{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T04:41:13Z","timestamp":1791261673406,"version":"4.1.0"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T00:00:00Z","timestamp":1680480000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T00:00:00Z","timestamp":1680480000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005713","name":"Technische Universit\u00e4t M\u00fcnchen","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005713","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Cardiovasc Imaging"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>To assess the prognostic value of convolutional neural networks (CNN) on coronary computed tomography angiography (CCTA) in comparison to conventional computed tomography (CT) reporting and clinical risk scores. 5468 patients who underwent CCTA with suspected coronary artery disease (CAD) were included. Primary endpoint was defined as a composite of all-cause death, myocardial infarction, unstable angina or late revascularization (&gt;\u200990\u00a0days after CCTA). Early revascularization was additionally included as a training endpoint for the CNN algorithm. Cardiovascular risk stratification was based on Morise score and the extent of CAD (eoCAD) as assessed on CCTA. Semiautomatic post-processing was performed for vessel delineation and annotation of calcified and non-calcified plaque areas. Using a two-step training of a DenseNet-121 CNN the entire network was trained with the training endpoint, followed by training the feature layer with the primary endpoint. During a median follow-up of 7.2\u00a0years, the primary endpoint occurred in 334 patients. CNN showed an AUC of 0.631\u2009\u00b1\u20090.015 for prediction of the combined primary endpoint, while combining it with conventional CT and clinical risk scores showed an improvement of AUC from 0.646\u2009\u00b1\u20090.014 (based on eoCAD only) to 0.680\u2009\u00b1\u20090.015 (p\u2009&lt;\u20090.0001) and from 0.619\u2009\u00b1\u20090.0149 (based on Morise Score only) to 0.6812\u2009\u00b1\u20090.0145 (p\u2009&lt;\u20090.0001), respectively. In a stepwise model including all prediction methods, it was found an AUC of 0.680\u2009\u00b1\u20090.0148. CNN analysis showed to improve conventional CCTA-derived and clinical risk stratification when evaluating CCTA of patients with suspected CAD.<\/jats:p>","DOI":"10.1007\/s10554-023-02824-y","type":"journal-article","created":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T12:28:46Z","timestamp":1680524926000},"page":"1209-1216","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Convolutional neural networks on risk stratification of patients with suspected coronary artery disease undergoing coronary computed tomography angiography"],"prefix":"10.1007","volume":"39","author":[{"given":"Rafael","family":"Adolf","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nejva","family":"Nano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessa","family":"Chami","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudio E.","family":"von Schacky","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Albrecht","family":"Will","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eva","family":"Hendrich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan A.","family":"Martinoff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Hadamitzky","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,4,3]]},"reference":[{"issue":"3","key":"2824_CR1","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1093\/eurheartj\/ehz425","volume":"41","author":"J Knuuti","year":"2020","unstructured":"Knuuti J et al (2020) 2019 ESC Guidelines for the diagnosis and management of chronic coronary syndromes. Eur Heart J 41(3):407\u2013477. https:\/\/doi.org\/10.1093\/eurheartj\/ehz425","journal-title":"Eur Heart J"},{"issue":"4","key":"2824_CR2","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1016\/j.jcmg.2012.09.016","volume":"6","author":"K Otsuka","year":"2013","unstructured":"Otsuka K et al (2013) Napkin-ring sign on coronary CT angiography for the prediction of acute coronary syndrome. JACC Cardiovasc Imaging 6(4):448\u2013457. https:\/\/doi.org\/10.1016\/j.jcmg.2012.09.016","journal-title":"JACC Cardiovasc Imaging"},{"issue":"1","key":"2824_CR3","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.jacc.2009.02.068","volume":"54","author":"S Motoyama","year":"2009","unstructured":"Motoyama S et al (2009) Computed tomographic angiography characteristics of atherosclerotic plaques subsequently resulting in acute coronary syndrome. J Am Coll Cardiol 54(1):49\u201357. https:\/\/doi.org\/10.1016\/j.jacc.2009.02.068","journal-title":"J Am Coll Cardiol"},{"issue":"24","key":"2824_CR4","doi-asserted-by":"publisher","first-page":"1975","DOI":"10.1093\/eurheartj\/ehy404","volume":"40","author":"SJ Al'Aref","year":"2019","unstructured":"Al\u2019Aref SJ et al (2019) Clinical applications of machine learning in cardiovascular disease and its relevance to cardiac imaging. Eur Heart J 40(24):1975\u20131986. https:\/\/doi.org\/10.1093\/eurheartj\/ehy404","journal-title":"Eur Heart J"},{"key":"2824_CR5","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCIMAGING.117.006843","author":"M Kolossvary","year":"2017","unstructured":"Kolossvary M et al (2017) Radiomic features are superior to conventional quantitative computed tomographic metrics to identify coronary plaques with napkin-ring sign. Circ Cardiovasc Imaging. https:\/\/doi.org\/10.1161\/CIRCIMAGING.117.006843","journal-title":"Circ Cardiovasc Imaging"},{"issue":"6","key":"2824_CR6","doi-asserted-by":"publisher","first-page":"2655","DOI":"10.1007\/s00330-017-5223-z","volume":"28","author":"D Dey","year":"2018","unstructured":"Dey D et al (2018) Integrated prediction of lesion-specific ischaemia from quantitative coronary CT angiography using machine learning: a multicentre study. Eur Radiol 28(6):2655\u20132664. https:\/\/doi.org\/10.1007\/s00330-017-5223-z","journal-title":"Eur Radiol"},{"issue":"1","key":"2824_CR7","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1038\/s41591-018-0316-z","volume":"25","author":"A Esteva","year":"2019","unstructured":"Esteva A et al (2019) A guide to deep learning in healthcare. Nat Med 25(1):24\u201329. https:\/\/doi.org\/10.1038\/s41591-018-0316-z","journal-title":"Nat Med"},{"issue":"7","key":"2824_CR8","doi-asserted-by":"publisher","first-page":"2113","DOI":"10.1148\/rg.2017170077","volume":"37","author":"G Chartrand","year":"2017","unstructured":"Chartrand G et al (2017) Deep learning: a primer for radiologists. Radiographics 37(7):2113\u20132131. https:\/\/doi.org\/10.1148\/rg.2017170077","journal-title":"Radiographics"},{"key":"2824_CR9","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"G Litjens","year":"2017","unstructured":"Litjens G et al (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60\u201388. https:\/\/doi.org\/10.1016\/j.media.2017.07.005","journal-title":"Med Image Anal"},{"issue":"4","key":"2824_CR10","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1016\/s0002-9343(97)00086-7","volume":"102","author":"AP Morise","year":"1997","unstructured":"Morise AP, Haddad WJ, Beckner D (1997) Development and validation of a clinical score to estimate the probability of coronary artery disease in men and women presenting with suspected coronary disease. Am J Med 102(4):350\u2013356. https:\/\/doi.org\/10.1016\/s0002-9343(97)00086-7","journal-title":"Am J Med"},{"issue":"10","key":"2824_CR11","doi-asserted-by":"publisher","first-page":"2162","DOI":"10.1016\/j.jcmg.2020.03.025","volume":"13","author":"SJ Al'Aref","year":"2020","unstructured":"Al\u2019Aref SJ et al (2020) A boosted ensemble algorithm for determination of plaque stability in high-risk patients on coronary CTA. JACC Cardiovasc Imaging 13(10):2162\u20132173. https:\/\/doi.org\/10.1016\/j.jcmg.2020.03.025","journal-title":"JACC Cardiovasc Imaging"},{"issue":"7","key":"2824_CR12","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1093\/eurheartj\/ehw188","volume":"38","author":"M Motwani","year":"2017","unstructured":"Motwani M et al (2017) Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis. Eur Heart J 38(7):500\u2013507. https:\/\/doi.org\/10.1093\/eurheartj\/ehw188","journal-title":"Eur Heart J"},{"key":"2824_CR13","unstructured":"Bauer MJ et al (2021) Machine learning for time-to-event analysis in patients with suspected coronary artery disease: increased long-term prognostic value of coronary CT angiography-derived measures and clinical parameters. Abstract"},{"issue":"4","key":"2824_CR14","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 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(4):e256\u2013e265. https:\/\/doi.org\/10.1016\/S2589-7500(22)00022-X","journal-title":"Lancet Digit Health"},{"issue":"7","key":"2824_CR15","doi-asserted-by":"publisher","first-page":"1588","DOI":"10.1109\/TMI.2018.2883807","volume":"38","author":"M Zreik","year":"2019","unstructured":"Zreik M et al (2019) A recurrent CNN for automatic detection and classification of coronary artery plaque and stenosis in coronary CT angiography. IEEE Trans Med Imaging 38(7):1588\u20131598. https:\/\/doi.org\/10.1109\/TMI.2018.2883807","journal-title":"IEEE Trans Med Imaging"},{"key":"2824_CR16","doi-asserted-by":"publisher","unstructured":"Van Stralen P et al (2023) Stenosis detection in X-ray coronary angiography with deep neural networks leveraged by attention mechanisms. In: Proceedings of the 9th International Conference on Bioinformatics Research and Applications (ICBRA '22), pp 123\u2013128. https:\/\/doi.org\/10.1145\/3569192.3569212","DOI":"10.1145\/3569192.3569212"},{"key":"2824_CR17","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2023.944135","volume":"10","author":"C Cong","year":"2023","unstructured":"Cong C et al (2023) Deep learning-based end-to-end automated stenosis classification and localization on catheter coronary angiography. Front Cardiovasc Med 10:944135. https:\/\/doi.org\/10.3389\/fcvm.2023.944135","journal-title":"Front Cardiovasc Med"},{"issue":"1","key":"2824_CR18","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1148\/radiol.2020190925","volume":"295","author":"CE von Schacky","year":"2020","unstructured":"von Schacky CE et al (2020) Development and validation of a multitask deep learning model for severity grading of hip osteoarthritis features on radiographs. Radiology 295(1):136\u2013145. https:\/\/doi.org\/10.1148\/radiol.2020190925","journal-title":"Radiology"},{"issue":"12","key":"2824_CR19","doi-asserted-by":"publisher","first-page":"8704","DOI":"10.1109\/TPAMI.2019.2918284","volume":"44","author":"G Huang","year":"2022","unstructured":"Huang G et al (2022) Convolutional networks with dense connectivity. IEEE Trans Pattern Anal Mach Intell 44(12):8704\u20138716. https:\/\/doi.org\/10.1109\/TPAMI.2019.2918284","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"2824_CR20","doi-asserted-by":"publisher","DOI":"10.1136\/openhrt-2014-000234","volume":"2","author":"MC Williams","year":"2015","unstructured":"Williams MC et al (2015) Observer variability in the assessment of CT coronary angiography and coronary artery calcium score: substudy of the Scottish computed Tomography of the HEART (SCOT-HEART) trial. Open Heart 2(1):e000234. https:\/\/doi.org\/10.1136\/openhrt-2014-000234","journal-title":"Open Heart"},{"issue":"2","key":"2824_CR21","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.cjco.2021.09.022","volume":"4","author":"GBJ Mancini","year":"2022","unstructured":"Mancini GBJ et al (2022) Measurement of plaque characteristics using coronary computed tomography angiography: achieving high interobserver performance. CJC Open 4(2):189\u2013196. https:\/\/doi.org\/10.1016\/j.cjco.2021.09.022","journal-title":"CJC Open"},{"issue":"4","key":"2824_CR22","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1016\/j.jcct.2020.12.008","volume":"15","author":"MN Meah","year":"2021","unstructured":"Meah MN et al (2021) Reproducibility of quantitative plaque measurement in advanced coronary artery disease. J Cardiovasc Comput Tomogr 15(4):333\u2013338. https:\/\/doi.org\/10.1016\/j.jcct.2020.12.008","journal-title":"J Cardiovasc Comput Tomogr"}],"container-title":["The International Journal of Cardiovascular Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10554-023-02824-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10554-023-02824-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10554-023-02824-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,27]],"date-time":"2023-05-27T03:44:21Z","timestamp":1685159061000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10554-023-02824-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,3]]},"references-count":22,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["2824"],"URL":"https:\/\/doi.org\/10.1007\/s10554-023-02824-y","relation":{},"ISSN":["1875-8312"],"issn-type":[{"value":"1875-8312","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,3]]},"assertion":[{"value":"27 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Dr. Martinoff reports receiving unrestricted research grants from Siemens Healthinieers, all other authors have no conflict of interest to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The study was approved by the local ethics committee.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Written informed consent was obtained from all individual participants prior to CT scan.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}