{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T16:13:01Z","timestamp":1788970381064,"version":"build-2803163510"},"reference-count":25,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T00:00:00Z","timestamp":1788307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100016238","name":"Dutch Ministry of Economic Affairs and Climate Policy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100016238","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Aims<\/jats:title>\n                    <jats:p>Intravascular optical coherence tomography (OCT) enables high-resolution imaging of the coronary vessel wall, but manual image interpretation is time-consuming and existing automated approaches often require high computational resources and exhibit slow inference times, limiting clinical use. We developed OCT-AID-lite, a neural network for near-real-time multi-class OCT segmentation leveraging knowledge distillation and semi-supervised learning to accelerate inference while maintaining segmentation accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and results<\/jats:title>\n                    <jats:p>A state-of-the-art model (OCT-AID) guided a compact U-Net\u2013based student model (OCT-AID-lite) through knowledge distillation-based supervision. OCT-AID-lite was trained on 3466 manually annotated and 137 961 pseudo-labelled frames after automated quality control. On 389 internal test frames, OCT-AID-lite achieved a forward-pass time of 0.10\u2005s for a 540-frame pullback, compared with 24.22\u2005s for the OCT-AID model (P \u00a0&amp;lt; \u00a00.01). Including pre- and post-processing, total processing time was 5.50\u2005s for OCT-AID-lite, compared with 30.62\u2005s for OCT-AID (P \u00a0&amp;lt; \u00a00.01). For lipid and calcium plaque classification, OCT-AID-lite reached sensitivity\/specificity of 98.1%\/74.4% and 89.5%\/87.5%, respectively. Pixel-wise segmentation performance on true-positive frames was high for guidewire, catheter, lumen, intima, and media (Dice: 0.79\u20130.99), moderate to high for sidebranch, lipid, and calcium (Dice: 0.76\u20130.78), and more variable for rare complex classes (Dice: 0.39\u20130.67). On an independent external test set, model predictions were in agreement with expert assessment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>OCT-AID-lite enables accurate OCT segmentation in near real-time, allowing efficient quantitative characterization of plaque and vessel structures.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/ehjdh\/ztag138","type":"journal-article","created":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T11:19:39Z","timestamp":1788347979000},"source":"Crossref","is-referenced-by-count":0,"title":["Near real-time multi-class segmentation for intravascular optical coherence tomography using knowledge distillation"],"prefix":"10.1093","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8462-1216","authenticated-orcid":false,"given":"Ruben G A","family":"van der Waerden","sequence":"first","affiliation":[{"name":"Department of Cardiology, Radboud University Medical Center , PO Box 9101, 6500 HB, Nijmegen ,","place":["the Netherlands"]},{"name":"Diagnostic Image Analysis Group, Radboud University Medical Center , Geert Grooteplein Zuid 10, 6525 GA, Nijmegen ,","place":["the Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7471-1006","authenticated-orcid":false,"given":"Rick H J A","family":"Volleberg","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Radboud University Medical Center , PO Box 9101, 6500 HB, Nijmegen ,","place":["the Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5191-6180","authenticated-orcid":false,"given":"Pierandrea","family":"Cancian","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering and Physics, Amsterdam University Medical Center , Amsterdam ,","place":["the Netherlands"]},{"name":"Informatics Institute, University of Amsterdam , Amsterdam ,","place":["the Netherlands"]},{"name":"Amsterdam Cardiovascular Sciences, Amsterdam UMC , Amsterdam ,","place":["the Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4998-6363","authenticated-orcid":false,"given":"Joske L","family":"van der Zande","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Radboud University Medical Center , PO Box 9101, 6500 HB, Nijmegen ,","place":["the Netherlands"]},{"name":"Diagnostic Image Analysis Group, Radboud University Medical Center , Geert Grooteplein Zuid 10, 6525 GA, Nijmegen ,","place":["the Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7706-5000","authenticated-orcid":false,"given":"Thijs J","family":"Luttikholt","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Radboud University Medical Center , PO Box 9101, 6500 HB, Nijmegen ,","place":["the Netherlands"]},{"name":"Diagnostic Image Analysis Group, Radboud University Medical Center , Geert Grooteplein Zuid 10, 6525 GA, Nijmegen ,","place":["the Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7455-049X","authenticated-orcid":false,"given":"Xiaojin","family":"Gu","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering and Physics, Amsterdam University Medical Center , Amsterdam ,","place":["the Netherlands"]},{"name":"Informatics Institute, University of Amsterdam , Amsterdam ,","place":["the Netherlands"]},{"name":"Amsterdam Cardiovascular Sciences, Amsterdam UMC , Amsterdam ,","place":["the Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leah","family":"Heil","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Radboud University Medical Center , PO Box 9101, 6500 HB, Nijmegen ,","place":["the Netherlands"]},{"name":"Diagnostic Image Analysis Group, Radboud University Medical Center , Geert Grooteplein Zuid 10, 6525 GA, Nijmegen ,","place":["the Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8609-1550","authenticated-orcid":false,"given":"Jan-Quinten","family":"Mol","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Radboud University Medical Center , PO Box 9101, 6500 HB, Nijmegen ,","place":["the Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4518-6458","authenticated-orcid":false,"given":"Kensuke","family":"Nishimiya","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Medicine, Tohoku University Graduate School of Medicine , Sendai ,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1370-7369","authenticated-orcid":false,"given":"Tomasz","family":"Roleder","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, Wroc\u0142aw University of Science and Technology , Wroc\u0142aw ,","place":["Poland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Clara I","family":"S\u00e1nchez","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering and Physics, Amsterdam University Medical Center , Amsterdam ,","place":["the Netherlands"]},{"name":"Informatics Institute, University of Amsterdam , Amsterdam ,","place":["the Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2028-8972","authenticated-orcid":false,"given":"Bram","family":"van Ginneken","sequence":"additional","affiliation":[{"name":"Diagnostic Image Analysis Group, Radboud University Medical Center , Geert Grooteplein Zuid 10, 6525 GA, Nijmegen ,","place":["the Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8605-0436","authenticated-orcid":false,"given":"Jos","family":"Thannhauser","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Radboud University Medical Center , PO Box 9101, 6500 HB, Nijmegen ,","place":["the Netherlands"]},{"name":"Diagnostic Image Analysis Group, Radboud University Medical Center , Geert Grooteplein Zuid 10, 6525 GA, Nijmegen ,","place":["the Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6136-8640","authenticated-orcid":false,"given":"Niels","family":"van Royen","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Radboud University Medical Center , PO Box 9101, 6500 HB, Nijmegen ,","place":["the Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1869-5034","authenticated-orcid":false,"given":"Ivana","family":"I\u0161gum","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering and Physics, Amsterdam University Medical Center , Amsterdam ,","place":["the Netherlands"]},{"name":"Informatics Institute, University of Amsterdam , Amsterdam ,","place":["the Netherlands"]},{"name":"Department of Radiology and Nuclear Medicine, Amsterdam University Medical Center University of Amsterdam , Amsterdam ,","place":["the Netherlands"]},{"name":"Department of Radiology, Mayo Clinic , Rochester, MN ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3974-5945","authenticated-orcid":false,"given":"Simone","family":"Saitta","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering and Physics, Amsterdam University Medical Center , Amsterdam ,","place":["the Netherlands"]},{"name":"Informatics Institute, University of Amsterdam , Amsterdam ,","place":["the Netherlands"]},{"name":"Amsterdam Cardiovascular Sciences, Amsterdam UMC , Amsterdam ,","place":["the Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,2]]},"reference":[{"key":"2026090911071444100_ztag138-B1","doi-asserted-by":"crossref","first-page":"634","DOI":"10.4244\/EIJ-D-17-00465","article-title":"State of the art: coronary angiography","volume":"13","author":"Collet","year":"2017","journal-title":"EuroIntervention"},{"key":"2026090911071444100_ztag138-B2","doi-asserted-by":"crossref","first-page":"3415","DOI":"10.1093\/eurheartj\/ehae177","article-title":"2024 ESC guidelines for the management of chronic coronary syndromes","volume":"45","author":"Vrints","year":"2024","journal-title":"Eur Heart J"},{"key":"2026090911071444100_ztag138-B3","doi-asserted-by":"crossref","first-page":"684","DOI":"10.1038\/s41569-022-00687-9","article-title":"Optical coherence tomography in coronary atherosclerosis assessment and intervention","volume":"19","author":"Araki","year":"2022","journal-title":"Nat Rev Cardiol"},{"key":"2026090911071444100_ztag138-B4","doi-asserted-by":"crossref","first-page":"1360","DOI":"10.1253\/circj.CJ-17-1144","article-title":"Current use of intracoronary imaging in interventional practice\u3000- results of a European association of percutaneous cardiovascular interventions (EAPCI) and Japanese association of cardiovascular interventions and therapeutics (CVIT) clinical practice survey","volume":"82","author":"Koskinas","year":"2018","journal-title":"Circ J"},{"key":"2026090911071444100_ztag138-B5","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1016\/j.jcmg.2023.10.005","article-title":"Accuracy of OCT core labs in identifying vulnerable plaque","volume":"17","author":"Gruslova","year":"2024","journal-title":"JACC Cardiovasc Imaging"},{"key":"2026090911071444100_ztag138-B6","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1093\/ehjdh\/ztaf005","article-title":"Artificial intelligence for the analysis of intracoronary optical coherence tomography images: a systematic review","volume":"6","author":"van der Waerden","year":"2025","journal-title":"Eur Heart J Digit Health"},{"key":"2026090911071444100_ztag138-B7","doi-asserted-by":"crossref","first-page":"41","DOI":"10.4244\/EIJ-D-20-01355","article-title":"Artificial intelligence and optical coherence tomography for the automatic characterisation of human atherosclerotic plaques","volume":"17","author":"Chu","year":"2021","journal-title":"Eurointervention"},{"key":"2026090911071444100_ztag138-B8","doi-asserted-by":"crossref","DOI":"10.1161\/CIRCIMAGING.125.018133","article-title":"Artificial intelligence-led whole coronary artery OCT analysis; validation and identification of drug efficacy and higher-risk plaques","volume":"18","author":"Jessney","year":"2025","journal-title":"Circ Cardiovasc Imaging"},{"key":"2026090911071444100_ztag138-B9","doi-asserted-by":"crossref","DOI":"10.1093\/ehjdh\/ztaf021","article-title":"Comprehensive full-vessel segmentation and volumetric plaque quantification for intracoronary optical coherence tomography using deep learning","author":"Volleberg","year":"2025","journal-title":"Eur Heart J Digit Health"},{"key":"2026090911071444100_ztag138-B10","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","year":"2019","journal-title":"BMC Med"},{"key":"2026090911071444100_ztag138-B11","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1038\/s41591-021-01614-0","article-title":"AI in health and medicine","volume":"28","author":"Rajpurkar","year":"2022","journal-title":"Nat Med"},{"key":"2026090911071444100_ztag138-B12","doi-asserted-by":"crossref","first-page":"5113","DOI":"10.1007\/s10462-020-09816-7","article-title":"A comprehensive survey on model compression and acceleration","volume":"53","author":"Choudhary","year":"2020","journal-title":"Artif Intell Rev"},{"key":"2026090911071444100_ztag138-B13","author":"Hinton"},{"key":"2026090911071444100_ztag138-B14","author":"Jiao"},{"key":"2026090911071444100_ztag138-B15","first-page":"177","volume-title":"Medical Imaging 2025: Image Processing","author":"Cancian","year":"2025"},{"key":"2026090911071444100_ztag138-B16","doi-asserted-by":"crossref","first-page":"e048994","DOI":"10.1136\/bmjopen-2021-048994","article-title":"Identification of anatomic risk factors for acute coronary events by optical coherence tomography in patients with myocardial infarction and residual nonflow limiting lesions: rationale and design of the PECTUS-obs study","volume":"11","author":"Mol","year":"2021","journal-title":"BMJ Open"},{"key":"2026090911071444100_ztag138-B17","doi-asserted-by":"crossref","first-page":"1013","DOI":"10.1001\/jamacardio.2023.2910","article-title":"Fractional flow reserve-negative high-risk plaques and clinical outcomes after myocardial infarction","volume":"8","author":"Mol","year":"2023","journal-title":"JAMA Cardiol"},{"key":"2026090911071444100_ztag138-B18"},{"key":"2026090911071444100_ztag138-B19","author":"Isensee"},{"key":"2026090911071444100_ztag138-B20","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat Methods"},{"key":"2026090911071444100_ztag138-B21","doi-asserted-by":"publisher","author":"Ahamed","DOI":"10.48550\/arXiv.2309.13553"},{"key":"2026090911071444100_ztag138-B22","first-page":"234","volume-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","author":"Ronneberger","year":"2015"},{"key":"2026090911071444100_ztag138-B23","author":"Camarasa"},{"key":"2026090911071444100_ztag138-B24","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1186\/s13104-022-06096-y","article-title":"Towards a guideline for evaluation metrics in medical image segmentation","volume":"15","author":"M\u00fcller","year":"2022","journal-title":"BMC Res Notes"},{"key":"2026090911071444100_ztag138-B25","doi-asserted-by":"publisher","author":"Kaplan","DOI":"10.48550\/arXiv.2001.08361"}],"container-title":["European Heart Journal - Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/ehjdh\/advance-article-pdf\/doi\/10.1093\/ehjdh\/ztag138\/70922030\/ztag138.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/7\/8\/ztag138\/70922030\/ztag138.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/7\/8\/ztag138\/70922030\/ztag138.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T15:28:55Z","timestamp":1788967735000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ehjdh\/article\/doi\/10.1093\/ehjdh\/ztag138\/8779935"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,2]]},"references-count":25,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,9,4]]}},"URL":"https:\/\/doi.org\/10.1093\/ehjdh\/ztag138","relation":{},"ISSN":["2634-3916"],"issn-type":[{"value":"2634-3916","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,10]]},"published":{"date-parts":[[2026,9,2]]},"article-number":"ztag138"}}