:list-item>\n \n \n Our method is validated across seven species (mouse to human) and in samples prepared in diverse experimental conditions from a range of models, including myocardial infarction and\n ex vivo<\/jats:italic>\n tissue culture, highlighting the robustness and versatility of our workflow.\n <\/jats:p>\n <\/jats:list-item>\n \n Our open\u2010source dataset and toolkit enable large\u2010scale analyses and extraction of realistic 3D geometries of ventricular microstructure. These can be used to explore a host of research questions and provide a new resource for modelling cardiac function at the cellular level.<\/jats:p>\n <\/jats:list-item>\n <\/jats:list>\n <\/jats:p>\n <\/jats:sec>","DOI":"10.1113\/jp288557","type":"journal-article","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T13:35:08Z","timestamp":1759325708000},"page":"5561-5584","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A deep learning\u2010enabled toolkit for the 3D segmentation of ventricular cardiomyocytes"],"prefix":"10.1113","volume":"604","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5454-2962","authenticated-orcid":false,"given":"Joachim","family":"Greiner","sequence":"first","affiliation":[{"name":"Institute for Experimental Cardiovascular Medicine, University Heart Center Freiburg \u00b7 Bad Krozingen, and Faculty of Medicine University of Freiburg Freiburg im Breisgau Germany"},{"name":"CIBSS Centre for Integrative Biological Signalling Studies University of Freiburg Freiburg im Breisgau Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabio","family":"Frangiamore","sequence":"additional","affiliation":[{"name":"Orobix Srl Bergamo Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0241-0894","authenticated-orcid":false,"given":"Fr\u00e9d\u00e9ric","family":"Sonak","sequence":"additional","affiliation":[{"name":"Institute for Experimental Cardiovascular Medicine, University Heart Center Freiburg \u00b7 Bad Krozingen, and Faculty of Medicine University of Freiburg Freiburg im Breisgau Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3637-2546","authenticated-orcid":false,"given":"Josef","family":"Madl","sequence":"additional","affiliation":[{"name":"Institute for Experimental Cardiovascular Medicine, University Heart Center Freiburg \u00b7 Bad Krozingen, and Faculty of Medicine University of Freiburg Freiburg im Breisgau Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3127-1693","authenticated-orcid":false,"given":"Thomas","family":"Seidel","sequence":"additional","affiliation":[{"name":"Institute of Cellular and Molecular Physiology Friedrich\u2010Alexander\u2010Universit\u00e4t Erlangen\u2010N\u00fcrnberg Erlangen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0416-6270","authenticated-orcid":false,"given":"Peter","family":"Kohl","sequence":"additional","affiliation":[{"name":"Institute for Experimental Cardiovascular Medicine, University Heart Center Freiburg \u00b7 Bad Krozingen, and Faculty of Medicine University of Freiburg Freiburg im Breisgau Germany"},{"name":"CIBSS Centre for Integrative Biological Signalling Studies University of Freiburg Freiburg im Breisgau Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3295-4728","authenticated-orcid":false,"given":"Eva A.","family":"Rog\u2010Zielinska","sequence":"additional","affiliation":[{"name":"Institute for Experimental Cardiovascular Medicine, University Heart Center Freiburg \u00b7 Bad Krozingen, and Faculty of Medicine University of Freiburg Freiburg im Breisgau Germany"},{"name":"CIBSS Centre for Integrative Biological Signalling Studies University of Freiburg Freiburg im Breisgau Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,10,1]]},"reference":[{"key":"e_1_2_6_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01135"},{"key":"e_1_2_6_3_1","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2024.1363538"},{"key":"e_1_2_6_4_1","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.4151"},{"key":"e_1_2_6_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/srep23756"},{"key":"e_1_2_6_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0582-9"},{"key":"e_1_2_6_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00395-005-0524-9"},{"key":"e_1_2_6_8_1","doi-asserted-by":"publisher","DOI":"10.1152\/ajpheart.00481.2009"},{"key":"e_1_2_6_9_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCRESAHA.116.303448"},{"key":"e_1_2_6_10_1","doi-asserted-by":"publisher","DOI":"10.1152\/ajpheart.00479.2007"},{"key":"e_1_2_6_11_1","first-page":"656","volume-title":"MICCAI 2023","author":"Chobola T.","year":"2023"},{"key":"e_1_2_6_12_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-022-01639-4"},{"key":"e_1_2_6_13_1","doi-asserted-by":"publisher","DOI":"10.15252\/embj.2022113288"},{"key":"e_1_2_6_14_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-023-04544-2"},{"key":"e_1_2_6_15_1","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2018.00239"},{"key":"e_1_2_6_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105579"},{"key":"e_1_2_6_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0650-1"},{"key":"e_1_2_6_18_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCRESAHA.114.302226"},{"key":"e_1_2_6_19_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCRESAHA.107.160085"},{"key":"e_1_2_6_20_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"e_1_2_6_21_1","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2021.763584"},{"key":"e_1_2_6_22_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-018-0049-4"},{"key":"e_1_2_6_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/jcp.22559"},{"key":"e_1_2_6_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10439-011-0369-3"},{"issue":"8","key":"e_1_2_6_25_1","first-page":"1156","article-title":"Towards modeling of cardiac micro\u2010structure with catheter\u2010based confocal microscopy: A novel approach for dye delivery and tissue characterization","volume":"28","author":"Lasher R. A.","year":"2009","journal-title":"Institute of Electrical and Electronics Engineers Transactions on Medical Imaging"},{"key":"e_1_2_6_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-022-01652-7"},{"issue":"2","key":"e_1_2_6_27_1","first-page":"318","article-title":"Focal loss for dense object detection","volume":"42","author":"Lin T.\u2010Y.","year":"2020","journal-title":"Institute of Electrical and Electronics Engineers Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_2_6_28_1","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2014.00013"},{"key":"e_1_2_6_29_1","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.2001.013415"},{"key":"e_1_2_6_30_1","unstructured":"Oktay O. Schlemper J. Folgoc L. L. Lee M. Heinrich M. Misawa K. Mori K. McDonagh S. Hammerla N. Y. Kainz B. Glocker B. &Rueckert D.(2018).Attention U\u2010Net: Learning Where to Look for the Pancreas.arXiv.https:\/\/doi.org\/10.48550\/arXiv.1804.03999"},{"key":"e_1_2_6_31_1","doi-asserted-by":"publisher","DOI":"10.3390\/biom10091334"},{"key":"e_1_2_6_32_1","doi-asserted-by":"crossref","unstructured":"Pape C. Beier T. Li P. Jain V. Bock D. D. &Kreshuk A.(2017).Solving large multicut problems for connectomics via domain decomposition. In2017 IEEE International Conference on Computer Vision Workshops (ICCVW)(pp.1\u201310).IEEE.","DOI":"10.1109\/ICCVW.2017.7"},{"key":"e_1_2_6_33_1","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2019.00006"},{"key":"e_1_2_6_34_1","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2021.730933"},{"key":"e_1_2_6_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0006-3495(96)79711-4"},{"issue":"2","key":"e_1_2_6_36_1","first-page":"64","article-title":"Structural remodelling in heart failure","volume":"7","author":"Schaper J.","year":"2002","journal-title":"Experimental & Clinical Cardiology"},{"issue":"7","key":"e_1_2_6_37_1","article-title":"Development of a cardiovascular magnetic resonance\u2010compatible large animal isolated heart model for direct comparison of beating and arrested hearts","volume":"35","author":"Scott A. D.","year":"2022","journal-title":"Nuclear Magnetic Resonance in Biomedicine"},{"key":"e_1_2_6_38_1","doi-asserted-by":"crossref","unstructured":"Seidel T. Draebing T. Seemann G. &Sachse F. B.(2013).A semi\u2010automatic approach for segmentation of three\u2010dimensional microscopic image stacks of cardiac tissue. InProceedings Functional Imaging and Modeling of the Heart(pp.300\u2013307).Springer.","DOI":"10.1007\/978-3-642-38899-6_36"},{"key":"e_1_2_6_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10439-015-1465-6"},{"key":"e_1_2_6_40_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.116.024470"},{"key":"e_1_2_6_41_1","doi-asserted-by":"crossref","unstructured":"Shit S. Paetzold J. C. Sekuboyina A. Ezhov I. Unger A. Zhylka A. Pluim J. P. W. Bauer U. &Menze B. H.(2021).clDice \u2010 a novel topology\u2010preserving loss function for tubular structure segmentation. InProceedings IEEE\/CVF Conference Computer Vision and Pattern Recognition (CVPR)(pp.16555\u201316564).IEEE.","DOI":"10.1109\/CVPR46437.2021.01629"},{"key":"e_1_2_6_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aanat.2022.151892"},{"key":"e_1_2_6_43_1","doi-asserted-by":"publisher","DOI":"10.22489\/CinC.2023.385"},{"key":"e_1_2_6_44_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01018-x"},{"issue":"12","key":"e_1_2_6_45_1","first-page":"2425","article-title":"Unraveling impacts of chamber\u2010specific differences in intercalated disc ultrastructure and molecular organization on cardiac conduction","volume":"9","author":"Struckman H. L.","year":"2023","journal-title":"Journal of the American College of Cardiology: Clinical Electrophysiology"},{"key":"e_1_2_6_46_1","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.101.25.2981"},{"key":"e_1_2_6_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10237-022-01660-8"},{"key":"e_1_2_6_48_1","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01026"},{"key":"e_1_2_6_49_1","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.453"},{"key":"e_1_2_6_50_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-018-0216-7"},{"key":"e_1_2_6_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBIC56247.2022.9854534"},{"key":"e_1_2_6_52_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-76932-3"},{"key":"e_1_2_6_53_1","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.57613"}],"container-title":["The Journal of Physiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/physoc.onlinelibrary.wiley.com\/doi\/pdf\/10.1113\/JP288557","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/physoc.onlinelibrary.wiley.com\/doi\/full-xml\/10.1113\/JP288557","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/physoc.onlinelibrary.wiley.com\/doi\/pdf\/10.1113\/JP288557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T21:30:37Z","timestamp":1783027837000},"score":1,"resource":{"primary":{"URL":"https:\/\/physoc.onlinelibrary.wiley.com\/doi\/10.1113\/JP288557"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,1]]},"references-count":52,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1113\/JP288557"],"URL":"https:\/\/doi.org\/10.1113\/jp288557","archive":["Portico"],"relation":{"has-preprint":[{"id-type":"doi","id":"10.22541\/au.173697566.64378528\/v1","asserted-by":"object"},{"id-type":"doi","id":"10.22541\/au.173697566.64378528\/v2","asserted-by":"object"}]},"ISSN":["0022-3751","1469-7793"],"issn-type":[{"value":"0022-3751","type":"print"},{"value":"1469-7793","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,1]]},"assertion":[{"value":"2025-03-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}