Xu Xian, Zhou Yanfeng, Sun Shasha, Cui Longbiao, Chen Zhiye, Guo Yuanhao, Jiang Jiacheng, Wang Xinjiang, Sun Ting, Yang Qian, Wang Yujia, Yuan Yuan, Fan Li, Yang Ge, Cao Feng
Department of Radiology, The Second Medical Center & National Clinical Research Center for Geriatric Diseases, Chinese PLA General Hospital, Beijing, China.
School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China.
Eur Radiol. 2025 Jan 9. doi: 10.1007/s00330-024-11336-9.
To establish morphological and radiomic models for early prediction of cognitive impairment associated with cerebrovascular disease (CI-CVD) in an elderly cohort based on cerebral magnetic resonance angiography (MRA).
One-hundred four patients with CI-CVD and 107 control subjects were retrospectively recruited from the 14-year elderly MRA cohort, and 63 subjects were enrolled for external validation. Automated quantitative analysis was applied to analyse the morphological features, including the stenosis score, length, relative length, twisted angle, and maximum deviation of cerebral arteries. Clinical and morphological risk factors were screened using univariate logistic regression. Radiomic features were extracted via least absolute shrinkage and selection operator (LASSO) regression. The predictive models of CI-CVD were established in the training set and verified in the external testing set.
A history of stroke was demonstrated to be a clinical risk factor (OR 2.796, 1.359-5.751). Stenosis ≥ 50% in the right middle cerebral artery (RMCA) and left posterior cerebral artery (LPCA), maximum deviation of the left internal carotid artery (LICA), and twisted angles of the right internal carotid artery (RICA) and LICA were identified as morphological risk factors, with ORs of 4.522 (1.237-16.523), 2.851 (1.438-5.652), 1.373 (1.136-1.661), 0.981 (0.966-0.997) and 0.976 (0.958-0.994), respectively. Overall, 33 radiomic features were screened as risk factors. The clinical-morphological-radiomic model demonstrated optimal performance, with an AUC of 0.883 (0.838-0.928) in the training set and 0.843 (0.743-0.943) in the external testing set.
Radiomics features combined with morphological indicators of cerebral arteries were effective indicators for early signs of CI-CVD in elderly individuals.
Question The relationship between morphological features of cerebral arteries and cognitive impairment associated with cerebrovascular disease (CI-CVD) deserves to be explored. Findings The multipredictor model combining with stroke history, vascular morphological indicators and radiomic features of cerebral arteries demonstrated optimal performance for the early warning of CI-CVD. Clinical relevance Stenosis percentage and tortuosity score of the cerebral arteries are important risk factors for cognitive impairment. The radiomic features combined with morphological quantification analysis based on cerebral MRA provide higher predictive performance of CI-CVD.
基于脑磁共振血管造影（MRA）建立老年队列中脑血管疾病相关认知障碍（CI-CVD）早期预测的形态学和放射组学模型。
从14年的老年MRA队列中回顾性招募了104例CI-CVD患者和107例对照受试者，并纳入63例受试者进行外部验证。应用自动定量分析来分析形态学特征，包括脑动脉的狭窄评分、长度、相对长度、扭曲角度和最大偏差。使用单因素逻辑回归筛选临床和形态学危险因素。通过最小绝对收缩和选择算子（LASSO）回归提取放射组学特征。在训练集中建立CI-CVD的预测模型，并在外部测试集中进行验证。
卒中史被证明是一个临床危险因素（OR 2.796，1.359 - 5.751）。右侧大脑中动脉（RMCA）和左侧大脑后动脉（LPCA）狭窄≥50%、左侧颈内动脉（LICA）的最大偏差以及右侧颈内动脉（RICA）和LICA的扭曲角度被确定为形态学危险因素，OR分别为4.522（1.237 - 16.523）、2.851（1.438 - 5.652）、1.373（1.136 - 1.661）、0.981（0.966 - 0.997）和0.976（0.958 - 0.994）。总体而言，筛选出33个放射组学特征作为危险因素。临床-形态学-放射组学模型表现出最佳性能，训练集中的AUC为0.883（0.838 - 0.928），外部测试集中的AUC为0.843（0.743 - 0.943）。
放射组学特征与脑动脉形态学指标相结合是老年个体CI-CVD早期迹象的有效指标。
问题 脑动脉形态学特征与脑血管疾病相关认知障碍（CI-CVD）之间的关系值得探索。发现 结合卒中史、血管形态学指标和脑动脉放射组学特征的多预测模型在CI-CVD早期预警方面表现出最佳性能。临床相关性 脑动脉狭窄百分比和迂曲评分是认知障碍的重要危险因素。基于脑MRA的放射组学特征与形态学定量分析相结合，对CI-CVD具有更高的预测性能。
Zotero 插件