{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T07:27:57Z","timestamp":1793950077117,"version":"4.8.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T00:00:00Z","timestamp":1672876800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T00:00:00Z","timestamp":1672876800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"GE Healthcare, United States","id":[{"id":"https:\/\/ror.org\/01bwa4v12","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Non-contrast head CT (NCCT) is extremely insensitive for early (&lt;\u20093\u20136\u00a0h) acute infarct identification. We developed a deep learning model that detects and delineates suspected early acute infarcts on NCCT, using diffusion MRI as ground truth (3566 NCCT\/MRI training patient pairs). The model substantially outperformed 3 expert neuroradiologists on a test set of 150 CT scans of patients who were potential candidates for thrombectomy (60 stroke-negative, 90 stroke-positive middle cerebral artery territory only infarcts), with sensitivity 96% (specificity 72%) for the model versus 61\u201366% (specificity 90\u201392%) for the experts; model infarct volume estimates also strongly correlated with those of diffusion MRI (r\n                    <jats:sup>2<\/jats:sup>\n                    \u2009&gt;\u20090.98). When this 150 CT test set was expanded to include a total of 364 CT scans with a more heterogeneous distribution of infarct locations (94 stroke-negative, 270 stroke-positive mixed territory infarcts), model sensitivity was 97%, specificity 99%, for detection of infarcts larger than the 70\u00a0mL volume threshold used for patient selection in several major randomized controlled trials of thrombectomy treatment.\n                  <\/jats:p>","DOI":"10.1038\/s41598-023-27496-5","type":"journal-article","created":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T06:03:02Z","timestamp":1672898582000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":40,"title":["Head CT deep learning model is highly accurate for early infarct estimation"],"prefix":"10.1038","volume":"13","author":[{"given":"Romane","family":"Gauriau","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernardo C.","family":"Bizzo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donnella S.","family":"Comeau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James M.","family":"Hillis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher P.","family":"Bridge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John K.","family":"Chin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jayashri","family":"Pawar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Pourvaziri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivana","family":"Sesic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elshaimaa","family":"Sharaf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinjin","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Flavia T. C.","family":"Noro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Walter F.","family":"Wiggins","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M. Travis","family":"Caton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felipe","family":"Kitamura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keith J.","family":"Dreyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John F.","family":"Kalafut","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katherine P.","family":"Andriole","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stuart R.","family":"Pomerantz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramon G.","family":"Gonzalez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael H.","family":"Lev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,1,5]]},"reference":[{"key":"27496_CR1","doi-asserted-by":"publisher","first-page":"806","DOI":"10.1177\/1747493019881353","volume":"14","author":"MP Lindsay","year":"2019","unstructured":"Lindsay, M. P. et al. World stroke organization (WSO): Global stroke fact sheet 2019. Int. J. Stroke 14, 806\u2013817 (2019).","journal-title":"Int. J. Stroke"},{"key":"27496_CR2","doi-asserted-by":"crossref","unstructured":"Nogueira RG, et al., DAWN Trial Investigators. Thrombectomy 6 to 24 Hours after Stroke with a Mismatch between Deficit and Infarct. N. Engl. J. Med. 378, 11\u201321 (2018).","DOI":"10.1056\/NEJMoa1706442"},{"key":"27496_CR3","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1001\/jamaneurol.2015.3000","volume":"73","author":"TM Leslie-Mazwi","year":"2016","unstructured":"Leslie-Mazwi, T. M. et al. Endovascular stroke treatment outcomes after patient selection based on magnetic resonance imaging and clinical criteria. JAMA Neurol. 73, 43\u201349 (2016).","journal-title":"JAMA Neurol."},{"key":"27496_CR4","doi-asserted-by":"crossref","unstructured":"Campbell BCV, et al., HERMES collaborators. Penumbral imaging and functional outcome in patients with anterior circulation ischaemic stroke treated with endovascular thrombectomy versus medical therapy: a meta-analysis of individual patient-level data. Lancet Neurol. 18, 46\u201355 (2019).","DOI":"10.1016\/S1474-4422(18)30314-4"},{"key":"27496_CR5","doi-asserted-by":"crossref","unstructured":"Nogueira RG, et al., Trevo Registry and DAWN Trial Investigators. stroke imaging selection modality and endovascular therapy outcomes in the early and extended time windows. Stroke. 52, 491\u2013497 (2021).","DOI":"10.1161\/STROKEAHA.120.031685"},{"key":"27496_CR6","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1001\/jamaneurol.2020.2804","volume":"78","author":"BJ Kim","year":"2021","unstructured":"Kim, B. J. et al. endovascular treatment after stroke due to large vessel occlusion for patients presenting very late from time last known well. JAMA Neurol. 78, 21\u201329 (2021).","journal-title":"JAMA Neurol."},{"key":"27496_CR7","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1056\/NEJMoa1411587","volume":"372","author":"OA Berkhemer","year":"2015","unstructured":"Berkhemer, O. A. et al. A randomized trial of intraarterial treatment for acute ischemic stroke. N. Engl. J. Med. 372, 11\u201320 (2015).","journal-title":"N. Engl. J. Med."},{"key":"27496_CR8","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1148\/radiology.213.1.r99oc10150","volume":"213","author":"MH Lev","year":"1999","unstructured":"Lev, M. H. et al. Acute stroke: improved nonenhanced CT detection\u2013benefits of soft-copy interpretation by using variable window width and center level settings. Radiology 213, 150\u2013155 (1999).","journal-title":"Radiology"},{"key":"27496_CR9","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1148\/radiol.2442061028","volume":"244","author":"EC Camargo","year":"2007","unstructured":"Camargo, E. C. et al. Acute brain infarct: detection and delineation with CT angiographic source images versus nonenhanced CT scans. Radiology 244, 541\u2013548 (2007).","journal-title":"Radiology"},{"key":"27496_CR10","doi-asserted-by":"crossref","unstructured":"Mullins, et al. CT and Conventional and Diffusion-Weighted MR Imaging in Acute Stroke: Study in 691 Patients at Presentation to the Emergency Department. Radiology 224, 353\u201360 (2002).","DOI":"10.1148\/radiol.2242010873"},{"key":"27496_CR11","doi-asserted-by":"publisher","first-page":"2206","DOI":"10.1161\/01.STR.0000026864.20339.CB","volume":"33","author":"JB Fiebach","year":"2002","unstructured":"Fiebach, J. B. et al. CT and diffusion-weighted MR imaging in randomized order: Diffusion-weighted imaging results in higher accuracy and lower interrater variability in the diagnosis of hyperacute ischemic stroke. Stroke 33, 2206\u20132210 (2002).","journal-title":"Stroke"},{"key":"27496_CR12","doi-asserted-by":"publisher","first-page":"1892","DOI":"10.1161\/01.STR.0000134746.93535.9b","volume":"35","author":"WD Heiss","year":"2004","unstructured":"Heiss, W. D. et al. Probability of cortical infarction predicted by flumazenil binding and diffusion-weighted imaging signal intensity: a comparative positron emission tomography\/magnetic resonance imaging study in early ischemic stroke. Stroke 35, 1892\u20131898 (2004).","journal-title":"Stroke"},{"key":"27496_CR13","doi-asserted-by":"publisher","first-page":"2104","DOI":"10.1212\/WNL.0b013e3181aa5329","volume":"24","author":"JR Sims","year":"2009","unstructured":"Sims, J. R. et al. ABC\/2 for rapid clinical estimate of infarct, perfusion, and mismatch volumes. Neurology 24, 2104\u20132110 (2009).","journal-title":"Neurology"},{"key":"27496_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jstrokecerebrovasdis.2020.104715","volume":"29","author":"P Mikhail","year":"2020","unstructured":"Mikhail, P., Le, M. G. D. & Mair, G. Computational image analysis of nonenhanced computed tomography for acute ischaemic stroke: A systematic review. J. Stroke Cerebrovasc. Dis. 29, 104715 (2020).","journal-title":"J. Stroke Cerebrovasc. Dis."},{"key":"27496_CR15","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1148\/radiol.2020191193","volume":"294","author":"W Qiu","year":"2020","unstructured":"Qiu, W. et al. Machine learning for detecting early infarction in acute stroke with non-contrast-enhanced CT. Radiology 294, 638\u2013644 (2020).","journal-title":"Radiology"},{"key":"27496_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jstrokecerebrovasdis.2021.105752","volume":"30","author":"J Pan","year":"2021","unstructured":"Pan, J. et al. Detecting the early infarct core on non-contrast CT images with a deep learning residual network. J. Stroke Cerebrovasc. Dis. 30, 105752 (2021).","journal-title":"J. Stroke Cerebrovasc. Dis."},{"key":"27496_CR17","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1161\/STROKEAHA.120.031651","volume":"52","author":"M Bouslama","year":"2021","unstructured":"Bouslama, M. et al. Noncontrast computed tomography e-stroke infarct volume is similar to RAPID computed tomography perfusion in estimating postreperfusion infarct volumes. Stroke 52, 634\u2013641 (2021).","journal-title":"Stroke"},{"key":"27496_CR18","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1177\/1747493019879661","volume":"15","author":"S Nagel","year":"2020","unstructured":"Nagel, S. et al. e-ASPECTS derived acute ischemic volumes on non-contrast-enhanced computed tomography images. Int. J. Stroke. 15, 995\u20131001 (2020).","journal-title":"Int. J. Stroke."},{"key":"27496_CR19","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1161\/STROKEAHA.114.007117","volume":"46","author":"PW Schaefer","year":"2015","unstructured":"Schaefer, P. W. et al. Limited reliability of computed tomographic perfusion acute infarct volume measurements compared with diffusion-weighted imaging in anterior circulation stroke. Stroke 46, 419\u2013424 (2015).","journal-title":"Stroke"},{"key":"27496_CR20","doi-asserted-by":"publisher","first-page":"1836","DOI":"10.1093\/annonc\/mdy166","volume":"29","author":"HA Haenssle","year":"2018","unstructured":"Haenssle, H. A. et al. Man against machine: Diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Ann. Oncol. 29, 1836\u20131842 (2018).","journal-title":"Ann. Oncol."},{"key":"27496_CR21","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1038\/s41586-019-1799-6","volume":"577","author":"SM McKinney","year":"2020","unstructured":"McKinney, S. M. et al. International evaluation of an AI system for breast cancer screening. Nature 577, 89\u201394 (2020).","journal-title":"Nature"},{"key":"27496_CR22","unstructured":"Ronneberger O, Fischer P, and Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Preprint at https:\/\/arxiv.org\/abs\/1505.04597v1 (2015)."},{"key":"27496_CR23","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1007\/s10278-019-00308-x","volume":"33","author":"R Gauriau","year":"2020","unstructured":"Gauriau, R. et al. Using DICOM metadata for radiological image series categorization: A feasibility study on large clinical brain MRI datasets. J Digit. Imaging. 33, 747\u2013762 (2020).","journal-title":"J Digit. Imaging."},{"key":"27496_CR24","first-page":"81","volume":"1107","author":"S Pedemonte","year":"2018","unstructured":"Pedemonte, S. et al. Detection and delineation of acute cerebral infarct on DWI using weakly supervised machine learning. Med. Image Comput. Comput. Assist. Interv. (MICCAI) 1107, 81\u201388 (2018).","journal-title":"Med. Image Comput. Comput. Assist. Interv. (MICCAI)"},{"key":"27496_CR25","first-page":"249","volume":"9","author":"X Glorot","year":"2010","unstructured":"Glorot, X. & Bengio, Y. Understanding the difficulty of training deep feedforward neural networks. Proc. Thirteenth Int. Conf. Artif. Intell. Stat. 9, 249\u2013256 (2010).","journal-title":"Proc. Thirteenth Int. Conf. Artif. Intell. Stat."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-27496-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-27496-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-27496-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T06:16:51Z","timestamp":1672899411000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-27496-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,5]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["27496"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-27496-5","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,5]]},"assertion":[{"value":"27 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"189"}}