{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:11:05Z","timestamp":1792782665874,"version":"4.5.0"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:00:00Z","timestamp":1780531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:00:00Z","timestamp":1780531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Universit\u00e4t Ulm","id":[{"id":"https:\/\/ror.org\/032000t02","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neuroradiology"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Digital subtraction angiography (DSA) interpretation is observer dependent. This study evaluated the diagnostic performance of an existing deep-learning (DL) based thrombus classifier prior to clinical application. The intended use of the model is as a clinical decision-support tool to assist neuroradiological assessment during mechanical recanalization.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study included an in-house dataset of DSA image series from endovascular recanalization procedures for anterior circulation occlusions collected over two years. For each case, two DSA runs were selected: one before and one after recanalization. The artificial intelligence system was applied to classify thrombus presence. Diagnostic performance was assessed using sensitivity, specificity, and false-positive rate.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 1,236 DSA series from 309 patients were analyzed, yielding 618 paired biplane acquisitions. The DL classifier achieved an overall sensitivity of 71.7% (95% CI 67.3\u201375.8%), with the highest sensitivity for proximal vessel occlusions (M1\/M2 segments: 87.6%; 95% CI 83.6\u201390.9%) and substantially lower sensitivity for distal occlusions (M3\/M4 segments: 23.1%; 95% CI 14.9\u201333.1%) as well as for occlusions of the anterior cerebral artery (27.3%; 95% CI 10.7\u201350.2%). Overall specificity for thrombus detection was 89.8% (149\/166) (95% CI: 84.1\u201393.9%), corresponding to 17 false-positive classifications.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The developed DL classifier on DSA series confirmed on a large-scale dataset its very high sensitivity to proximal vessel occlusions with a sensitivity of 87.6%. Sensitivity for distal vessel occlusions was very low. Training the system for these lesion types will be the next step prior to clinical application.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00234-026-04046-0","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T02:02:25Z","timestamp":1780538545000},"page":"2927-2933","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Validation of a deep-learning based thrombus classifier on digital subtraction angiography using a large-scale dataset"],"prefix":"10.1007","volume":"68","author":[{"given":"Johannes","family":"Rosskopf","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aliye","family":"Yazilitas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah","family":"Elfeel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timo","family":"Baumg\u00e4rtner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alfred Michael","family":"Franz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Mueller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Ertl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernd","family":"Schmitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katharina","family":"Althaus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,4]]},"reference":[{"issue":"14","key":"4046_CR1","doi-asserted-by":"publisher","first-page":"1374","DOI":"10.1056\/NEJMoa2408954","volume":"392","author":"M Psychogios","year":"2025","unstructured":"Psychogios M, Brehm A, Ribo M, Rizzo F, Strbian D, R\u00e4ty S et al (2025) Endovascular Treatment for Stroke Due to Occlusion of Medium or Distal Vessels. N Engl J Med 392(14):1374\u20131384","journal-title":"N Engl J Med"},{"issue":"18","key":"4046_CR2","doi-asserted-by":"publisher","first-page":"1677","DOI":"10.1056\/NEJMoa2314063","volume":"390","author":"V Costalat","year":"2024","unstructured":"Costalat V, Jovin TG, Albucher JF, Cognard C, Henon H, Nouri N et al (2024) Trial of Thrombectomy for Stroke with a Large Infarct of Unrestricted Size. N Engl J Med 390(18):1677\u20131689","journal-title":"N Engl J Med"},{"issue":"10029","key":"4046_CR3","doi-asserted-by":"publisher","first-page":"1723","DOI":"10.1016\/S0140-6736(16)00163-X","volume":"387","author":"M Goyal","year":"2016","unstructured":"Goyal M, Menon BK, van Zwam WH, Dippel DWJ, Mitchell PJ, Demchuk AM et al (2016) Endovascular thrombectomy after large-vessel ischaemic stroke: a meta-analysis of individual patient data from five randomised trials. Lancet 387(10029):1723\u20131731","journal-title":"Lancet"},{"issue":"8","key":"4046_CR4","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1136\/jnis-2024-021892","volume":"17","author":"PM van der Sluijs","year":"2025","unstructured":"van der Sluijs PM, Su R, Cornelissen S, van Es ACGM, Lycklama A, Nijeholt GJ, van Doormaal PJ et al (2025) Assessment of automated TICI scoring during endovascular treatment in patients with an ischemic stroke. J Neurointerv Surg 17(8):830\u2013836","journal-title":"J Neurointerv Surg"},{"issue":"1","key":"4046_CR5","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1186\/s41747-024-00452-2","volume":"8","author":"P Glielmo","year":"2024","unstructured":"Glielmo P, Fusco S, Gitto S, Zantonelli G, Albano D, Messina C et al (2024) Artificial intelligence in interventional radiology: state of the art. Eur Radiol Exp 8(1):62","journal-title":"Eur Radiol Exp"},{"issue":"11","key":"4046_CR6","doi-asserted-by":"publisher","first-page":"3497","DOI":"10.1161\/STROKEAHA.120.033807","volume":"52","author":"M Nielsen","year":"2021","unstructured":"Nielsen M, Waldmann M, Fr\u00f6lich AM, Flottmann F, Hristova E, Bendszus M et al (2021) Deep Learning-Based Automated Thrombolysis in Cerebral Infarction Scoring: A Timely Proof-of-Principle Study. Stroke 52(11):3497\u20133504","journal-title":"Stroke"},{"issue":"6","key":"4046_CR7","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1136\/neurintsurg-2021-018638","volume":"15","author":"J Khankari","year":"2023","unstructured":"Khankari J, Yu Y, Ouyang J, Hussein R, Do HM, Heit JJ et al (2023) Automated detection of arterial landmarks and vascular occlusions in patients with acute stroke receiving digital subtraction angiography using deep learning. J Neurointerv Surg 15(6):521\u2013525","journal-title":"J Neurointerv Surg"},{"key":"4046_CR8","doi-asserted-by":"crossref","unstructured":"Ibrahim MK, Shehata MA, Ghozy S, Bilgin C, Jabal MS, Heiferman DM et al (2023) Operator assessment versus core laboratory adjudication of recanalization following endovascular treatment of acute ischemic stroke: a systematic review and meta-analysis. J Neurointerv Surg. ;15(2):133 LP \u2013 138","DOI":"10.1136\/jnis-2022-019266"},{"issue":"5","key":"4046_CR9","doi-asserted-by":"publisher","first-page":"972","DOI":"10.3174\/ajnr.A2896","volume":"33","author":"M Bar","year":"2012","unstructured":"Bar M, Mikulik R, Jonszta T, Krajina A, Roubec M, Skoloudik D et al (2012) Diagnosis of recanalization of the intracranial artery has poor inter-rater reliability. AJNR Am J Neuroradiol 33(5):972\u2013974","journal-title":"AJNR Am J Neuroradiol"},{"issue":"8","key":"4046_CR10","doi-asserted-by":"publisher","first-page":"1441","DOI":"10.3174\/ajnr.A6696","volume":"41","author":"DM Heiferman","year":"2020","unstructured":"Heiferman DM, Pecoraro NC, Wozniak AW, Ebersole KC, Jimenez LM, Reynolds MR et al (2020) Reliability of the Modified TICI Score among Endovascular Neurosurgeons. AJNR Am J Neuroradiol 41(8):1441\u20131446","journal-title":"AJNR Am J Neuroradiol"},{"issue":"2","key":"4046_CR11","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1177\/1747493020909632","volume":"16","author":"H Prasetya","year":"2021","unstructured":"Prasetya H, Ramos LA, Epema T, Treurniet KM, Emmer BJ, van den Wijngaard IR et al (2021) qTICI: Quantitative assessment of brain tissue reperfusion on digital subtraction angiograms of acute ischemic stroke patients. Int J stroke Off J Int Stroke Soc 16(2):207\u2013216","journal-title":"Int J stroke Off J Int Stroke Soc"},{"key":"4046_CR12","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/978-3-030-59725-2_9","volume-title":"Medical Image Computing and Computer Assisted Intervention - - MICCAI 2020","author":"M Nielsen","year":"2020","unstructured":"Nielsen M, Waldmann M, Sentker T, Fr\u00f6lich A, Fiehler J, Werner R (2020) Time Matters: Handling Spatio-Temporal Perfusion Information for Automated TICI Scoring. In: Martel AL, Abolmaesumi P, Stoyanov D, Mateus D, Zuluaga MA, Zhou SK et al (eds) Medical Image Computing and Computer Assisted Intervention -- MICCAI 2020. Springer International Publishing, Cham, pp 86\u201396"},{"issue":"9","key":"4046_CR13","doi-asserted-by":"publisher","first-page":"2380","DOI":"10.1109\/TMI.2021.3077113","volume":"40","author":"R Su","year":"2021","unstructured":"Su R, Cornelissen SAP, van der Sluijs M, van Es ACGM, van Zwam WH, Dippel DWJ et al (2021) autoTICI: Automatic Brain Tissue Reperfusion Scoring on 2D DSA Images of Acute Ischemic Stroke Patients. IEEE Trans Med Imaging 40(9):2380\u20132391","journal-title":"IEEE Trans Med Imaging"},{"issue":"9","key":"4046_CR14","doi-asserted-by":"publisher","first-page":"1633","DOI":"10.1007\/s11548-022-02654-8","volume":"17","author":"BJ Mittmann","year":"2022","unstructured":"Mittmann BJ, Braun M, Runck F, Schmitz B, Tran TN, Yamlahi A et al (2022) Deep learning-based classification of DSA image sequences of patients with acute ischemic stroke. Int J Comput Assist Radiol Surg 17(9):1633\u20131641","journal-title":"Int J Comput Assist Radiol Surg"},{"issue":"3","key":"4046_CR15","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1111\/jon.13193","volume":"34","author":"R Warman","year":"2024","unstructured":"Warman R, Warman PI, Warman A, Bueso T, Ota R, Windisch T et al (2024) A deep learning method to identify and localize large-vessel occlusions from cerebral digital subtraction angiography. J neuroimaging Off J Am Soc Neuroimaging 34(3):366\u2013375","journal-title":"J neuroimaging Off J Am Soc Neuroimaging"},{"issue":"8","key":"4046_CR16","doi-asserted-by":"publisher","first-page":"5728","DOI":"10.1007\/s00330-023-09478-3","volume":"33","author":"B Kelly","year":"2023","unstructured":"Kelly B, Martinez M, Do H, Hayden J, Huang Y, Yedavalli V et al (2023) DEEP MOVEMENT: Deep learning of movie files for management of endovascular thrombectomy. Eur Radiol 33(8):5728\u20135739","journal-title":"Eur Radiol"},{"issue":"6","key":"4046_CR17","doi-asserted-by":"publisher","first-page":"1791","DOI":"10.1088\/0031-9155\/56\/6\/017","volume":"56","author":"D Schuldhaus","year":"2011","unstructured":"Schuldhaus D, Spiegel M, Redel T, Polyanskaya M, Struffert T, Hornegger J et al (2011) Classification-based summation of cerebral digital subtraction angiography series for image post-processing algorithms. Phys Med Biol 56(6):1791\u20131802","journal-title":"Phys Med Biol"},{"issue":"37","key":"4046_CR18","doi-asserted-by":"publisher","first-page":"2541","DOI":"10.1093\/eurheartj\/ehu278","volume":"35","author":"S Windecker","year":"2014","unstructured":"Windecker S, Kolh P, Alfonso F, Collet J-PP, Cremer J, Falk V et al (2014) 2014 ESC\/EACTS Guidelines on myocardial revascularization: The Task Force on Myocardial Revascularization of the European Society of Cardiology (ESC) and the European Association for Cardio-Thoracic Surgery (EACTS)Developed with the special contribution o. Eur Heart J 35(37):2541\u20132619","journal-title":"Eur Heart J"},{"issue":"4","key":"4046_CR19","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1515\/cdbme-2024-2094","volume":"10","author":"J Komposch","year":"2024","unstructured":"Komposch J, Malzacher T, Baumg\u00e4rtner T, Braun M, Ro\u00dfkopf J, Franz AM et al (2024) A setup for live AI support in interventional radiology. Curr Dir Biomed Eng 10(4):385\u2013388","journal-title":"Curr Dir Biomed Eng"},{"key":"4046_CR20","unstructured":"Kunapinun A, Suthakorn J, Siravaman D, Songsaeng D Toward AI-Powered Neurovascular Intervention: 2026;(April)"},{"issue":"1","key":"4046_CR21","doi-asserted-by":"publisher","first-page":"2024","DOI":"10.5797\/jnet.ra.2024-0107","volume":"19","author":"K Kono","year":"2025","unstructured":"Kono K (2025) Artificial Intelligence in Neuroendovascular Procedures. J neuroendovascular Ther 19(1):2024\u20130107","journal-title":"J neuroendovascular Ther"},{"key":"4046_CR22","doi-asserted-by":"crossref","unstructured":"Baumg\u00e4rtner T, Mittmann BJ, Malzacher T, Ro\u00dfkopf J (2023) Towards clinical translation of deep-learning based classification of DSA image sequences for stroke treatment. Inf aktuell Proc Ger Work Med Image Comput. pp 95\u2013101","DOI":"10.1007\/978-3-658-41657-7_22"},{"issue":"8","key":"4046_CR23","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long Short-Term Memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"4046_CR24","unstructured":"Narang S, Diamos G, Elsen E, Micikevicius P, Alben J, Garcia D et al (2017) Mixed Precision Training. 6th Int Conf Learn Represent ICLR 2018 - Conf Track Proc"},{"key":"4046_CR25","unstructured":"Loshchilov I, Hutter F (2017) Decoupled Weight Decay Regularization. 7th Int Conf Learn Represent ICLR 2019"},{"issue":"6","key":"4046_CR26","doi-asserted-by":"publisher","first-page":"e210097","DOI":"10.1148\/ryai.2021210097","volume":"3","author":"T Eche","year":"2021","unstructured":"Eche T, Schwartz LH, Mokrane F-Z, Dercle L (2021) Toward Generalizability in the Deployment of Artificial Intelligence in Radiology: Role of Computation Stress Testing to Overcome Underspecification. Radiol Artif Intell 3(6):e210097","journal-title":"Radiol Artif Intell"}],"container-title":["Neuroradiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00234-026-04046-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00234-026-04046-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00234-026-04046-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T05:54:23Z","timestamp":1792389263000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00234-026-04046-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,4]]},"references-count":26,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["4046"],"URL":"https:\/\/doi.org\/10.1007\/s00234-026-04046-0","relation":{},"ISSN":["0028-3940","1432-1920"],"issn-type":[{"value":"0028-3940","type":"print"},{"value":"1432-1920","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,4]]},"assertion":[{"value":"24 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The study was approved by the Ethics Committee of Ulm University and was conducted in accordance with the 1964 Helsinki Declaration and its later amendments.","order":1,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Due to the retrospective study design, the requirement for written informed consent was waived.","order":2,"name":"Ethics","label":"Informed consent","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":4,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}]}}