{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T22:26:42Z","timestamp":1792016802113,"version":"4.4.0"},"reference-count":19,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,2,5]],"date-time":"2025-02-05T00:00:00Z","timestamp":1738713600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,2,5]],"date-time":"2025-02-05T00:00:00Z","timestamp":1738713600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001858","name":"VINNOVA","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005754","name":"Sahlgrenska Universitetssjukhuset","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005754","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Analytic Imaging Diagnostic Arena"},{"DOI":"10.13039\/501100007687","name":"Svenska L\u00e4kares\u00e4llskapet","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007687","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol"],"abstract":"Abstract<\/jats:title>\n \n Objectives<\/jats:title>\n To develop and evaluate a deep learning model for segmentation of the coronary artery vessels and coronary plaques in coronary computed tomography angiography (CCTA).<\/jats:p>\n <\/jats:sec>\n \n Materials and methods<\/jats:title>\n \n CCTA image data from the Swedish CardioPulmonary BioImage Study (SCAPIS) was used for model development (\n n<\/jats:italic>\n \u2009=\u2009463 subjects) and testing (\n n<\/jats:italic>\n \u2009=\u2009123) and for an interobserver study (\n n<\/jats:italic>\n \u2009=\u200965). A dataset from Link\u00f6ping University Hospital (\n n<\/jats:italic>\n \u2009=\u200928) was used for external validation. The model\u2019s ability to detect coronary artery disease (CAD) was tested in a separate SCAPIS dataset (\n n<\/jats:italic>\n \u2009=\u2009684). A deep ensemble (k\u2009=\u20096) of a customized 3D vision transformer model was used for voxelwise classification. The Dice coefficient, the average surface distance, Pearson\u2019s correlation coefficient, analysis of segmented volumes by intraclass correlation coefficient (ICC), and agreement (sensitivity and specificity) were used to analyze model performance.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n PlaqueViT segmented coronary plaques with a Dice coefficient = 0.55, an average surface distance = 0.98\u2009mm and ICC\u2009=\u20090.93 versus an expert reader. In the interobserver study, PlaqueViT performed as well as the expert reader (Dice coefficient = 0.51 and 0.50, average surface distance = 1.31 and 1.15\u2009mm, ICC\u2009=\u20090.97 and 0.98, respectively). PlaqueViT achieved 88% agreement (sensitivity 97%, specificity 76%) in detecting any coronary plaque in the test dataset (\n n<\/jats:italic>\n \u2009=\u2009123) and 89% agreement (sensitivity 95%, specificity 83%) in the CAD detection dataset (\n n<\/jats:italic>\n \u2009=\u2009684).\n <\/jats:p>\n <\/jats:sec>\n \n Conclusion<\/jats:title>\n We developed a deep learning model for fully automatic plaque detection and segmentation that identifies and delineates coronary plaques and the arterial lumen with similar performance as an experienced reader.<\/jats:p>\n <\/jats:sec>\n \n Key Points<\/jats:title>\n \n \n Question<\/jats:italic>\n <\/jats:bold>\n A tool for fully automatic and voxelwise segmentation of coronary plaques in coronary CTA (CCTA) is important for both clinical and research usage of the CCTA examination.<\/jats:italic>\n <\/jats:p>\n \n \n Findings<\/jats:italic>\n <\/jats:bold>\n Segmentation of coronary artery plaques by PlaqueViT was comparable to an expert reader\u2019s performance.<\/jats:italic>\n <\/jats:p>\n \n \n Clinical relevance<\/jats:italic>\n <\/jats:bold>\n This novel, fully automatic deep learning model for voxelwise segmentation of coronary plaques in CCTA is highly relevant for large population studies such as the Swedish CardioPulmonary BioImage Study.<\/jats:italic>\n <\/jats:p>\n <\/jats:sec>\n \n Graphical Abstract<\/jats:title>\n <\/jats:sec>","DOI":"10.1007\/s00330-025-11410-w","type":"journal-article","created":{"date-parts":[[2025,2,5]],"date-time":"2025-02-05T11:37:04Z","timestamp":1738755424000},"page":"4461-4471","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["PlaqueViT: a vision transformer model for fully automatic vessel and plaque segmentation in coronary computed tomography angiography"],"prefix":"10.1007","volume":"35","author":[{"given":"Jennifer","family":"Alv\u00e9n","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard","family":"Petersen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Hagerman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M\u00e5rten","family":"Sandstedt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pieter","family":"Kitslaar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G\u00f6ran","family":"Bergstr\u00f6m","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erika","family":"Fagman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8639-6928","authenticated-orcid":false,"given":"Ola","family":"Hjelmgren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,2,5]]},"reference":[{"key":"11410_CR1","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1093\/eurheartj\/ehab892","volume":"43","author":"A Timmis","year":"2022","unstructured":"Timmis A, Vardas P, Townsend N et al (2022) European Society of Cardiology: cardiovascular disease statistics 2021. Eur Heart J 43:716\u2013799","journal-title":"Eur Heart J"},{"key":"11410_CR2","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.jcct.2020.11.002","volume":"15","author":"LJ Shaw","year":"2021","unstructured":"Shaw LJ, Blankstein R, Bax JJ et al (2021) Society of Cardiovascular Computed Tomography \/ North American Society of Cardiovascular Imaging\u2014expert consensus document on coronary CT imaging of atherosclerotic plaque. J Cardiovasc Comput Tomogr 15:93\u2013109","journal-title":"J Cardiovasc Comput Tomogr"},{"key":"11410_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajpc.2022.100318","volume":"9","author":"MJ Budoff","year":"2022","unstructured":"Budoff MJ, Lakshmanan S, Toth PP et al (2022) Cardiac CT angiography in current practice: an American Society For Preventive Cardiology clinical practice statement. Am J Prev Cardiol 9:100318","journal-title":"Am J Prev Cardiol"},{"key":"11410_CR4","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1161\/CIRCULATIONAHA.119.044720","volume":"141","author":"MC Williams","year":"2020","unstructured":"Williams MC, Kwiecinski J, Doris M et al (2020) Low-attenuation noncalcified plaque on coronary computed tomography angiography predicts myocardial infarction: results from the multicenter SCOT-HEART trial (Scottish computed tomography of the HEART). Circulation 141:1452\u20131462","journal-title":"Circulation"},{"key":"11410_CR5","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1016\/j.jcct.2015.07.003","volume":"9","author":"M Ferencik","year":"2015","unstructured":"Ferencik M, Mayrhofer T, Puchner SB et al (2015) Computed tomography-based high-risk coronary plaque score to predict acute coronary syndrome among patients with acute chest pain\u2014results from the ROMICAT II trial. J Cardiovasc Comput Tomogr 9:538\u2013545","journal-title":"J Cardiovasc Comput Tomogr"},{"key":"11410_CR6","doi-asserted-by":"publisher","first-page":"684","DOI":"10.1016\/j.jacc.2014.05.039","volume":"64","author":"SB Puchner","year":"2014","unstructured":"Puchner SB, Liu T, Mayrhofer T et al (2014) High-risk plaque detected on coronary CT angiography predicts acute coronary syndromes independent of significant stenosis in acute chest pain: results from the ROMICAT-II trial. J Am Coll Cardiol 64:684\u2013692","journal-title":"J Am Coll Cardiol"},{"key":"11410_CR7","doi-asserted-by":"publisher","first-page":"693","DOI":"10.1148\/radiol.14140933","volume":"274","author":"SB Puchner","year":"2015","unstructured":"Puchner SB, Lu MT, Mayrhofer T et al (2015) High-risk coronary plaque at coronary CT angiography is associated with nonalcoholic fatty liver disease, independent of coronary plaque and stenosis burden: results from the ROMICAT II trial. Radiology 274:693\u2013701","journal-title":"Radiology"},{"key":"11410_CR8","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1111\/joim.12384","volume":"278","author":"G Bergstrom","year":"2015","unstructured":"Bergstrom G, Berglund G, Blomberg A et al (2015) The Swedish CArdioPulmonary BioImage Study: objectives and design. J Intern Med 278:645\u2013659","journal-title":"J Intern Med"},{"key":"11410_CR9","doi-asserted-by":"publisher","first-page":"916","DOI":"10.1161\/CIRCULATIONAHA.121.055340","volume":"144","author":"G Bergstr\u00f6m","year":"2021","unstructured":"Bergstr\u00f6m G, Persson M, Adiels M et al (2021) Prevalence of subclinical coronary artery atherosclerosis in the general population. Circulation 144:916\u2013929","journal-title":"Circulation"},{"key":"11410_CR10","doi-asserted-by":"publisher","first-page":"e256","DOI":"10.1016\/S2589-7500(22)00022-X","volume":"4","author":"A Lin","year":"2022","unstructured":"Lin A, Manral N, McElhinney P et al (2022) Deep learning-enabled coronary CT angiography for plaque and stenosis quantification and cardiac risk prediction: an international multicentre study. Lancet Digit Health 4:e256\u2013e265","journal-title":"Lancet Digit Health"},{"key":"11410_CR11","doi-asserted-by":"publisher","first-page":"7217","DOI":"10.1007\/s00330-022-08801-8","volume":"32","author":"N J\u00e1vorszky","year":"2022","unstructured":"J\u00e1vorszky N, Homonnay B, Gerstenblith G et al (2022) Deep learning-based atherosclerotic coronary plaque segmentation on coronary CT angiography. Eur Radiol 32:7217\u20137226","journal-title":"Eur Radiol"},{"key":"11410_CR12","doi-asserted-by":"publisher","first-page":"5276","DOI":"10.1007\/s00330-022-08664-z","volume":"32","author":"X Jin","year":"2022","unstructured":"Jin X, Li Y, Yan F et al (2022) Automatic coronary plaque detection, classification, and stenosis grading using deep learning and radiomics on computed tomography angiography images: a multi-center multi-vendor study. Eur Radiol 32:5276\u20135286","journal-title":"Eur Radiol"},{"key":"11410_CR13","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2021.597568","volume":"8","author":"H Liu","year":"2021","unstructured":"Liu H, Wingert A, Wang J et al (2021) Extraction of coronary atherosclerotic plaques from computed tomography imaging: a review of recent methods. Front Cardiovasc Med 8:597568","journal-title":"Front Cardiovasc Med"},{"key":"11410_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2023.e16058","volume":"9","author":"E Fagman","year":"2023","unstructured":"Fagman E, Alv\u00e9n J, Westerbergh J et al (2023) High-quality annotations for deep learning enabled plaque analysis in SCAPIS cardiac computed tomography angiography. Heliyon 9:e16058","journal-title":"Heliyon"},{"key":"11410_CR15","doi-asserted-by":"publisher","first-page":"2957","DOI":"10.1177\/02841851231199384","volume":"64","author":"S Skoog","year":"2023","unstructured":"Skoog S, Sandborg M, Henriksson L, Sandstedt M, Gustafsson H, Persson A (2023) A prospective study comparing the quality of coronary computed tomography angiography images from photon counting and energy integrating detector systems. Acta Radiol 64:2957\u20132966","journal-title":"Acta Radiol"},{"key":"11410_CR16","doi-asserted-by":"publisher","first-page":"827","DOI":"10.1016\/0735-1097(90)90282-T","volume":"15","author":"AS Agatston","year":"1990","unstructured":"Agatston AS, Janowitz WR, Hildner FJ, Zusmer NR, Viamonte Jr M, Detrano R (1990) Quantification of coronary artery calcium using ultrafast computed tomography. J Am Coll Cardiol 15:827\u2013832","journal-title":"J Am Coll Cardiol"},{"key":"11410_CR17","doi-asserted-by":"publisher","first-page":"4036","DOI":"10.1109\/TIP.2023.3293771","volume":"32","author":"HY Zhou","year":"2023","unstructured":"Zhou HY, Guo J, Zhang Y et al (2023) nnFormer: volumetric medical image segmentation via a 3D transformer. IEEE Trans Image Process 32:4036\u20134045","journal-title":"IEEE Trans Image Process"},{"key":"11410_CR18","unstructured":"Lakshminarayanan B, Pritzel A, Blundell C (2017) Simple and scalable predictive uncertainty estimation using deep ensembles. Adv Neural Inf Process Syst 30. NIPS"},{"key":"11410_CR19","doi-asserted-by":"publisher","unstructured":"F\u00f6llmer B, Williams MC, Dey D et al (2023) Roadmap on the use of artificial intelligence for imaging of vulnerable atherosclerotic plaque in coronary arteries. Nat Rev Cardiol. https:\/\/doi.org\/10.1038\/s41569-023-00900-3","DOI":"10.1038\/s41569-023-00900-3"}],"container-title":["European Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-025-11410-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00330-025-11410-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-025-11410-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T12:16:10Z","timestamp":1751544970000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00330-025-11410-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,5]]},"references-count":19,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["11410"],"URL":"https:\/\/doi.org\/10.1007\/s00330-025-11410-w","relation":{},"ISSN":["1432-1084"],"issn-type":[{"value":"1432-1084","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,5]]},"assertion":[{"value":"14 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The scientific guarantor of this publication is Dr Ola Hjelmgren.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Guarantor"}},{"value":"The authors of this manuscript declare relationships with the following companies: P.K. is employed by Medis Medical Imaging. The remaining authors declare no conflicts of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Two of the authors have significant statistical expertise (J.A., O.H.).","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Statistics and biometry"}},{"value":"Written informed consent was obtained from all subjects (patients) in this study.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"Institutional Review Board approval was obtained.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":7,"name":"Ethics","group":{"name":"EthicsHeading","label":"Study subjects or cohorts overlap"}},{"order":8,"name":"Ethics","group":{"name":"EthicsHeading","label":"Methodology"}}]}}