biostudies-literatureLiu Jnational natural science foundation of chinaNatural Science Foundation of Chinawest china hospital, sichuan university17562864211060029https://www.ebi.ac.uk/biostudies/studies/S-EPMC8842178biostudies-literatureUnknown14<h4>Introduction</h4>Patients with hemorrhagic transformation (HT) were reported to have hemorrhage expansion. However, identification these patients with high risk of hemorrhage expansion has not been well studied.<h4>Objectives</h4>We aimed to develop a radiomic score to predict hemorrhage expansion after HT among patients treated with thrombolysis/thrombectomy during acute phase of ischemic stroke.<h4>Methods</h4>A total of 104 patients with HT after reperfusion treatment from the West China hospital, Sichuan University, were retrospectively included in this study between 1 January 2012 and 31 December 2020. The preprocessed initial non-contrast-enhanced computed tomography (NECT) imaging brain images were used for radiomic feature extraction. A synthetic minority oversampling techniqueTherapeutic advances in neurological disordersRadiomics-based prediction of hemorrhage expansion among patients with thrombolysis/thrombectomy related-hemorrhagic transformation using machine learning.PMC88421788190119981620108009ZYGD18009Liu JTao WLiu MWu BChen XWang ZfalseRadiomics-based prediction of hemorrhage expansion among patients with thrombolysis/thrombectomy related-hemorrhagic transformation using machine learning.<h4>Introduction</h4>Patients with hemorrhagic transformation (HT) were reported to have hemorrhage expansion. However, identification these patients with high risk of hemorrhage expansion has not been well studied.<h4>Objectives</h4>We aimed to develop a radiomic score to predict hemorrhage expansion after HT among patients treated with thrombolysis/thrombectomy during acute phase of ischemic stroke.<h4>Methods</h4>A total of 104 patients with HT after reperfusion treatment from the West China hospital, Sichuan University, were retrospectively included in this study between 1 January 2012 and 31 December 2020. The preprocessed initial non-contrast-enhanced computed tomography (NECT) imaging brain images were used for radiomic feature extraction. A synthetic minority oversampling technique2021-01-01T00:00:00Z20212025-04-04T14:49:19.491Z2025-04-04T14:49:19.491ZS-EPMC88421783517380910.1177/17562864211060029