Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg-Eppendorf, Martinistr. 52, 20246, Hamburg, Germany.
Institute of Clinical Radiology, University Hospital of Muenster, Albert-Schweitzer-Campus 1, 48149, Muenster, Germany.
J Neurol. 2020 Sep;267(9):2632-2641. doi: 10.1007/s00415-020-09859-4. Epub 2020 May 11.
Triage of patients with basilar artery occlusion for additional imaging diagnostics, therapy planning, and initial outcome prediction requires assessment of early ischemic changes in early hyperacute non-contrast computed tomography (NCCT) scans. However, accuracy of visual evaluation is impaired by inter- and intra-reader variability, artifacts in the posterior fossa and limited sensitivity for subtle density shifts. We propose a machine learning approach for detecting early ischemic changes in pc-ASPECTS regions (Posterior circulation Alberta Stroke Program Early CT Score) based on admission NCCTs.
The retrospective study includes 552 pc-ASPECTS regions (144 with infarctions in follow-up NCCTs) extracted from pre-therapeutic early hyperacute scans of 69 patients with basilar artery occlusion that later underwent successful recanalization. We evaluated 1218 quantitative image features utilizing random forest algorithms with fivefold cross-validation for the ability to detect early ischemic changes in hyperacute images that lead to definitive infarctions in follow-up imaging. Classifier performance was compared to conventional readings of two neuroradiologists.
Receiver operating characteristic area under the curves for detection of early ischemic changes were 0.70 (95% CI [0.64; 0.75]) for cerebellum to 0.82 (95% CI [0.77; 0.86]) for thalamus. Predictive performance of the classifier was significantly higher compared to visual reading for thalamus, midbrain, and pons (P value < 0.05).
Quantitative features of early hyperacute NCCTs can be used to detect early ischemic changes in pc-ASPECTS regions. The classifier performance was higher or equal to results of human raters. The proposed approach could facilitate reproducible analysis in research and may allow standardized assessments for outcome prediction and therapy planning in clinical routine.
对基底动脉闭塞患者进行分诊，以进行额外的影像学诊断、治疗计划和初始预后预测，需要评估早期超急性非对比 CT（NCCT）扫描中的早期缺血性改变。然而，视觉评估的准确性受到观察者间和观察者内的变异性、后颅窝伪影以及对细微密度变化的敏感性有限的影响。我们提出了一种基于入院 NCCT 检测 pc-ASPECTS 区域（后循环 Alberta 卒中项目早期 CT 评分）早期缺血性改变的机器学习方法。
这项回顾性研究包括 552 个 pc-ASPECTS 区域（144 个在随访 NCCT 中有梗死），这些区域来自 69 例基底动脉闭塞患者的治疗前早期超急性扫描，这些患者后来成功进行了再通。我们利用随机森林算法评估了 1218 个定量图像特征，采用五重交叉验证来评估这些特征在超急性图像中检测导致随访成像中明确梗死的早期缺血性改变的能力。将分类器的性能与两位神经放射科医生的常规阅读进行比较。
小脑的检测早期缺血性改变的接收者操作特征曲线下面积为 0.70（95%置信区间[0.64；0.75]），而丘脑的面积为 0.82（95%置信区间[0.77；0.86]）。与视觉阅读相比，分类器对丘脑、中脑和脑桥的预测性能显著更高（P 值<0.05）。
早期超急性 NCCT 的定量特征可用于检测 pc-ASPECTS 区域的早期缺血性改变。分类器的性能与人类观察者的结果相当或更高。所提出的方法可以促进研究中的可重复性分析，并可能允许在临床常规中进行预后预测和治疗计划的标准化评估。
