Deep learning of noncontrast CT for fast prediction of hemorrhagic transformation of acute ischemic stroke: a multicenter study

作者：Huanhuan Ren, Haojie Song, Shaoguo Cui, Hua Xiong, Bangyuan Long, Yongmei Li · 发表于：European Radiology Experimental · 年份：2025 · DOI：10.1186/s41747-024-00535-0 · 被引用次数：10 · 研究领域：Acute Ischemic Stroke Management、Intracerebral and Subarachnoid Hemorrhage Research、Venous Thromboembolism Diagnosis and Management

BACKGROUND: Hemorrhagic transformation (HT) is a complication of reperfusion therapy following acute ischemic stroke (AIS). We aimed to develop and validate a model for predicting HT and its subtypes with poor prognosis-parenchymal hemorrhage (PH), including PH-1 (hematoma within infarcted tissue, occupying < 30%) and PH-2 (hematoma occupying ≥ 30% of the infarcted tissue)-in AIS patients following intravenous thrombolysis (IVT) based on noncontrast computed tomography (NCCT) and clinical data. METHODS: In this six-center retrospective study, clinical and imaging data from 445 consecutive IVT-treated AIS patients were collected (01/2018-06/2023). The training cohort comprised 344 patients from five centers, and the test cohort included 101 patients from the sixth center. A clinical model was developed using eXtreme Gradient Boosting, an NCCT-based imaging model was created using deep learning, and an ensemble model integrated both models. Comparison with existing clinical scores (MSS, SEDAN, GRASPS) was performed using the DeLong test. RESULTS: Of the 445 individuals, 202 (45.4%) had HT, 79 (17.8%) had hemorrhagic infarction, and 123 (27.6%) had PH. In the test cohort, the area under the receiver operating characteristic curve (AUROC) of the clinical, imaging, and ensemble model for HT prediction was 0.877, 0.920, and 0.937, respectively. The ensemble model for HT prediction outperformed MSS, SEDAN, and GRASPS scores (p ≤ 0.023). The ensemble model predicted PH and PH-2 with ...