Department of Neurology, Chung-Ang University Gwangmyeong Hospital, Gwangmyeong, South Korea.
Department of Neurology, Yonsei University College of Medicine, Seoul, South Korea.
Eur Radiol. 2024 Sep;34(9):6005-6015. doi: 10.1007/s00330-024-10618-6. Epub 2024 Feb 3.
This study explores whether textural features from initial non-contrast CT scans of infarcted brain tissue are linked to hemorrhagic transformation susceptibility.
Stroke patients undergoing thrombolysis or thrombectomy from Jan 2012 to Jan 2022 were analyzed retrospectively. Hemorrhagic transformation was defined using follow-up magnetic resonance imaging. A total of 94 radiomic features were extracted from the infarcted tissue on initial NCCT scans. Patients were divided into training and test sets (7:3 ratio). Two models were developed with fivefold cross-validation: one incorporating first-order and textural radiomic features, and another using only textural radiomic features. A clinical model was also constructed using logistic regression with clinical variables, and test set validation was performed.
Among 362 patients, 218 had hemorrhagic transformations. The LightGBM model with all radiomics features had the best performance, with an area under the receiver operating characteristic curve (AUROC) of 0.986 (95% confidence interval [CI], 0.971-1.000) on the test dataset. The ExtraTrees model performed best when textural features were employed, with an AUROC of 0.845 (95% CI, 0.774-0.916). Minimum, maximum, and ten percentile values were significant predictors of hemorrhagic transformation. The clinical model showed an AUROC of 0.544 (95% CI, 0.431-0.658). The performance of the radiomics models was significantly better than that of the clinical model on the test dataset (p < 0.001).
The radiomics model can predict hemorrhagic transformation using NCCT in stroke patients. Low Hounsfield unit was a strong predictor of hemorrhagic transformation, while textural features alone can predict hemorrhagic transformation.
Using radiomic features extracted from initial non-contrast computed tomography, early prediction of hemorrhagic transformation has the potential to improve patient care and outcomes by aiding in personalized treatment decision-making and early identification of at-risk patients.
• Predicting hemorrhagic transformation following thrombolysis in stroke is challenging since multiple factors are associated. • Radiomics features of infarcted tissue on initial non-contrast CT are associated with hemorrhagic transformation. • Textural features on non-contrast CT are associated with the frailty of the infarcted tissue.
本研究旨在探讨梗死脑组织初始平扫 CT 纹理特征是否与出血转化易感性相关。
回顾性分析 2012 年 1 月至 2022 年 1 月期间接受溶栓或取栓治疗的脑卒中患者。采用随访磁共振成像定义出血转化。从初始 NCCT 扫描的梗死组织中提取 94 个放射组学特征。患者分为训练集和测试集（比例为 7:3）。使用五重交叉验证分别建立了包含一阶和纹理放射组学特征的模型和仅使用纹理放射组学特征的模型。使用逻辑回归结合临床变量构建临床模型，并在测试集上进行验证。
在 362 例患者中，218 例发生出血转化。包含所有放射组学特征的 LightGBM 模型在测试数据集上的表现最佳，受试者工作特征曲线下面积（AUROC）为 0.986（95%置信区间[CI]，0.971-1.000）。当使用纹理特征时，ExtraTrees 模型表现最佳，AUROC 为 0.845（95%CI，0.774-0.916）。最小值、最大值和十分位数值是出血转化的显著预测因子。临床模型的 AUROC 为 0.544（95%CI，0.431-0.658）。放射组学模型在测试数据集上的性能明显优于临床模型（p<0.001）。
使用 NCCT 可以基于放射组学模型预测脑卒中患者的出血转化。低亨斯菲尔德单位值是出血转化的强预测因子，而仅使用纹理特征即可预测出血转化。
使用初始平扫 CT 提取的放射组学特征，可以通过辅助个体化治疗决策制定和早期识别高危患者，提高患者护理和预后，实现出血转化的早期预测。
• 预测溶栓后脑卒中的出血转化具有挑战性，因为有多种因素与之相关。• 梗死组织的初始平扫 CT 纹理特征与出血转化相关。• 平扫 CT 的纹理特征与梗死组织的脆弱性相关。
