{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T02:09:14Z","timestamp":1792807754571,"version":"4.5.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T00:00:00Z","timestamp":1685491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T00:00:00Z","timestamp":1685491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004410","name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu","doi-asserted-by":"publisher","award":["118C353"],"award-info":[{"award-number":["118C353"]}],"id":[{"id":"10.13039\/501100004410","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The use of deep learning (DL) techniques for automated diagnosis of large vessel occlusion (LVO) and collateral scoring on computed tomography angiography (CTA) is gaining attention. In this study, a state-of-the-art self-configuring object detection network called nnDetection was used to detect LVO and assess collateralization on CTA scans using a multi-task 3D object detection approach. The model was trained on single-phase CTA scans of 2425 patients at five centers, and its performance was evaluated on an external test set of 345 patients from another center. Ground-truth labels for the presence of LVO and collateral scores were provided by three radiologists. The nnDetection model achieved a diagnostic accuracy of 98.26% (95% CI 96.25\u201399.36%) in identifying LVO, correctly classifying 339 out of 345 CTA scans in the external test set. The DL-based collateral scores had a kappa of 0.80, indicating good agreement with the consensus of the radiologists. These results demonstrate that the self-configuring 3D nnDetection model can accurately detect LVO on single-phase CTA scans and provide semi-quantitative collateral scores, offering a comprehensive approach for automated stroke diagnostics in patients with LVO.<\/jats:p>","DOI":"10.1038\/s41598-023-33723-w","type":"journal-article","created":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T10:02:41Z","timestamp":1685527361000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Automated LVO detection and collateral scoring on CTA using a 3D self-configuring object detection network: a multi-center study"],"prefix":"10.1038","volume":"13","author":[{"given":"Omer","family":"Bagcilar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deniz","family":"Alis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ceren","family":"Alis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mustafa Ege","family":"Seker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mert","family":"Yergin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmet","family":"Ustundag","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emil","family":"Hikmet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alperen","family":"Tezcan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gokhan","family":"Polat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmet Tugrul","family":"Akkus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fatih","family":"Alper","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Murat","family":"Velioglu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Omer","family":"Yildiz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hakan Hatem","family":"Selcuk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ilkay","family":"Oksuz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Osman","family":"Kizilkilic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ercan","family":"Karaarslan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,5,31]]},"reference":[{"key":"33723_CR1","unstructured":"WHO EMRO|Stroke, Cerebrovascular accident|Health topics. World Health Organization-Regional Office for the Eastern Mediterranean. http:\/\/www.emro.who.int\/health-topics\/stroke-cerebrovascular-accident\/index.html."},{"key":"33723_CR2","doi-asserted-by":"publisher","first-page":"3834","DOI":"10.1161\/STROKEAHA.109.561787","volume":"40","author":"WS Smith","year":"2009","unstructured":"Smith, W. S. et al. Significance of large vessel intracranial occlusion causing acute ischemic stroke and TIA. Stroke 40, 3834\u20133840 (2009).","journal-title":"Stroke"},{"key":"33723_CR3","doi-asserted-by":"publisher","first-page":"2296","DOI":"10.1056\/NEJMoa1503780","volume":"372","author":"TG Jovin","year":"2015","unstructured":"Jovin, T. G. et al. Thrombectomy within 8 hours after symptom onset in ischemic stroke. N. Engl. J. Med. 372, 2296\u20132306 (2015).","journal-title":"N. Engl. J. Med."},{"key":"33723_CR4","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1161\/STROKEAHA.115.011788","volume":"47","author":"OA Berkhemer","year":"2016","unstructured":"Berkhemer, O. A. et al. Collateral status on baseline computed tomographic angiography and intra-arterial treatment effect in patients with proximal anterior circulation stroke. Stroke 47, 768\u2013776 (2016).","journal-title":"Stroke"},{"key":"33723_CR5","doi-asserted-by":"publisher","first-page":"1279","DOI":"10.1001\/jama.2016.13647","volume":"316","author":"JL Saver","year":"2016","unstructured":"Saver, J. L. et al. Time to treatment with endovascular thrombectomy and outcomes from ischemic stroke: A meta-analysis. JAMA 316, 1279\u20131288 (2016).","journal-title":"JAMA"},{"key":"33723_CR6","first-page":"396","volume":"40","author":"MA Almekhlafi","year":"2019","unstructured":"Almekhlafi, M. A. et al. Imaging of patients with suspected large-vessel occlusion at primary stroke centers: Available modalities and a suggested approach. Am. J. Neuroradiol. 40, 396\u2013400 (2019).","journal-title":"Am. J. Neuroradiol."},{"key":"33723_CR7","doi-asserted-by":"publisher","first-page":"1640","DOI":"10.3174\/ajnr.A2564","volume":"32","author":"BK Menon","year":"2011","unstructured":"Menon, B. K. et al. Regional leptomeningeal score on CT angiography predicts clinical and imaging outcomes in patients with acute anterior circulation occlusions. Am. J. Neuroradiol. 32, 1640\u20131645 (2011).","journal-title":"Am. J. Neuroradiol."},{"key":"33723_CR8","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1161\/STROKEAHA.113.004072","volume":"45","author":"DS Liebeskind","year":"2014","unstructured":"Liebeskind, D. S. et al. Collaterals at angiography and outcomes in the Interventional Management of Stroke (IMS) III trial. Stroke 45, 759\u2013764 (2014).","journal-title":"Stroke"},{"key":"33723_CR9","doi-asserted-by":"publisher","first-page":"1528","DOI":"10.1161\/01.STR.30.8.1528","volume":"30","author":"JC Grotta","year":"1999","unstructured":"Grotta, J. C. et al. Agreement and variability in the interpretation of early CT changes in stroke patients qualifying for intravenous rtPA therapy. Stroke 30, 1528\u20131533 (1999).","journal-title":"Stroke"},{"key":"33723_CR10","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1159\/000500076","volume":"47","author":"IQ Grunwald","year":"2019","unstructured":"Grunwald, I. Q. et al. Collateral automation for triage in stroke: Evaluating automated scoring of collaterals in acute stroke on computed tomography scans. Cerebrovasc. Dis. 47, 217\u2013222 (2019).","journal-title":"Cerebrovasc. Dis."},{"key":"33723_CR11","doi-asserted-by":"publisher","first-page":"3001","DOI":"10.1161\/STROKEAHA.109.552513","volume":"40","author":"MB Maas","year":"2009","unstructured":"Maas, M. B. et al. Collateral vessels on CT angiography predict outcome in acute ischemic stroke. Stroke 40, 3001\u20133005 (2009).","journal-title":"Stroke"},{"key":"33723_CR12","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1007\/978-3-319-67564-0_16","volume-title":"Molecular Imaging, Reconstruction and Analysis of Moving Body Organs, and Stroke Imaging and Treatment","author":"Y Xiao","year":"2017","unstructured":"Xiao, Y. et al. Towards automatic collateral circulation score evaluation in ischemic stroke using image decompositions and support vector machines. In Molecular Imaging, Reconstruction and Analysis of Moving Body Organs, and Stroke Imaging and Treatment (eds Cardoso, M. J. et al.) 158\u2013167 (Springer, 2017). https:\/\/doi.org\/10.1007\/978-3-319-67564-0_16."},{"key":"33723_CR13","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1136\/svn-2021-001096","volume":"7","author":"J Wang","year":"2022","unstructured":"Wang, J. et al. Prediction of large vessel occlusion for ischaemic stroke by using the machine learning model random forests. Stroke Vasc. Neurol. 7, 94\u2013100 (2022).","journal-title":"Stroke Vasc. Neurol."},{"key":"33723_CR14","doi-asserted-by":"publisher","first-page":"2790","DOI":"10.1161\/STROKEAHA.119.026259","volume":"50","author":"SA Amukotuwa","year":"2019","unstructured":"Amukotuwa, S. A. et al. Automated detection of intracranial large vessel occlusions on computed tomography angiography: A single center experience. Stroke 50, 2790\u20132798 (2019).","journal-title":"Stroke"},{"key":"33723_CR15","doi-asserted-by":"publisher","first-page":"1074","DOI":"10.3174\/ajnr.A5623","volume":"39","author":"AMM Boers","year":"2018","unstructured":"Boers, A. M. M. et al. Value of quantitative collateral scoring on CT angiography in patients with acute ischemic stroke. Am. J. Neuroradiol. 39, 1074\u20131082 (2018).","journal-title":"Am. J. Neuroradiol."},{"key":"33723_CR16","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1148\/radiol.2020200334","volume":"297","author":"MT Stib","year":"2020","unstructured":"Stib, M. T. et al. Detecting large vessel occlusion at multiphase CT angiography by using a deep convolutional neural network. Radiology 297, 640\u2013649 (2020).","journal-title":"Radiology"},{"key":"33723_CR17","doi-asserted-by":"publisher","first-page":"656112","DOI":"10.3389\/fneur.2021.656112","volume":"12","author":"J McLouth","year":"2021","unstructured":"McLouth, J. et al. Validation of a deep learning tool in the detection of intracranial hemorrhage and large vessel occlusion. Front. Neurol. 12, 656112 (2021).","journal-title":"Front. Neurol."},{"key":"33723_CR18","doi-asserted-by":"publisher","first-page":"5711","DOI":"10.1007\/s00330-022-08627-4","volume":"32","author":"L Wolff","year":"2022","unstructured":"Wolff, L. et al. Diagnostic performance of an algorithm for automated collateral scoring on computed tomography angiography. Eur. Radiol. 32, 5711\u20135718 (2022).","journal-title":"Eur. Radiol."},{"key":"33723_CR19","doi-asserted-by":"publisher","first-page":"1717","DOI":"10.1148\/rg.2019190142","volume":"39","author":"CA Potter","year":"2019","unstructured":"Potter, C. A. et al. CT for treatment selection in acute ischemic stroke: A code stroke primer. Radiographics 39, 1717\u20131738 (2019).","journal-title":"Radiographics"},{"key":"33723_CR20","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1136\/neurintsurg-2015-012191","volume":"8","author":"M Goyal","year":"2016","unstructured":"Goyal, M. et al. What constitutes the M1 segment of the middle cerebral artery?. J. Neurointerv. Surg. 8, 1273\u20131277 (2016).","journal-title":"J. Neurointerv. Surg."},{"key":"33723_CR21","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1002\/ana.21130","volume":"61","author":"JC Tan","year":"2007","unstructured":"Tan, J. C. et al. Systematic comparison of perfusion-CT and CT-angiography in acute stroke patients. Ann. Neurol. 61, 533\u2013543 (2007).","journal-title":"Ann. Neurol."},{"key":"33723_CR22","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.3390\/diagnostics12071562","volume":"12","author":"J Wang","year":"2022","unstructured":"Wang, J. et al. Merging multiphase CTA images and training them simultaneously with a deep learning algorithm could improve the efficacy of AI models for lateral circulation assessment in ischemic stroke. Diagnostics (Basel) 12, 1562 (2022).","journal-title":"Diagnostics (Basel)"},{"key":"33723_CR23","doi-asserted-by":"crossref","unstructured":"Baumgartner, M., Jaeger, P. F., Isensee, F. & Maier-Hein, K. H. nnDetection: A Self-configuring Method for Medical Object Detection, 12905, 530\u2013539 (2021).","DOI":"10.1007\/978-3-030-87240-3_51"},{"key":"33723_CR24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1811.08661","author":"PF Jaeger","year":"2018","unstructured":"Jaeger, P. F. et al. Retina U-Net: Embarrassingly simple exploitation of segmentation supervision for medical object detection. Preprint https:\/\/doi.org\/10.48550\/arXiv.1811.08661 (2018).","journal-title":"Preprint"},{"key":"33723_CR25","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1177\/001316446002000104","volume":"20","author":"J Cohen","year":"1960","unstructured":"Cohen, J. A coefficient of agreement for nominal scales. Educ. Psychol. Measur. 20, 37\u201346 (1960).","journal-title":"Educ. Psychol. Measur."},{"key":"33723_CR26","doi-asserted-by":"publisher","first-page":"2170","DOI":"10.1002\/sim.2677","volume":"26","author":"ND Mercaldo","year":"2007","unstructured":"Mercaldo, N. D., Lau, K. F. & Zhou, X. H. Confidence intervals for predictive values with an emphasis to case-control studies. Stat. Med. 26, 2170\u20132183 (2007).","journal-title":"Stat. Med."},{"key":"33723_CR27","unstructured":"Statistics with Confidence: Confidence Intervals and Statistical Guidelines (BMJ Books, 2011)."},{"key":"33723_CR28","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1186\/s12880-021-00609-0","volume":"21","author":"S Ot\u00e1lora","year":"2021","unstructured":"Ot\u00e1lora, S., Marini, N., M\u00fcller, H. & Atzori, M. Combining weakly and strongly supervised learning improves strong supervision in Gleason pattern classification. BMC Med. Imaging 21, 77 (2021).","journal-title":"BMC Med. Imaging"},{"key":"33723_CR29","doi-asserted-by":"publisher","first-page":"5915","DOI":"10.1038\/s41467-021-26216-9","volume":"12","author":"S Wang","year":"2021","unstructured":"Wang, S. et al. Annotation-efficient deep learning for automatic medical image segmentation. Nat. Commun. 12, 5915 (2021).","journal-title":"Nat. Commun."},{"key":"33723_CR30","doi-asserted-by":"publisher","first-page":"10017","DOI":"10.3390\/app112110017","volume":"11","author":"M Sawicki","year":"2021","unstructured":"Sawicki, M. et al. Diagnostic value of artificial intelligence\u2014based software in detection of large vessel occlusion in acute ischemic stroke. Appl. Sci. 11, 10017 (2021).","journal-title":"Appl. Sci."},{"key":"33723_CR31","doi-asserted-by":"publisher","first-page":"247","DOI":"10.3174\/ajnr.A6923","volume":"42","author":"A Yahav-Dovrat","year":"2021","unstructured":"Yahav-Dovrat, A. et al. Evaluation of artificial intelligence-powered identification of large-vessel occlusions in a comprehensive stroke center. Am. J. Neuroradiol. 42, 247\u2013254 (2021).","journal-title":"Am. J. Neuroradiol."},{"key":"33723_CR32","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.3174\/ajnr.A4746","volume":"37","author":"IR van den Wijngaard","year":"2016","unstructured":"van den Wijngaard, I. R. et al. Assessment of collateral status by dynamic CT angiography in acute MCA stroke: Timing of acquisition and relationship with final infarct volume. Am. J. Neuroradiol. 37, 1231\u20131236 (2016).","journal-title":"Am. J. Neuroradiol."},{"key":"33723_CR33","doi-asserted-by":"publisher","first-page":"984","DOI":"10.1097\/RCT.0000000000001090","volume":"44","author":"F Kauw","year":"2020","unstructured":"Kauw, F. et al. Collateral status in ischemic stroke: A comparison of computed tomography angiography, computed tomography perfusion, and digital subtraction angiography. J. Comput. Assist. Tomogr. 44, 984\u2013992 (2020).","journal-title":"J. Comput. Assist. Tomogr."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-33723-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-33723-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-33723-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T22:02:17Z","timestamp":1685570537000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-33723-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,31]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["33723"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-33723-w","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2428530\/v1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,31]]},"assertion":[{"value":"30 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 May 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"D.A. is the CEO and co-founder of Hevi AI Health Tech. M.Y. is the chief AI scientist and co-founder of Hevi AI Health Tech. Other authors declare no interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"8834"}}