{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T03:19:51Z","timestamp":1792984791708,"version":"4.5.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100006390","name":"University of Lausanne","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100006390","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>\n                  <jats:p>Non\u2013ST-elevation acute coronary syndrome (NSTE-ACS) remains a diagnostic challenge, as a proportion of patients do not present with obstructive coronary lesions. Coronary computed tomography angiography (CCTA) has emerged as a non-invasive tool for coronary assessment, and integrating artificial intelligence (AI) may enhance its diagnostic accuracy. This study evaluates a machine learning (ML) model using a learned fusion approach to identify culprit lesions in high-risk NSTE-ACS patients.\u00a0This study is a sub-analysis of a prospective, multicenter trial including patients with high-risk NSTE-ACS who underwent CCTA, followed by ICA and fractional flow reserve (FFR) assessment in every intermediate stenosis. An ML framework was developed to analyze 2 orthogonal CCTA views of each coronary segment and classify them as culprit or non-culprit, with ICA +\/- FFR as gold standards. The model was trained using 5-fold cross-validation and compared against 5 baseline methods, including conventional feature extraction and FFR-CT.\u00a0Among 80 patients, 514 coronary segments were analyzed, with 63 (12.3%) labeled as culprit. The learned fusion model achieved a sensitivity of 0.55\u2009\u00b1\u20090.14, specificity of 0.93\u2009\u00b1\u20090.05, and F1-score of 0.53\u2009\u00b1\u20090.11. The AUC was 0.84\u2009\u00b1\u20090.06, matching the performance of FFR-CT (AUC of 0.82\u2009\u00b1\u20090.08).\u00a0Our findings demonstrate that the learned fusion approach, based on combining two orthogonal views, achieved a performance level comparable to that of FFR-CT, as shown by the AUC of both techniques. These results confirm that AI-driven CCTA analysis could enhance clinical decision-making in high-risk NSTE-ACS patients, warranting further validation of this method in larger cohorts.<\/jats:p>\n                  <jats:p>\n                    <jats:bold>Graphical abstract<\/jats:bold>\n                  <\/jats:p>\n                  <jats:p>CCTA: coronary computed tomography angiography, FFR: fractional flow reserve, ICA: invasive coronary angiogram, NSTE-ACS: non-ST-elevation acute coronary syndrome PPV: positive predictive value<\/jats:p>","DOI":"10.1007\/s10554-025-03523-6","type":"journal-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T03:30:40Z","timestamp":1759980640000},"page":"543-549","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["AI-Driven multi-view learning from CCTA for myocardial infarction diagnosis"],"prefix":"10.1007","volume":"42","author":[{"given":"Jakub","family":"Gwizdala","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adil","family":"Salihu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ortal","family":"Senouf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Meier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Rotzinger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salah","family":"Qanadli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivier","family":"Muller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pascal","family":"Frossard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emmanuel","family":"Abbe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dorina","family":"Thanou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephane","family":"Fournier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Denise","family":"Auberson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,9]]},"reference":[{"key":"3523_CR1","unstructured":"Collet JP, ESC Scientific Document Group et al (2021) 2020 ESC guidelines for the management of acute coronary syndromes in patients presenting without persistent ST-segment elevation. Rev Esp Cardiol (Engl Ed) 74(6):544"},{"issue":"38","key":"3523_CR2","doi-asserted-by":"publisher","first-page":"3720","DOI":"10.1093\/eurheartj\/ehad191","volume":"44","author":"RA Byrne","year":"2023","unstructured":"Byrne RA et al (2023) 2023 ESC guidelines for the management of acute coronary syndromes. Eur Heart J 44(38):3720\u20133826","journal-title":"Eur Heart J"},{"key":"3523_CR3","doi-asserted-by":"crossref","unstructured":"Vrints C et al (2024) 2024 ESC guidelines for the management of chronic coronary syndromes. Eur Heart J 45(36):3415\u20133537.","DOI":"10.1093\/eurheartj\/ehae177"},{"issue":"12","key":"3523_CR4","doi-asserted-by":"publisher","first-page":"2447","DOI":"10.1007\/s10554-024-03274-w","volume":"40","author":"G Sarto","year":"2024","unstructured":"Sarto G et al (2024) Management of acute chest pain in the emergency department: benefits of coronary computed tomography angiography. Int J Cardiovasc Imaging 40(12):2447\u20132457","journal-title":"Int J Cardiovasc Imaging"},{"key":"3523_CR5","volume":"8","author":"V Gorenoi","year":"2012","unstructured":"Gorenoi V, Schonermark MP, Hagen A (2012) CT coronary angiography vs. invasive coronary angiography in CHD. GMS Health Technol Assess 8:Doc02","journal-title":"GMS Health Technol Assess"},{"issue":"12","key":"3523_CR6","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1016\/j.jacc.2013.11.043","volume":"63","author":"BL Norgaard","year":"2014","unstructured":"Norgaard BL et al (2014) Diagnostic performance of noninvasive fractional flow reserve derived from coronary computed tomography angiography in suspected coronary artery disease: the NXT trial (Analysis of coronary blood flow using CT angiography: next Steps). J Am Coll Cardiol 63(12):1145\u20131155","journal-title":"J Am Coll Cardiol"},{"issue":"1","key":"3523_CR7","doi-asserted-by":"publisher","first-page":"73","DOI":"10.4244\/EIJ-D-24-00779","volume":"21","author":"D Meier","year":"2025","unstructured":"Meier D et al (2025) Usefulness of FFR-CT to exclude haemodynamically significant lesions in high-risk NSTE-ACS. EuroIntervention 21(1):73\u201381","journal-title":"EuroIntervention"},{"issue":"11","key":"3523_CR8","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/s12471-024-01901-8","volume":"32","author":"RLM van Herten","year":"2024","unstructured":"van Herten RLM et al (2024) The role of artificial intelligence in coronary CT angiography. Neth Heart J 32(11):417\u2013425","journal-title":"Neth Heart J"},{"issue":"40","key":"3523_CR9","doi-asserted-by":"publisher","first-page":"4291","DOI":"10.1093\/eurheartj\/ehae465","volume":"45","author":"TF Luscher","year":"2024","unstructured":"Luscher TF (2024) Artificial intelligence in cardiovascular medicine: clinical applications. Eur Heart J 45(40):4291\u20134304","journal-title":"Eur Heart J"},{"key":"3523_CR10","doi-asserted-by":"publisher","DOI":"10.1136\/openhrt-2022-002237","author":"T Mahendiran","year":"2023","unstructured":"Mahendiran T (2023) Deep learning-based prediction of future myocardial infarction using invasive coronary angiography: a feasibility study. Open Heart 2023;10:e002237 https:\/\/doi.org\/10.1136\/openhrt-2022-002237","journal-title":"Open Heart"},{"key":"3523_CR11","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1109\/OJEMB.2024.3403948","volume":"5","author":"ID Sievering","year":"2024","unstructured":"Sievering ID et al (2024) Anatomy-informed multimodal learning for myocardial infarction prediction. IEEE Open J Eng Med Biol 5:837\u2013845","journal-title":"IEEE Open J Eng Med Biol"},{"issue":"12","key":"3523_CR12","doi-asserted-by":"publisher","first-page":"2429","DOI":"10.1007\/s10554-020-01929-y","volume":"36","author":"V Brandt","year":"2020","unstructured":"Brandt V et al (2020) Ischemia and outcome prediction by cardiac CT based machine learning. Int J Cardiovasc Imaging 36(12):2429\u20132439","journal-title":"Int J Cardiovasc Imaging"},{"issue":"6","key":"3523_CR13","doi-asserted-by":"publisher","first-page":"1209","DOI":"10.1007\/s10554-023-02824-y","volume":"39","author":"R Adolf","year":"2023","unstructured":"Adolf R et al (2023) Convolutional neural networks on risk stratification of patients with suspected coronary artery disease undergoing coronary computed tomography angiography. Int J Cardiovasc Imaging 39(6):1209\u20131216","journal-title":"Int J Cardiovasc Imaging"},{"key":"3523_CR14","unstructured":"Ilse M, Tomczak JM, Welling M (2018) Attention-based Deep Multiple Instance Learning. In Proceedings of the 35th International Conference on Machine Learning, volume 80: pp. 2127\u20132136"},{"key":"3523_CR15","unstructured":"Pang G, Ding C, Shen C, Hengel AV (2021) Explainable Deep Few-shot Anomaly Detection with Deviation Networks. arXiv"},{"key":"3523_CR16","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.media.2019.01.012","volume":"53","author":"J Schlemper","year":"2019","unstructured":"Schlemper J et al (2019) Attention gated networks: learning to leverage salient regions in medical images. Med Image Anal 53:197\u2013207","journal-title":"Med Image Anal"},{"key":"3523_CR17","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2018) Deep Residual Learning for Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, : pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2","key":"3523_CR18","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","volume":"42","author":"TY Lin","year":"2020","unstructured":"Lin TY et al (2020) Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell 42(2):318\u2013327","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"5","key":"3523_CR19","first-page":"051809","volume":"10","author":"J Singh","year":"2023","unstructured":"Singh J et al (2023) Batch-balanced focal loss: a hybrid solution to class imbalance in deep learning. J Med Imaging (Bellingham) 10(5):051809","journal-title":"J Med Imaging (Bellingham)"},{"issue":"2","key":"3523_CR20","doi-asserted-by":"publisher","first-page":"636","DOI":"10.1007\/s12325-024-03060-z","volume":"42","author":"S Nie","year":"2025","unstructured":"Nie S et al (2025) Machine learning applications in acute coronary syndrome: diagnosis, outcomes and management. Adv Ther 42(2):636\u2013665","journal-title":"Adv Ther"},{"issue":"2","key":"3523_CR21","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.jcmg.2021.10.020","volume":"16","author":"WF Griffin","year":"2023","unstructured":"Griffin WF (2023) AI evaluation of stenosis on coronary CTA, comparison with quantitative coronary angiography and fractional flow reserve: a CREDENCE trial substudy. JACC Cardiovasc Imaging 16(2):193\u2013205","journal-title":"JACC Cardiovasc Imaging"},{"key":"3523_CR22","doi-asserted-by":"publisher","DOI":"10.1117\/12.2512168","author":"Y Hong","year":"2019","unstructured":"Hong Y (2019) Deep learning-based stenosis quantification from coronary CT angiography. Proc SPIE Int Soc Opt Eng 10949:109492I https:\/\/doi.org\/10.1117\/12.2512168","journal-title":"Proc SPIE Int Soc Opt Eng"},{"key":"3523_CR23","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.media.2016.04.004","volume":"34","author":"JM Wolterink","year":"2016","unstructured":"Wolterink JM et al (2016) Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks. Med Image Anal 34:123\u2013136","journal-title":"Med Image Anal"},{"issue":"12","key":"3523_CR24","doi-asserted-by":"publisher","first-page":"2403","DOI":"10.1007\/s10554-020-01926-1","volume":"36","author":"D Opincariu","year":"2020","unstructured":"Opincariu D et al (2020) From CT to artificial intelligence for complex assessment of plaque-associated risk. Int J Cardiovasc Imaging 36(12):2403\u20132427","journal-title":"Int J Cardiovasc Imaging"},{"key":"3523_CR25","doi-asserted-by":"publisher","first-page":"4322","DOI":"10.1109\/TMI.2020.3017275","volume":"39","author":"D Zhang","year":"2020","unstructured":"Zhang D, Yang G, Zhao S, Zhang Y, Ghista D, Zhang H, Li S (2020) Direct quantification of coronary artery stenosis through hierarchical attentive multi-view learning. IEEE Trans Med Imaging 39:4322\u20134334","journal-title":"IEEE Trans Med Imaging"},{"issue":"7","key":"3523_CR26","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","journal-title":"IEEE Trans Med Imaging"},{"key":"3523_CR27","doi-asserted-by":"crossref","unstructured":"Ma XH et al Transformer Network for Significant Stenosis Detection in CCTA of Coronary Arteries. Medical Image Computing and Computer Assisted Intervention - Miccai 2021, Pt Vi, 2021. 12906: pp. 516\u2013525","DOI":"10.1007\/978-3-030-87231-1_50"},{"key":"3523_CR28","first-page":"p593","volume":"11767","author":"F Denzinger","year":"2019","unstructured":"Denzinger F et al (2019) Coronary artery plaque characterization from CCTA scans using deep learning and radiomics. Med Image Comput Comput Assist Intervention - Miccai 2019 Pt Iv 11767:p593\u2013601","journal-title":"Med Image Comput Comput Assist Intervention - Miccai 2019 Pt Iv"}],"container-title":["The International Journal of Cardiovascular Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10554-025-03523-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10554-025-03523-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10554-025-03523-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T05:29:39Z","timestamp":1773379779000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10554-025-03523-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,9]]},"references-count":28,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["3523"],"URL":"https:\/\/doi.org\/10.1007\/s10554-025-03523-6","relation":{},"ISSN":["1875-8312"],"issn-type":[{"value":"1875-8312","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,9]]},"assertion":[{"value":"21 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}