{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T03:04:00Z","timestamp":1793847840146,"version":"4.6.1"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T00:00:00Z","timestamp":1721865600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>We developed and externally validated a fully automated algorithm using deep learning to detect large vessel occlusion (LVO) in computed tomography angiography (CTA).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>A total of 2,045 patients with acute ischemic stroke who underwent CTA were included in the development of our model. We validated the algorithm using two separate external datasets: one with 64 patients (external 1) and another with 313 patients (external 2), with ischemic stroke. In the context of current clinical practice, thrombectomy amenable vessel occlusion (TAVO) was defined as an occlusion in the intracranial internal carotid artery (ICA), or in the M1 or M2 segment of the middle cerebral artery (MCA). We employed the U-Net for vessel segmentation on the maximum intensity projection images, followed by the application of the EfficientNetV2 to predict TAVO. The algorithm\u2019s diagnostic performance was evaluated by calculating the area under the receiver operating characteristics curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The mean age in the training and validation dataset was 68.7\u2009\u00b1\u200912.6; 56.3% of participants were men, and 18.0% had TAVO. The algorithm achieved AUC of 0.950 (95% CI, 0.915\u20130.971) in the internal test. For the external datasets 1 and 2, the AUCs were 0.970 (0.897\u20130.997) and 0.971 (0.924\u20130.990), respectively. With a fixed sensitivity of 0.900, the specificities and PPVs for the internal test, external test 1, and external test 2 were 0.891, 0.796, and 0.930, and 0.665, 0.583, and 0.667, respectively. The algorithm demonstrated a sensitivity and specificity of approximately 0.95 in both internal and external datasets, specifically for cases involving intracranial ICA or M1-MCA occlusion. However, the diagnostic performance was somewhat reduced for isolated M2-MCA occlusion; the AUC for the internal and combined external datasets were 0.903 (0.812\u20130.944) and 0.916 (0.816\u20130.963), respectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>We developed and externally validated a fully automated algorithm that identifies TAVO. Further research is needed to evaluate its effectiveness in real-world clinical settings. This validated algorithm has the potential to assist early-career physicians, thereby streamlining the treatment process for patients who can benefit from endovascular treatment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2024.1442025","type":"journal-article","created":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T00:31:15Z","timestamp":1721867475000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Automated identification of thrombectomy amenable vessel occlusion on computed tomography angiography using deep learning"],"prefix":"10.3389","volume":"15","author":[{"given":"Jung Hoon","family":"Han","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sue Young","family":"Ha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hoyeon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gi-Hun","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hotak","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongmin","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jae Guk","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joon-Tae","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leonard","family":"Sunwoo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi Kyung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wi-Sun","family":"Ryu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,7,25]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"708","DOI":"10.1056\/NEJMoa1713973","article-title":"Thrombectomy for stroke at 6 to 16 hours with selection by perfusion imaging","volume":"378","author":"Albers","year":"2018","journal-title":"N Engl J Med"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1056\/NEJMoa1706442","article-title":"Thrombectomy 6 to 24 hours after stroke with a mismatch between deficit and infarct","volume":"378","author":"Nogueira","year":"2018","journal-title":"N Engl J Med"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1423","DOI":"10.1161\/STROKEAHA.121.033528","article-title":"Should primary stroke centers perform advanced imaging?","volume":"53","author":"Hill","year":"2022","journal-title":"Stroke"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1001\/jamaneurol.2021.4082","article-title":"Noncontrast computed tomography vs computed tomography perfusion or magnetic resonance imaging selection in late presentation of stroke with large-vessel occlusion","volume":"79","author":"Nguyen","year":"2022","journal-title":"JAMA Neurol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1348","DOI":"10.1161\/STROKEAHA.121.034331","article-title":"Thrombectomy with and without computed tomography perfusion imaging in the early time window: a pooled analysis of patient-level data","volume":"53","author":"Jadhav","year":"2022","journal-title":"Stroke"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e347","DOI":"10.3346\/jkms.2020.35.e347","article-title":"Routing to endovascular treatment of ischemic stroke in Korea: recognition of need for process improvement","volume":"35","author":"Kang","year":"2020","journal-title":"J Korean Med Sci"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"110845","DOI":"10.1016\/j.ejrad.2023.110845","article-title":"Automated occlusion detection for the diagnosis of acute ischemic stroke: a detailed performance review","volume":"164","author":"Werdiger","year":"2023","journal-title":"Eur J Radiol"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"794","DOI":"10.1136\/neurintsurg-2021-017842","article-title":"Diagnostic performance of an algorithm for automated large vessel occlusion detection on CT angiography","volume":"14","author":"Luijten","year":"2022","journal-title":"J Neurointervention Surg"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"2315","DOI":"10.3389\/fneur.2022.1026609","article-title":"Head-to-head comparison of commercial artificial intelligence solutions for detection of large vessel occlusion at a comprehensive stroke center","volume":"13","author":"Schlossman","year":"2022","journal-title":"Front Neurol"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1136\/neurintsurg-2017-013371","article-title":"A population-based incidence of M2 strokes indicates potential expansion of large vessel occlusions amenable to endovascular therapy","volume":"10","author":"Rai","year":"2018","journal-title":"J NeuroIntervention Surg"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1136\/neurintsurg-2015-012191","article-title":"What constitutes the M1 segment of the middle cerebral artery?","volume":"8","author":"Goyal","year":"2016","journal-title":"J NeuroIntervention Surg"},{"key":"ref12","author":"Hocking","year":"2013"},{"key":"ref13","author":"Szegedy","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1148\/radiographics.17.2.9084083","article-title":"Use of maximum intensity projections in CT angiography: a basic review","volume":"17","author":"Prokop","year":"1997","journal-title":"Radiographics"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"105395","DOI":"10.1016\/j.cmpb.2020.105395","article-title":"DENSE-INception U-net for medical image segmentation","volume":"192","author":"Zhang","year":"2020","journal-title":"Comput Methods Prog Biomed"},{"key":"ref16","author":"Tan","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"125","DOI":"10.3390\/info11020125","article-title":"Albumentations: fast and flexible image augmentations","volume":"11","author":"Buslaev","year":"2020","journal-title":"Information"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1097\/01.ede.0000147512.81966.ba","article-title":"Optimal cut-point and its corresponding Youden index to discriminate individuals using pooled blood samples","volume":"16","author":"Schisterman","year":"2005","journal-title":"Epidemiology"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1136\/neurintsurg-2021-018391","article-title":"AI software detection of large vessel occlusion stroke on CT angiography: a real-world prospective diagnostic test accuracy study","volume":"15","author":"Matsoukas","year":"2023","journal-title":"J Neurointervention Surg"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1651","DOI":"10.1161\/STROKEAHA.121.036091","article-title":"Machine learning automated detection of large vessel occlusion from mobile stroke unit computed tomography angiography","volume":"53","author":"Czap","year":"2022","journal-title":"Stroke"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"106753","DOI":"10.1016\/j.jstrokecerebrovasdis.2022.106753","article-title":"End-to-end artificial intelligence platform for the management of large vessel occlusions: a preliminary study","volume":"31","author":"Meng","year":"2022","journal-title":"J Stroke Cerebrovasc Dis"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"3133","DOI":"10.1161\/STROKEAHA.120.030326","article-title":"Deep learning based software to identify large vessel occlusion on noncontrast computed tomography","volume":"51","author":"Olive-Gadea","year":"2020","journal-title":"Stroke"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"299","DOI":"10.5853\/jos.2022.03692","article-title":"Endovascular treatment of distal-M2 segment occlusions: a clinical registry and Meta-analysis","volume":"25","author":"Bensoussan","year":"2023","journal-title":"J Stroke"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"607","DOI":"10.3174\/ajnr.A6469","article-title":"CT angiography in evaluating large-vessel occlusion in acute anterior circulation ischemic stroke: factors associated with diagnostic error in clinical practice","volume":"41","author":"Fasen","year":"2020","journal-title":"Am J Neuroradiol"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1161\/STROKEAHA.120.031338","article-title":"Leptomeningeal collateral flow modifies endovascular treatment efficacy on large-vessel occlusion strokes","volume":"52","author":"Garc\u00eda-Tornel","year":"2021","journal-title":"Stroke"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"2886","DOI":"10.1161\/STROKEAHA.115.010264","article-title":"Routing ambulances to designated centers increases access to stroke center care and enrollment in prehospital research","volume":"46","author":"Sanossian","year":"2015","journal-title":"Stroke"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"2863","DOI":"10.1161\/01.STR.0000251852.07152.63","article-title":"Time is brain","volume":"37","author":"Furlan","year":"2006","journal-title":"Am Heart Assoc"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"105","DOI":"10.5853\/jos.2014.16.3.105","article-title":"Research on intracranial atherosclerosis from the east and west: why are the results different?","volume":"16","author":"Kim","year":"2014","journal-title":"J Stroke"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"3001","DOI":"10.1161\/STROKEAHA.109.552513","article-title":"Collateral vessels on CT angiography predict outcome in acute ischemic stroke","volume":"40","author":"Maas","year":"2009","journal-title":"Stroke"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2024.1442025\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T00:31:18Z","timestamp":1721867478000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2024.1442025\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,25]]},"references-count":30,"alternative-id":["10.3389\/fneur.2024.1442025"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2024.1442025","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.05.07.24306974","asserted-by":"object"}]},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,25]]},"article-number":"1442025"}}