{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T05:04:59Z","timestamp":1789362299105,"version":"build-2803163510"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T00:00:00Z","timestamp":1789344000000},"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":"\n Purpose<\/jats:title>\n Although mechanical thrombectomy (MT) achieves high recanalization rates in acute ischemic stroke (AIS), functional outcomes remain highly inconsistent. We aimed to evaluate the effectiveness of radiomics and deep learning features (DLFs) extracted from both intra-thrombus and peri-thrombus regions on baseline CT in predicting prognosis following MT.<\/jats:p>\n <\/jats:sec>\n \n Materials and methods<\/jats:title>\n \n This retrospective, multicenter study included 471 AIS patients who underwent MT. Patients from Center A (\n n<\/jats:italic>\n \u202f=\u202f315) constituted the training cohort, while those from Center B and C (\n n<\/jats:italic>\n \u202f=\u202f156) served as an external test cohort. Thrombus regions were manually segmented, with a subsequent 1\u202fmm expansion to define the peri-thrombus regions. A total of 428 radiomics features and 128 DLFs were extracted from non-contrast CT (NCCT) and CTA images. After feature selection, ten machine learning classifiers were employed to build prediction models. Combined models were developed based on two strategies including early feature-level fusion and late decision-level fusion. Model performance was evaluated using ROC analysis, DeLong test, NRI and IDI. Subgroup analyses were also performed.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n A total of 191 patients (40.6%) achieved a favorable outcome (90-day mRS\u202f\u2264\u202f2). In the test cohort, the late-fusion combined model achieved the highest discriminative performance (AUC\u202f=\u202f0.836, 95% CI: 0.769\u20130.891). It significantly outperformed both the peri-thrombus model (AUC\u202f=\u202f0.758,\n p<\/jats:italic>\n \u202f=\u202f0.005) and the early-fusion combined model (AUC\u202f=\u202f0.763,\n p<\/jats:italic>\n \u202f=\u202f0.009). Compared with the intra-thrombus model, the late-fusion combined model also demonstrated improved reclassification, with an NRI of 0.935 and an IDI of 0.278. Subgroup analyses showed consistent discriminative performance of the late-fusion combined model across the prespecified subgroups.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusion<\/jats:title>\n The late-fusion combined model, integrating CT-derived radiomic and DLFs from both intra-thrombus and peri-thrombus regions, may provide an effective approach for predicting 90-day functional outcome after mechanical thrombectomy.<\/jats:p>\n <\/jats:sec>","DOI":"10.3389\/fneur.2026.1943953","type":"journal-article","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T04:36:54Z","timestamp":1789360614000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Prediction of functional outcome after mechanical thrombectomy using radiomics and deep learning features derived from intra-thrombus and peri-thrombus regions"],"prefix":"10.3389","volume":"17","author":[{"given":"Kai","family":"Shang","sequence":"first","affiliation":[{"name":"Institute of Diagnostic and Interventional Radiology, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxiao","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Diagnostic and Interventional Radiology, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lifang","family":"Ye","sequence":"additional","affiliation":[{"name":"Institute of Diagnostic and Interventional Radiology, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Radiology, Wuxi No 2 People's Hospital","place":["Wuxi, China"]},{"name":"Department of Radiology, The Tenth People's Hospital Affiliated to Tongji University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Xiong","sequence":"additional","affiliation":[{"name":"Department of Cardiology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University","place":["Nanchang, Jiangxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuehua","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Diagnostic and Interventional Radiology, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingxuan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Institute of Diagnostic and Interventional Radiology, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine","place":["Shanghai, China"]},{"name":"Department of Radiology, Affiliated Hospital of Nantong University","place":["Nantong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1016\/S1474-4422(19)30034-1","article-title":"Global, regional, and national burden of stroke, 1990-2016: a systematic analysis for the global burden of disease study 2016","volume":"18","year":"2019","journal-title":"Lancet Neurol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"S6","DOI":"10.1212\/wnl.0000000000012781","article-title":"Global epidemiology of stroke and access to acute ischemic stroke interventions","volume":"97","author":"Saini","year":"2021","journal-title":"Neurology"},{"key":"ref3","doi-asserted-by":"publisher","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":"ref4","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1136\/neurintsurg-2021-017765","article-title":"Predictors of futile recanalization in patients undergoing endovascular treatment in the DIRECT-MT trial","volume":"14","author":"Zhou","year":"2022","journal-title":"J Neurointerv Surg"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1186\/s40001-023-01414-x","article-title":"The risk and outcome of malignant brain edema in post-mechanical thrombectomy: acute ischemic stroke by anterior circulation occlusion","volume":"28","author":"Zhang","year":"2023","journal-title":"Eur J Med Res"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"2379","DOI":"10.1161\/strokeaha.119.025411","article-title":"Predicting clinical outcomes of large vessel occlusion before mechanical Thrombectomy using machine learning","volume":"50","author":"Nishi","year":"2019","journal-title":"Stroke"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1136\/neurintsurg-2018-014250","article-title":"Influence of ASPECTS and endovascular thrombectomy in acute ischemic stroke: a meta-analysis","volume":"11","author":"Phan","year":"2019","journal-title":"J Neurointerv Surg"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1148\/radiol.2020192029","article-title":"Collateral status at single-phase and multiphase CT angiography versus CT perfusion for outcome prediction in anterior circulation acute ischemic stroke","volume":"296","author":"Wang","year":"2020","journal-title":"Radiology"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1212\/WNL.0b013e31828406de","article-title":"Blood-brain barrier disruption is associated with increased mortality after endovascular therapy","volume":"80","author":"Desilles","year":"2013","journal-title":"Neurology"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1148\/radiol.212358","article-title":"CT Hyperdense artery sign and the effect of Alteplase in endovascular Thrombectomy after acute stroke","volume":"305","author":"Zhou","year":"2022","journal-title":"Radiology"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/s00234-025-03871-z","article-title":"Hyperdense middle cerebral artery sign is a prognostic factor of favourable long-term outcomes of mechanical thrombectomy in acute ischaemic stroke","volume":"68","author":"Wrona","year":"2025","journal-title":"Neuroradiology"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"42","DOI":"10.3174\/ajnr.A6865","article-title":"Clot burden score and collateral status and their impact on functional outcome in acute ischemic stroke","volume":"42","author":"Derraz","year":"2021","journal-title":"AJNR Am J Neuroradiol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1121","DOI":"10.1007\/s00234-025-03627-9","article-title":"Thrombus perviousness in acute ischemic stroke: a scoping review of methodology, predictive value, and future perspectives","volume":"67","author":"Bertalan","year":"2025","journal-title":"Neuroradiology"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1016\/j.ejca.2011.11.036","article-title":"Radiomics: extracting more information from medical images using advanced feature analysis","volume":"48","author":"Lambin","year":"2012","journal-title":"Eur J Cancer"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"4644","DOI":"10.1038\/ncomms5006","article-title":"Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach","volume":"5","author":"Aerts","year":"2014","journal-title":"Nat Commun"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"2469","DOI":"10.1016\/j.acra.2022.12.032","article-title":"Computed tomography angiography-based Thrombus Radiomics for predicting the time since stroke onset","volume":"30","author":"Cheng","year":"2023","journal-title":"Acad Radiol"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.1007\/s12975-025-01344-2","article-title":"Dual-energy CT-based Thrombus Radiomics can predict functional outcome of intravenous thrombolysis in acute ischemic stroke","volume":"16","author":"Ma","year":"2025","journal-title":"Transl Stroke Res"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"R150","DOI":"10.1088\/0031-9155\/61\/13\/r150","article-title":"Applications and limitations of radiomics","volume":"61","author":"Yip","year":"2016","journal-title":"Phys Med Biol"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: images are more than pictures, They Are Data","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"3267","DOI":"10.3390\/cancers15133267","article-title":"Recent advances in deep learning and medical imaging for head and neck cancer treatment: MRI, CT, and PET scans","volume":"15","author":"Illimoottil","year":"2023","journal-title":"Cancers"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"2088","DOI":"10.1161\/strokeaha.118.021320","article-title":"Number of stent retriever passes associated with futile recanalization in acute stroke","volume":"49","author":"Baek","year":"2018","journal-title":"Stroke"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"940","DOI":"10.1136\/neurintsurg-2016-012628","article-title":"CT angiography-based collateral flow and time to reperfusion are strong predictors of outcome in endovascular treatment of patients with stroke","volume":"9","author":"Sallustio","year":"2017","journal-title":"J Neurointerv Surg"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"2241","DOI":"10.1161\/strokeaha.120.033377","article-title":"Frequency, determinants, and outcomes of emboli to distal and new territories related to mechanical Thrombectomy for acute ischemic stroke","volume":"52","author":"Wong","year":"2021","journal-title":"Stroke"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1136\/neurintsurg-2018-014601","article-title":"Characterization of strut indentation during mechanical thrombectomy in acute ischemic stroke clot analogs","volume":"11","author":"Weafer","year":"2019","journal-title":"J Neurointerv Surg"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1131","DOI":"10.1161\/strokeaha.120.032810","article-title":"Thrombus composition and efficacy of thrombolysis and Thrombectomy in acute ischemic stroke","volume":"52","author":"Jolugbo","year":"2021","journal-title":"Stroke"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1136\/neurintsurg-2016-012391","article-title":"Correlation of imaging and histopathology of thrombi in acute ischemic stroke with etiology and outcome: a systematic review","volume":"9","author":"Brinjikji","year":"2017","journal-title":"J Neurointerv Surg"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1136\/neurintsurg-2016-012721","article-title":"Clot friction variation with fibrin content; implications for resistance to thrombectomy","volume":"10","author":"Gunning","year":"2018","journal-title":"J Neurointerv Surg"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1159\/000481578","article-title":"Ischemic stroke: histological Thrombus composition and pre-interventional CT attenuation are associated with intervention time and rate of secondary embolism","volume":"44","author":"Sporns","year":"2017","journal-title":"Cerebrovasc Dis"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1136\/neurintsurg-2017-013489","article-title":"Mechanical thrombectomy and rescue therapy for intracranial large artery occlusion with underlying atherosclerosis","volume":"10","author":"Jia","year":"2018","journal-title":"J Neurointerv Surg"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1460","DOI":"10.1161\/strokeaha.119.024889","article-title":"Thrombectomy outcomes of intracranial atherosclerosis-related occlusions","volume":"50","author":"Tsang","year":"2019","journal-title":"Stroke"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1161\/strokeaha.123.043635","article-title":"Emergent large vessel occlusion due to intracranial stenosis: identification, management, challenges, and future directions","volume":"55","author":"Al Kasab","year":"2024","journal-title":"Stroke"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"5560","DOI":"10.1109\/tpami.2021.3075339","article-title":"Sparse SVM for sufficient data reduction","volume":"44","author":"Zhou","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"106767","DOI":"10.1016\/j.neunet.2024.106767","article-title":"Support matrix machine: a review","volume":"181","author":"Kumari","year":"2025","journal-title":"Neural Netw"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"102385","DOI":"10.1016\/j.eclinm.2023.102385","article-title":"Comparing three-dimensional and two-dimensional deep-learning, radiomics, and fusion models for predicting occult lymph node metastasis in laryngeal squamous cell carcinoma based on CT imaging: a multicentre, retrospective, diagnostic study","volume":"67","author":"Wang","year":"2024","journal-title":"EClinicalMedicine"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1943953\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T04:36:59Z","timestamp":1789360619000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1943953\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,14]]},"references-count":35,"alternative-id":["10.3389\/fneur.2026.1943953"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1943953","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,14]]},"article-number":"1943953"}}