{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T04:50:08Z","timestamp":1788497408732,"version":"build-2803163510"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T00:00:00Z","timestamp":1788393600000},"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. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Rupture of intracranial aneurysms leads to aneurysmal subarachnoid hemorrhage with severe adverse outcomes. Current retrospective imaging studies merely differentiate existing ruptured and unruptured aneurysms instead of forecasting prospective rupture risk. To address this limitation, we constructed a multimodal fusion model combining handcrafted radiomics and deep learning embeddings from routine CTA\/MRA for aneurysm rupture discrimination and performed internal validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This multicenter retrospective study screened 520 patients with 572 saccular aneurysms. After eligibility and imaging quality control, 400 patients with 400 index aneurysms were enrolled. Patients were divided into training, validation and test sets (70\/15\/15) with balanced ruptured\/unruptured aneurysm ratios. A total of 1,316 radiomic features were extracted from aneurysm segmentations; stable, non-redundant predictors (n=42) were retained via filtering and LASSO regression. A 3D ResNet produced 512-dimensional deep embeddings, compressed to 128 components by PCA. We fused radiomic and deep features as a 170-dimensional input for an XGBoost classifier. Model performance was assessed via discrimination, calibration and decision-curve analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The fusion model reached an AUC of 0.928, accuracy 0.889, sensitivity 0.902, specificity 0.872, PPV 0.886 and NPV 0.889 on the test set, superior to single radiomic and deep learning models. The model exhibited excellent calibration (slope=0.98, Brier score=0.082). Decision-curve analysis demonstrated greater net clinical benefit across probability thresholds of 0.10\u20130.70.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Integrating reproducible radiomic metrics and volumetric deep embeddings significantly improves the discrimination of aneurysm rupture status. Nevertheless, all rupture labels were determined at initial presentation, and external independent validation was absent. Thus, this pipeline is only an internally validated methodological tool for imaging phenotype analysis, rather than a ready-to-use clinical model for predicting future aneurysm rupture.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnins.2026.1856293","type":"journal-article","created":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T06:44:27Z","timestamp":1788417867000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Radiomics and deep learning for intracranial aneurysm rupture-status assessment on CTA\/MRA: a multicenter retrospective study"],"prefix":"10.3389","volume":"20","author":[{"given":"Tao","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Neurosurgery, The Affiliated Hospital of Southwest Medical University","place":["Luzhou, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiang","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The Affiliated Hospital of Southwest Medical University","place":["Luzhou, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"He","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The Affiliated Hospital of Southwest Medical University","place":["Luzhou, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changren","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The Affiliated Hospital of Southwest Medical University","place":["Luzhou, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kunyang","family":"Bao","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The Affiliated Hospital of Southwest Medical University","place":["Luzhou, Sichuan, China"]},{"name":"Neurosurgical Clinical Research Center of Sichuan Province","place":["Luzhou, China"]},{"name":"Laboratory of Neurological Diseases and Brain Functions, The Affiliated Hospital of Southwest Medical University","place":["Luzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,3]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"4006","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":"ref2","first-page":"785","author":"Chen","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1148\/radiol.2019181960","article-title":"Deep learning\u2013based image conversion of CT reconstruction kernels improves radiomics reproducibility for pulmonary nodules or masses","volume":"292","author":"Choe","year":"2019","journal-title":"Radiology"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"110965","DOI":"10.1016\/j.compbiomed.2025.110965","article-title":"Prediction of intracranial aneurysm rupture from computed tomography angiography using an automated artificial intelligence framework","volume":"197","author":"Choi","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s00062-024-01474-4","article-title":"Machine learning algorithms to predict the risk of rupture of intracranial aneurysms: a systematic review","volume":"35","author":"Daga","year":"2025","journal-title":"Clin. Neuroradiol."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1212\/WNL.0000000000001891","article-title":"The unruptured intracranial aneurysm treatment score: a multidisciplinary consensus","volume":"85","author":"Etminan","year":"2015","journal-title":"Neurology"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"105643","DOI":"10.1016\/j.jstrokecerebrovasdis.2021.105643","article-title":"External validation of the PHASES score in patients with multiple intracranial aneurysms","volume":"30","author":"Feng","year":"2021","journal-title":"J. Stroke Cerebrovasc. Dis."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1186\/s13244-023-01423-8","article-title":"Automatic differentiation of ruptured and unruptured intracranial aneurysms on computed tomography angiography based on deep learning and radiomics","volume":"14","author":"Feng","year":"2023","journal-title":"Insights Imaging"},{"key":"ref10","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":"ref11","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/S1474-4422(13)70263-1","article-title":"Development of the PHASES score for prediction of risk of rupture of intracranial aneurysms: a pooled analysis of six prospective cohort studies","volume":"13","author":"Greving","year":"2014","journal-title":"The Lancet Neurology"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"6114","DOI":"10.1016\/j.acra.2025.07.001","article-title":"Deep learning-driven multimodal fusion model for prediction of middle cerebral artery aneurysm rupture risk","volume":"32","author":"Jia","year":"2025","journal-title":"Acad. Radiol."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1093\/neuros\/nyx238","article-title":"Risk factors for intracranial aneurysm rupture: a systematic review","volume":"82","author":"Kleinloog","year":"2018","journal-title":"Neurosurgery"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1958","DOI":"10.1161\/STROKEAHA.114.005318","article-title":"Lifelong rupture risk of intracranial aneurysms depends on risk factors: a prospective Finnish cohort study","volume":"45","author":"Korja","year":"2014","journal-title":"Stroke"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1016\/j.mri.2012.06.010","article-title":"Radiomics: the process and the challenges","volume":"30","author":"Kumar","year":"2012","journal-title":"Magn. Reson. Imaging"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/nrclinonc.2017.141","article-title":"Radiomics: the bridge between medical imaging and personalized medicine","volume":"14","author":"Lambin","year":"2017","journal-title":"Nat. Rev. Clin. Oncol."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"100709","DOI":"10.1016\/j.patter.2023.100709","article-title":"A deep-learning method for the end-to-end prediction of intracranial aneurysm rupture risk","volume":"4","author":"Li","year":"2023","journal-title":"Patterns"},{"key":"ref18","first-page":"4765","volume-title":"Advances in Neural Information Processing Systems","author":"Lundberg","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1097\/RLI.0000000000000180","article-title":"Measuring computed tomography scanner variability of radiomics features","volume":"50","author":"Mackin","year":"2015","journal-title":"Investig. Radiol."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1111\/ene.14636","article-title":"The unruptured intracranial aneurysm treatment score as a predictor of aneurysm growth or rupture","volume":"28","author":"Molenberg","year":"2021","journal-title":"Eur. J. Neurol."},{"key":"ref21","doi-asserted-by":"crossref","first-page":"100","DOI":"10.3171\/2017.4.JNS17548","article-title":"Validation of the unruptured intracranial aneurysm treatment score: comparison with real-world cerebrovascular practice","volume":"129","author":"Ravindra","year":"2018","journal-title":"J. Neurosurg."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"25","DOI":"10.3174\/ajnr.A5911","article-title":"Deep learning\u2013based detection of intracranial aneurysms in 3D TOF-MRA","volume":"40","author":"Sichtermann","year":"2019","journal-title":"Am. J. Neuroradiol."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"111739","DOI":"10.1016\/j.ejrad.2024.111739","article-title":"Accuracy of radiomics-based models in distinguishing between ruptured and unruptured intracranial aneurysms: a systematic review and meta-analysis","volume":"181","author":"Sohrabi-Ashlaghi","year":"2024","journal-title":"Eur. J. Radiol."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"e190077","DOI":"10.1148\/ryai.2019190077","article-title":"Machine learning classification of cerebral aneurysm rupture status with morphologic variables and hemodynamic parameters","volume":"2","author":"Tanioka","year":"2020","journal-title":"Radiology"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"2368","DOI":"10.1161\/STR.0000000000000070","article-title":"Guidelines for the management of patients with unruptured intracranial aneurysms: a guideline for healthcare professionals from the American Heart Association\/American Stroke Association","volume":"46","author":"Thompson","year":"2015","journal-title":"Stroke"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1148\/radiol.2021202553","article-title":"The biological meaning of radiomic features","volume":"298","author":"Tomaszewski","year":"2021","journal-title":"Radiology"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.1016\/j.ijrobp.2018.05.053","article-title":"Repeatability and reproducibility of radiomic features: a systematic review","volume":"102","author":"Traverso","year":"2018","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"6759","DOI":"10.1007\/s00330-023-09672-3","article-title":"Development and validation of a deep learning model for prediction of intracranial aneurysm rupture risk based on multi-omics factor","volume":"33","author":"Turhon","year":"2023","journal-title":"Eur. Radiol."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational radiomics system to decode the radiographic phenotype","volume":"77","author":"van Griethuysen","year":"2017","journal-title":"Cancer Res."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: a novel method for evaluating prediction models","volume":"26","author":"Vickers","year":"2006","journal-title":"Med. Decis. Mak."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1474780","DOI":"10.3389\/fnins.2024.1474780","article-title":"Predictive value of radiomics for intracranial aneurysm rupture: a systematic review and meta-analysis","volume":"18","author":"Wang","year":"2024","journal-title":"Front. Neurosci."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1126949","DOI":"10.3389\/fneur.2023.1126949","article-title":"Automatic risk prediction of intracranial aneurysm on CTA image with convolutional neural networks and radiomics analysis","volume":"14","author":"Xie","year":"2023","journal-title":"Front. Neurol."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"8615","DOI":"10.3390\/app12178615","article-title":"Prediction of intracranial aneurysm rupture risk using non-invasive radiomics analysis based on follow-up magnetic resonance angiography images: a preliminary study","volume":"12","author":"Yamanouchi","year":"2022","journal-title":"Appl. Sci."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"2627","DOI":"10.3390\/diagnostics13162627","article-title":"Comparison of ruptured intracranial aneurysms identification using different machine learning algorithms and radiomics","volume":"13","author":"Yang","year":"2023","journal-title":"Diagnostics"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"e30214","DOI":"10.1016\/j.heliyon.2024.e30214","article-title":"Prediction of small intracranial aneurysm rupture status based on combined clinical\u2013radiomics model","volume":"10","author":"Ye","year":"2024","journal-title":"Heliyon"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1116","DOI":"10.1016\/j.neuroimage.2006.01.015","article-title":"User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability","volume":"31","author":"Yushkevich","year":"2006","journal-title":"NeuroImage"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"e70050","DOI":"10.1049\/syb2.70050","article-title":"The accuracy in rupture risk prediction of intracranial aneurysms by artificial intelligence algorithms using imaging data from CTA and DSA: a systematic review and meta-analysis","author":"Zhang","year":"2026","journal-title":"IET Syst. Biol."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1007\/s10143-024-03086-5","article-title":"Diagnostic and predictive value of radiomics-based machine learning for intracranial aneurysm rupture status: a systematic review and meta-analysis","volume":"47","author":"Zhong","year":"2024","journal-title":"Neurosurg. Rev."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1148\/radiol.2020191145","article-title":"The image biomarker standardisation initiative: standardized quantitative radiomics for high-throughput image-based phenotyping","volume":"295","author":"Zwanenburg","year":"2020","journal-title":"Radiology"}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1856293\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T06:44:29Z","timestamp":1788417869000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1856293\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,3]]},"references-count":39,"alternative-id":["10.3389\/fnins.2026.1856293"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2026.1856293","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,3]]},"article-number":"1856293"}}