{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T04:54:38Z","timestamp":1776315278853,"version":"3.50.1"},"reference-count":48,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T00:00:00Z","timestamp":1776297600000},"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>Objective<\/jats:title>\n                    <jats:p>To develop and validate an interpretable machine learning (ML) model integrating computed tomography angiography (CTA)-derived radiomics features of carotid plaque and perivascular adipose tissue (PVAT) for predicting ipsilateral stroke recurrence in patients with carotid atherosclerosis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this retrospective study, patients with unilateral carotid atherosclerosis who underwent head and neck CTA between May 2016 and March 2024 were included and followed for recurrent ischemic stroke detected by follow-up MRI. Radiomics features of carotid plaque and PVAT were automatically extracted using a deep learning-based segmentation model and then gathered to constructed a ML model to predict stroke risk. A conventional clinical model based on carotid stenosis degree and clinical factors was also developed. Additionally, a combined model incorporating both radiomics and clinical factors was constructed. The optimal predictive model was chosen among five ML algorithms based on the area under receiver operating characteristics curve (AUC). Model performance was validated through repeated 10-fold cross-validation and tested in an independent testing cohort. Model interpretability was examined using Shapley Additive Explanations (SHAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Of 162 patients (mean age, 69.28\u202fyears\u202f\u00b1\u202f8.30 [SD]; 136 [83.95%] male) were included, of whom 63 (38.9%) experienced ipsilateral stroke recurrence during follow-up (median, 1\u202fyears). The combined model using support vector machines achieved the highest AUC of 0.87(95% CI: 0.74\u20130.97) in the testing set, higher than the radiomics-only model (AUC, 0.80; 0.63\u20130.94) and the clinical model (AUC, 0.77; 0.58\u20130.91; all\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.05). SHAP analysis demonstrated that plaque texture features contributed strongly to recurrence risk, while PVAT-derived features provided complementary inflammatory information.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>An ML model including both radiomics features of carotid plaque and PVAT can improve performance in predicting ipsilateral stroke recurrence risk than clinical factors alone, offering a promising tool for stroke prevent in clinical practice.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2026.1821860","type":"journal-article","created":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T04:21:09Z","timestamp":1776313269000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CT angiography\u2013derived plaque and perivascular fat radiomics for predicting ipsilateral stroke recurrence in patients with carotid atherosclerosis"],"prefix":"10.3389","volume":"17","author":[{"given":"Jianyong","family":"Wei","sequence":"first","affiliation":[{"name":"School of Health Science and Engineering, University of Shanghai for Science and Technology","place":["Shanghai, China"]},{"name":"Institute of Diagnostic and Interventional Radiology, Shanghai Sixth People\u2019s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulu","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Diagnostic and Interventional Radiology, Shanghai Sixth People\u2019s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoer","family":"Wei","sequence":"additional","affiliation":[{"name":"Institute of Diagnostic and Interventional Radiology, Shanghai Sixth People\u2019s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiwen","family":"Yang","sequence":"additional","affiliation":[{"name":"ShuKun Technology Co., Ltd.","place":["Beijing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingying","family":"Tao","sequence":"additional","affiliation":[{"name":"Institute of Diagnostic and Interventional Radiology, Shanghai Sixth People\u2019s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Zheng","sequence":"additional","affiliation":[{"name":"ShuKun Technology Co., Ltd.","place":["Beijing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shundong","family":"Hu","sequence":"additional","affiliation":[{"name":"Institute of Diagnostic and Interventional Radiology, Shanghai Sixth People\u2019s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueqi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute of Diagnostic and Interventional Radiology, Shanghai Sixth People\u2019s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuehua","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Diagnostic and Interventional Radiology, Shanghai Sixth People\u2019s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,16]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"e347","DOI":"10.1161\/CIR.0000000000001209","article-title":"2024 heart disease and stroke statistics: a report of US and global data from the American Heart Association","volume":"149","author":"Martin","year":"2024","journal-title":"Circulation"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.ejvs.2017.06.021","article-title":"Editor's choice - Management of Atherosclerotic Carotid and Vertebral Artery Disease: 2017 clinical practice Guidelines of the European Society for Vascular Surgery (ESVS)","volume":"55","author":"Naylor","year":"2018","journal-title":"Eur J Vasc Endovasc Surg"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1186\/1471-2377-14-23","article-title":"Recurrent stroke risk is high after a single cerebrovascular event in patients with symptomatic 50-99% carotid stenosis: a cohort study","volume":"14","author":"Johansson","year":"2014","journal-title":"BMC Neurol"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1007\/s00415-019-09605-5","article-title":"Symptomatic carotid near-occlusion causes a high risk of recurrent ipsilateral ischemic stroke","volume":"267","author":"Gu","year":"2020","journal-title":"J Neurol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1093\/cvr\/cvad135","article-title":"Stroke risk management in carotid atherosclerotic disease: a clinical consensus statement of the ESC Council on stroke and the ESC working group on aorta and peripheral vascular diseases","volume":"121","author":"Musialek","year":"2025","journal-title":"Cardiovasc Res"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e364","DOI":"10.1161\/STR.0000000000000375","article-title":"2021 Guideline for the prevention of stroke in patients with stroke and transient ischemic attack: a Guideline from the American Heart Association\/American Stroke Association","volume":"52","author":"Kleindorfer","year":"2021","journal-title":"Stroke"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1016\/j.ejvs.2014.08.017","article-title":"Clinical and imaging features associated with an increased risk of late stroke in patients with asymptomatic carotid disease","volume":"48","author":"Naylor","year":"2014","journal-title":"Eur J Vasc Endovasc Surg"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"e016274","DOI":"10.1161\/CIRCIMAGING.123.016274","article-title":"Machine learning detects symptomatic plaques in patients with carotid atherosclerosis on CT angiography","volume":"17","author":"Pisu","year":"2024","journal-title":"Circ Cardiovasc Imaging"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1016\/S1474-4422(19)30035-3","article-title":"Imaging biomarkers of vulnerable carotid plaques for stroke risk prediction and their potential clinical implications","volume":"18","author":"Saba","year":"2019","journal-title":"Lancet Neurol"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1715","DOI":"10.1016\/j.jcmg.2022.04.003","article-title":"Carotid plaque characteristics predict recurrent ischemic stroke and TIA: the PARISK (plaque at RISK) study","volume":"15","author":"van Dam-Nolen","year":"2022","journal-title":"JACC Cardiovasc Imaging"},{"key":"ref11","first-page":"923","article-title":"Accuracy of pre- and postcontrast 3D time-of-flight MR angiography in patients with acute ischemic stroke: correlation with catheter angiography","volume":"28","author":"Ishimaru","year":"2007","journal-title":"AJNR Am J Neuroradiol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"2727","DOI":"10.1007\/s00330-021-08379-7","article-title":"Diagnostic accuracy of computed tomography angiography (CTA) for diagnosing blunt cerebrovascular injury in trauma patients: a systematic review and meta-analysis","volume":"32","author":"Kik","year":"2022","journal-title":"Eur Radiol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1016\/j.jvssci.2021.03.001","article-title":"Review of imaging biomarkers for the vulnerable carotid plaque","volume":"2","author":"Saba","year":"2021","journal-title":"JVS Vasc Sci"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"272","DOI":"10.3174\/ajnr.A7401","article-title":"Impact analysis of different CT configurations of carotid artery plaque calcifications on cerebrovascular events","volume":"43","author":"Saba","year":"2022","journal-title":"AJNR Am J Neuroradiol"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1016\/j.jcmg.2023.11.007","article-title":"Carotid plaque-RADS: a novel stroke risk classification system","volume":"17","author":"Hou","year":"2024","journal-title":"JACC Cardiovasc Imaging"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"3612","DOI":"10.1007\/s00330-023-10347-2","article-title":"Machine learning detects symptomatic patients with carotid plaques based on 6-type calcium configuration classification on CT angiography","volume":"34","author":"Pisu","year":"2024","journal-title":"Eur Radiol"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1016\/S0140-6736(18)31114-0","article-title":"Non-invasive detection of coronary inflammation using computed tomography and prediction of residual cardiovascular risk (the CRISP CT study): a post-hoc analysis of prospective outcome data","volume":"392","author":"Oikonomou","year":"2018","journal-title":"Lancet"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.aal2658","article-title":"Detecting human coronary inflammation by imaging perivascular fat","volume":"9","author":"Antonopoulos","year":"2017","journal-title":"Sci Transl Med"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"110269","DOI":"10.1016\/j.ejrad.2022.110269","article-title":"Identification of high-risk carotid plaque by using carotid perivascular fat density on computed tomography angiography","volume":"150","author":"Zhang","year":"2022","journal-title":"Eur J Radiol"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"e010383","DOI":"10.1161\/JAHA.118.010383","article-title":"Association between carotid artery perivascular fat density and cerebrovascular ischemic events","volume":"7","author":"Baradaran","year":"2018","journal-title":"J Am Heart Assoc"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1340202","DOI":"10.3389\/fneur.2024.1340202","article-title":"Initial experience with radiomics of carotid perivascular adipose tissue in identifying symptomatic plaque","volume":"15","author":"Nie","year":"2024","journal-title":"Front Neurol"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e29331","DOI":"10.1016\/j.heliyon.2024.e29331","article-title":"Improving radiomic modeling for the identification of symptomatic carotid atherosclerotic plaques using deep learning-based 3D super-resolution CT angiography","volume":"10","author":"Wang","year":"2024","journal-title":"Heliyon"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1186\/s12880-025-02113-1","article-title":"Interpretable machine learning for detecting symptomatic patients with carotid atherosclerosis on computed tomography angiography: a retrospective diagnostic study","volume":"25","author":"Yang","year":"2025","journal-title":"BMC Med Imaging"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1016\/j.clinimag.2020.09.005","article-title":"Artificial intelligence in stroke imaging: current and future perspectives","volume":"69","author":"Yedavalli","year":"2021","journal-title":"Clin Imaging"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s40169-020-0263-4","article-title":"Personalized CT-based radiomics nomogram preoperative predicting Ki-67 expression in gastrointestinal stromal tumors: a multicenter development and validation cohort","volume":"9","author":"Zhang","year":"2020","journal-title":"Clin Transl Med"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"970","DOI":"10.1007\/s00330-022-09116-4","article-title":"Clot-based radiomics model for cardioembolic stroke prediction with CT imaging before recanalization: a multicenter study","volume":"33","author":"Jiang","year":"2023","journal-title":"Eur Radiol"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"110364","DOI":"10.1016\/j.ejrad.2022.110364","article-title":"Associations between pericarotid fat density and image-based risk characteristics of carotid plaque","volume":"153","author":"Yu","year":"2022","journal-title":"Eur J Radiol"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"18839","DOI":"10.18632\/aging.203327","article-title":"Association between carotid artery perivascular fat density and cerebral small vessel disease","volume":"13","author":"Zhang","year":"2021","journal-title":"Aging (Albany NY)"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1177\/17474930231158538","article-title":"Association between spontaneous internal carotid artery dissection and perivascular adipose tissue attenuation on computed tomography angiography","volume":"18","author":"Cheng","year":"2023","journal-title":"Int J Stroke"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"765962","DOI":"10.3389\/fneur.2021.765962","article-title":"Association between carotid artery perivascular fat density and embolic stroke of undetermined source","volume":"12","author":"Hu","year":"2021","journal-title":"Front Neurol"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1177\/10815589241226728","article-title":"A novel predictive model based on pericarotid adipose tissue and lumen stenosis for stroke risk in patients with asymptomatic carotid stenosis","volume":"72","author":"Liu","year":"2024","journal-title":"J Investig Med"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"104813","DOI":"10.1016\/j.compbiomed.2021.104813","article-title":"Interpretable prediction of 3-year all-cause mortality in patients with heart failure caused by coronary heart disease based on machine learning and SHAP","volume":"137","author":"Wang","year":"2021","journal-title":"Comput Biol Med"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"I","DOI":"10.1177\/23969873211012121","article-title":"European stroke organisation guideline on endarterectomy and stenting for carotid artery stenosis","volume":"6","author":"Bonati","year":"2021","journal-title":"Eur Stroke J"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"1460","DOI":"10.3174\/ajnr.A6710","article-title":"Perivascular fat density and contrast plaque enhancement: does a correlation exist?","volume":"41","author":"Saba","year":"2020","journal-title":"AJNR Am J Neuroradiol"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"2064","DOI":"10.1161\/STR.0b013e318296aeca","article-title":"An updated definition of stroke for the 21st century: a statement for healthcare professionals from the American Heart Association\/American Stroke Association","volume":"44","author":"Sacco","year":"2013","journal-title":"Stroke"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"e220996","DOI":"10.1148\/radiol.220996","article-title":"Deep learning for head and neck CT angiography: stenosis and plaque classification","volume":"307","author":"Fu","year":"2023","journal-title":"Radiology"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"4829","DOI":"10.1038\/s41467-020-18606-2","article-title":"Rapid vessel segmentation and reconstruction of head and neck angiograms using 3D convolutional neural network","volume":"11","author":"Fu","year":"2020","journal-title":"Nat Commun"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"e233197","DOI":"10.1148\/radiol.233197","article-title":"Knowledge-augmented deep learning for segmenting and detecting cerebral aneurysms with CT angiography: a multicenter study","volume":"312","author":"Wei","year":"2024","journal-title":"Radiology"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"3827","DOI":"10.1093\/eurheartj\/ehad484","article-title":"Perivascular adipose tissue as a source of therapeutic targets and clinical biomarkers","volume":"44","author":"Antoniades","year":"2023","journal-title":"Eur Heart J"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"1415","DOI":"10.1056\/NEJM199811123392002","article-title":"Benefit of carotid endarterectomy in patients with symptomatic moderate or severe stenosis. North American symptomatic carotid endarterectomy trial collaborators","volume":"339","author":"Barnett","year":"1998","journal-title":"N Engl J Med"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"10545","DOI":"10.1038\/s41598-018-28895-9","article-title":"Voxel size and gray level normalization of CT radiomic features in lung cancer","volume":"8","author":"Shafiq-Ul-Hassan","year":"2018","journal-title":"Sci Rep"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"3301","DOI":"10.1093\/bioinformatics\/bti499","article-title":"Prediction error estimation: a comparison of resampling methods","volume":"21","author":"Molinaro","year":"2005","journal-title":"Bioinformatics"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"106584","DOI":"10.1016\/j.cmpb.2021.106584","article-title":"Explanation of machine learning models using shapley additive explanation and application for real data in hospital","volume":"214","author":"Nohara","year":"2022","journal-title":"Comput Methods Prog Biomed"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"4150","DOI":"10.1093\/eurheartj\/ehaf614","article-title":"ESC consensus statement on stroke risk management in carotid atherosclerotic disease: 10 key points","volume":"46","author":"Musialek","year":"2025","journal-title":"Eur Heart J"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"1453","DOI":"10.3174\/ajnr.A6613","article-title":"The risk of stroke and TIA in nonstenotic carotid plaques: a systematic review and Meta-analysis","volume":"41","author":"Singh","year":"2020","journal-title":"AJNR Am J Neuroradiol"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"106924","DOI":"10.1016\/j.vph.2021.106924","article-title":"The changing landscape of the vulnerable plaque: a call for fine-tuning of preclinical models","volume":"141","author":"Buono","year":"2021","journal-title":"Vasc Pharmacol"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"1646916","DOI":"10.3389\/fnagi.2025.1646916","article-title":"Risk prediction of recurrent ischemic stroke based on carotid plaque-RADS: construction and validation of a nomogram model","volume":"17","author":"Qiao","year":"2025","journal-title":"Front Aging Neurosci"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1821860\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T04:21:10Z","timestamp":1776313270000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1821860\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,16]]},"references-count":48,"alternative-id":["10.3389\/fneur.2026.1821860"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1821860","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,16]]},"article-number":"1821860"}}