{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T02:16:13Z","timestamp":1778811373099,"version":"3.51.4"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T00:00:00Z","timestamp":1765584000000},"content-version":"vor","delay-in-days":834,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Cambridge British Heart Foundation Centre of Research Excellence","award":["RE\/18\/1\/34212"],"award-info":[{"award-number":["RE\/18\/1\/34212"]}]},{"name":"British Heart Foundation programme","award":["RG\/4\/32218"],"award-info":[{"award-number":["RG\/4\/32218"]}]},{"DOI":"10.13039\/501100018956","name":"NIHR Cambridge Biomedical Research Centre","doi-asserted-by":"publisher","award":["NIHR203312"],"award-info":[{"award-number":["NIHR203312"]}],"id":[{"id":"10.13039\/501100018956","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Cambridge British Heart Foundation Centre of Research Excellence","award":["RE\/18\/1\/34212"],"award-info":[{"award-number":["RE\/18\/1\/34212"]}]},{"name":"British Heart Foundation programme","award":["RG\/4\/32218"],"award-info":[{"award-number":["RG\/4\/32218"]}]},{"DOI":"10.13039\/501100018956","name":"NIHR Cambridge Biomedical Research Centre","doi-asserted-by":"publisher","award":["NIHR203312"],"award-info":[{"award-number":["NIHR203312"]}],"id":[{"id":"10.13039\/501100018956","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background:<\/jats:title>\n                    <jats:p>In ischaemic stroke patients undergoing reperfusion therapy, the amount of salvageable tissue, that is, extent of the ischaemic penumbra, predicts the clinical outcomes. CT perfusion (CTP) enables quantification of penumbral tissues to guide decision making, and current programmes have automated its analysis. More advanced machine learning techniques utilising the CTP maps may improve prediction beyond the ischaemic volume measures.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method:<\/jats:title>\n                    <jats:p>We determined whether applying convolutional neural networks (CNN), a key machine learning technique in modelling image-label relationships, to post-processed CTP maps improved prediction of outcome, assessed by 3\u2009months modified Rankin scale (mRS). Patients who underwent thrombolysis but not thrombectomy were included. CTP maps of a retrospective cohort of 230 patients with middle cerebral artery stroke were used to develop the model, which was validated in an independent cohort of 129 patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>We constructed a CNN model that predicted a favourable post-thrombolysis outcome (mRS 0\u20132 at 3\u2009months) with an area under receiver-operator characteristics curve (AUC) of 0.792 (95% CI, 0.707\u20130.877). This model outperformed a currently clinically used MISTAR software using previously validated thresholds (AUC\u2009=\u20090.583, 95% CI, 0.480\u20130.686) and a model modified using thresholds from the derivation cohort (AUC\u2009=\u20090.670, 95% CI, 0.571\u20130.769). By combining CNN-derived features and baseline demographic features, the prediction AUC was improved to 0.865 (95% CI, 0.794\u20130.936).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>CNN improved prediction of post-thrombolysis outcome, and may be useful in selecting which patients benefit from thrombolysis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/23969873231183206","type":"journal-article","created":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T14:55:26Z","timestamp":1687618526000},"page":"629-637","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":10,"title":["Prediction of response to thrombolysis in acute stroke using neural network analysis of CT perfusion imaging"],"prefix":"10.1093","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8024-8775","authenticated-orcid":false,"given":"Yutong","family":"Chen","sequence":"first","affiliation":[{"name":"Stroke Research Group, Department of Clinical Neurosciences, University of Cambridge, Cambridge, UK 1"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel J","family":"Tozer","sequence":"additional","affiliation":[{"name":"Stroke Research Group, Department of Clinical Neurosciences, University of Cambridge, Cambridge, UK 1"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiran","family":"Liu","sequence":"additional","affiliation":[{"name":"Stroke Research Group, Department of Clinical Neurosciences, University of Cambridge, Cambridge, UK 1"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0109-5067","authenticated-orcid":false,"given":"Edward J","family":"Peake","sequence":"additional","affiliation":[{"name":"Department of Radiology, Cambridge University Hospitals NHS Foundation Trust, Cambridge, UK 2"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hugh S","family":"Markus","sequence":"additional","affiliation":[{"name":"Stroke Research Group, Department of Clinical Neurosciences, University of Cambridge, Cambridge, UK 1"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2023,9,1]]},"reference":[{"key":"2026012113101673900_bibr1-23969873231183206","doi-asserted-by":"crossref","first-page":"1929","DOI":"10.1016\/S0140-6736(14)60584-5","article-title":"Effect of treatment delay, age, and stroke severity on the effects of intravenous thrombolysis with alteplase for acute ischaemic stroke: a meta-analysis of individual patient data from randomised trials","volume":"384","author":"Emberson","year":"2014","journal-title":"Lancet"},{"key":"2026012113101673900_bibr2-23969873231183206","doi-asserted-by":"crossref","first-page":"1723","DOI":"10.1016\/S0140-6736(16)00163-X","article-title":"Endovascular thrombectomy after large-vessel ischaemic stroke: a meta-analysis of individual patient data from five randomised trials","volume":"387","author":"Goyal","year":"2016","journal-title":"Lancet"},{"key":"2026012113101673900_bibr3-23969873231183206","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1177\/1747493020975229","article-title":"The ischemic penumbra: from concept to reality","volume":"16","author":"Ermine","year":"2021","journal-title":"Int J Stroke"},{"key":"2026012113101673900_bibr4-23969873231183206","doi-asserted-by":"crossref","first-page":"164","DOI":"10.5853\/jos.2013.15.3.164","article-title":"Perfusion patterns of ischemic stroke on computed tomography perfusion","volume":"15","author":"Lin","year":"2013","journal-title":"J Stroke"},{"key":"2026012113101673900_bibr5-23969873231183206","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1056\/NEJMoa1804355","article-title":"MRI-Guided thrombolysis for stroke with unknown time of onset","volume":"379","author":"Thomalla","year":"2018","journal-title":"N Engl J Med"},{"key":"2026012113101673900_bibr6-23969873231183206","first-page":"583","article-title":"Thrombectomy 6 to 24 hours after stroke with a mismatch between deficit and infarct","volume":"54","author":"Nogueira","year":"2018","journal-title":"N Engl J Med"},{"key":"2026012113101673900_bibr7-23969873231183206","doi-asserted-by":"crossref","first-page":"718","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":"2026012113101673900_bibr8-23969873231183206","doi-asserted-by":"crossref","first-page":"41","DOI":"10.3389\/fneur.2018.00041","article-title":"Tissue is more important than time in stroke patients being assessed for thrombolysis","volume":"9","author":"Bivard","year":"2018","journal-title":"Front Neurol"},{"key":"2026012113101673900_bibr9-23969873231183206","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s11910-009-0075-9","article-title":"The role of CT and MRI in the emergency evaluation of persons with suspected stroke","volume":"10","author":"Kidwell","year":"2010","journal-title":"Curr Neurol Neurosci Rep"},{"key":"2026012113101673900_bibr10-23969873231183206","doi-asserted-by":"crossref","first-page":"3435","DOI":"10.1161\/STROKEAHA.111.618355","article-title":"Cerebral blood flow is the optimal CT perfusion parameter for assessing infarct core","volume":"42","author":"Campbell","year":"2011","journal-title":"Stroke"},{"key":"2026012113101673900_bibr11-23969873231183206","doi-asserted-by":"crossref","first-page":"979","DOI":"10.1161\/01.STR.0000209238.61459.39","article-title":"Perfusion-CT Assessment of Infarct Core and Penumbra","volume":"37","author":"Wintermark","year":"2006","journal-title":"Stroke"},{"key":"2026012113101673900_bibr12-23969873231183206","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1023\/A:1022643204877","article-title":"Induction of decision trees","volume":"1","author":"Quinlan","year":"1986","journal-title":"Mach Learn"},{"key":"2026012113101673900_bibr13-23969873231183206","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1161\/STROKEAHA.116.015143","article-title":"Validating a predictive model of acute advanced imaging biomarkers in ischemic stroke","volume":"48","author":"Bivard","year":"2017","journal-title":"Stroke"},{"key":"2026012113101673900_bibr14-23969873231183206","doi-asserted-by":"crossref","first-page":"3541","DOI":"10.1161\/STROKEAHA.120.030287","article-title":"Multimodal predictive modeling of endovascular treatment outcome for acute ischemic stroke using machine-learning","volume":"51","author":"Brugnara","year":"2020","journal-title":"Stroke"},{"key":"2026012113101673900_bibr15-23969873231183206","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1016\/j.nicl.2014.02.003","article-title":"Prediction of stroke thrombolysis outcome using CT brain machine learning","volume":"4","author":"Bentley","year":"2014","journal-title":"NeuroImage Clin"},{"key":"2026012113101673900_bibr16-23969873231183206","first-page":"2319","article-title":"Feature extraction using convolution neural networks (CNN) and deep learning","author":"Mohana","year":"2018"},{"key":"2026012113101673900_bibr17-23969873231183206","doi-asserted-by":"crossref","first-page":"604","DOI":"10.1161\/01.STR.19.5.604","article-title":"Interobserver agreement for the assessment of handicap in stroke patients","volume":"19","author":"van Swieten","year":"1988","journal-title":"Stroke"},{"key":"2026012113101673900_bibr18-23969873231183206","unstructured":"Apollo Medical Imaging Technology. Apollo Medical Imaging Technology - Product, https:\/\/www.apollomit.com\/products.htm (2020, accessed 11 March 2022)."},{"key":"2026012113101673900_bibr19-23969873231183206","doi-asserted-by":"crossref","first-page":"876","DOI":"10.1148\/radiol.2015150319","article-title":"Whole-brain CT perfusion to quantify acute ischemic penumbra and Core","volume":"279","author":"Lin","year":"2016","journal-title":"Radiology"},{"key":"2026012113101673900_bibr20-23969873231183206","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1093\/biomet\/52.3-4.591","article-title":"An analysis of variance test for normality (complete samples)","volume":"52","author":"Shapiro","year":"1965","journal-title":"Biometrika"},{"key":"2026012113101673900_bibr21-23969873231183206","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1186\/1471-2105-12-77","article-title":"pROC: an open-source package for R and S+ to analyze and compare ROC curves","volume":"12","author":"Robin","year":"2011","journal-title":"BMC Bioinformatics"},{"key":"2026012113101673900_bibr22-23969873231183206","unstructured":"Hintze J . NCCS. NCSS, LLC. Kaysville, UT, 2007. www.ncss.com"},{"key":"2026012113101673900_bibr23-23969873231183206","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v028.i05","article-title":"Building predictive models in R using the caret package","volume":"28","author":"Kuhn","year":"2008","journal-title":"J Stat Softw"},{"key":"2026012113101673900_bibr24-23969873231183206","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3459665","article-title":"k-Nearest Neighbour Classifiers: 2nd Edition (with Python examples)","volume":"54","author":"Cunningham","year":"2022","journal-title":"ACM Comput Surv"},{"key":"2026012113101673900_bibr25-23969873231183206","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/5254.708428","article-title":"Support vector machines","volume":"13","author":"Hearst","year":"1998","journal-title":"IEEE Intell Syst Appl"},{"key":"2026012113101673900_bibr26-23969873231183206","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"2026012113101673900_bibr27-23969873231183206","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the Lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J R Stat Soc Ser B Methodol"},{"key":"2026012113101673900_bibr28-23969873231183206","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1007\/978-3-540-28650-9_4","volume-title":"Advanced lectures on machine learning","author":"Rasmussen","year":"2004"},{"key":"2026012113101673900_bibr29-23969873231183206","unstructured":"Paszke A, Gross S, Massa F, et al \u00a0PyTorch: An Imperative Style, High-Performance Deep Learning Library. In: Advances in Neural Information Processing Systems. Curran Associates, Inc., https:\/\/papers.nips.cc\/paper\/2019\/hash\/bdbca288fee7f92f2bfa9f7012727740-Abstract.html (2019, accessed 28 February 2022)."},{"key":"2026012113101673900_bibr30-23969873231183206","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1910.03151.","article-title":"ECA-Net: efficient channel attention for deep convolutional neural networks","author":"Wang","year":"2020"},{"key":"2026012113101673900_bibr31-23969873231183206","unstructured":"Kingma DP, Ba J. Adam: a method for stochastic optimization. ArXiv14126980 Cs, http:\/\/arxiv.org\/abs\/1412.6980 (2017, accessed 11 March 2022)."},{"key":"2026012113101673900_bibr32-23969873231183206","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvaraju","year":"2020","journal-title":"Int J Comput Vis"},{"key":"2026012113101673900_bibr33-23969873231183206","doi-asserted-by":"crossref","first-page":"e323","DOI":"10.2196\/jmir.5870","article-title":"Guidelines for developing and reporting machine learning predictive models in biomedical research: a multidisciplinary view","volume":"18","author":"Luo","year":"2016","journal-title":"J Med Internet Res"},{"key":"2026012113101673900_bibr34-23969873231183206","doi-asserted-by":"crossref","first-page":"1953","DOI":"10.1109\/TCBB.2018.2811471","article-title":"Using machine learning to improve the prediction of functional outcome in ischemic stroke patients","volume":"15","author":"Monteiro","year":"2018","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2026012113101673900_bibr35-23969873231183206","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1148\/radiol.12120971","article-title":"Perfusion CT in acute stroke: A comprehensive analysis of infarct and penumbra","volume":"267","author":"Bivard","year":"2013","journal-title":"Radiology"},{"key":"2026012113101673900_bibr36-23969873231183206","doi-asserted-by":"crossref","first-page":"1552","DOI":"10.3174\/ajnr.A2026","article-title":"Evaluation of CT perfusion in the setting of cerebral ischemia: patterns and pitfalls","volume":"31","author":"Lui","year":"2010","journal-title":"AJNR Am J Neuroradiol"},{"key":"2026012113101673900_bibr37-23969873231183206","unstructured":"NICE. Impact on NHS workforce and resources | Stroke and transient ischaemic attack in over 16s: diagnosis and initial management | Guidance | NICE, https:\/\/www.nice.org.uk\/guidance\/ng128\/resources\/impact-on-nhs-workforce-and-resources-6842988829 (2022, accessed 4 May 2023)."},{"key":"2026012113101673900_bibr38-23969873231183206","doi-asserted-by":"crossref","first-page":"995","DOI":"10.1002\/ana.25109","article-title":"Ischemic core thresholds change with time to reperfusion: A case control study","volume":"82","author":"Bivard","year":"2017","journal-title":"Ann. Neurol"}],"container-title":["European Stroke Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/23969873231183206","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/23969873231183206","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/academic.oup.com\/esj\/article-pdf\/8\/3\/629\/64652795\/23969873231183206.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/esj\/article-pdf\/8\/3\/629\/64652795\/23969873231183206.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T18:11:32Z","timestamp":1769019092000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/esj\/article\/8\/3\/629\/8269050"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,1]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,9,1]]}},"URL":"https:\/\/doi.org\/10.1177\/23969873231183206","relation":{},"ISSN":["2396-9873","2396-9881"],"issn-type":[{"value":"2396-9873","type":"print"},{"value":"2396-9881","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,9,1]]},"published":{"date-parts":[[2023,9,1]]}}}