Department of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, Technische Universität München, Ismaninger Str. 22, 81675, Munich, Germany.
Chair for Computer Aided Medical Procedures & Augmented Reality, Technische Universität München, Munich, Germany.
Clin Neuroradiol. 2022 Jun;32(2):419-426. doi: 10.1007/s00062-021-01081-7. Epub 2021 Aug 31.
Advanced machine-learning (ML) techniques can potentially detect the entire spectrum of pathology through deviations from a learned norm. We investigated the utility of a weakly supervised ML tool to detect characteristic findings related to ischemic stroke in head CT and provide subsequent patient triage.
Patients having undergone non-enhanced head CT at a tertiary care hospital in April 2020 with either no anomalies, subacute or chronic ischemia, lacunar infarcts of the deep white matter or hyperdense vessel signs were retrospectively analyzed. Anomaly detection was performed using a weakly supervised ML classifier. Findings were displayed on a voxel-level (heatmap) and pooled to an anomaly score. Thresholds for this score classified patients into i) normal, ii) inconclusive, iii) pathological. Expert-validated radiological reports were considered as ground truth. Test assessment was performed with ROC analysis; inconclusive results were pooled to pathological predictions for accuracy measurements.
During the investigation period 208 patients were referred for head CT of which 111 could be included. Definite ratings into normal/pathological were feasible in 77 (69.4%) patients. Based on anomaly scores, the AUC to differentiate normal from pathological scans was 0.98 (95% CI 0.97-1.00). The sensitivity, specificity, positive and negative predictive values were 100%, 40.6%, 80.6% and 100%, respectively.
Our study demonstrates the potential of a weakly supervised anomaly-detection tool to detect stroke findings in head CT. Definite classification into normal/pathological was made with high accuracy in > 2/3 of patients. Anomaly heatmaps further provide guidance towards pathologies, also in cases with inconclusive ratings.
先进的机器学习（ML）技术可以通过偏离已学习的规范来潜在地检测整个病理学谱。我们研究了一种弱监督 ML 工具在检测头 CT 中与缺血性中风相关的特征表现并进行后续患者分诊的实用性。
回顾性分析了 2020 年 4 月在一家三级护理医院进行非增强头部 CT 检查的患者，这些患者要么没有异常，要么存在亚急性或慢性缺血、深部白质腔隙性梗死或高密度血管征。使用弱监督 ML 分类器进行异常检测。结果以体素级（热图）显示，并汇总为异常评分。该评分的阈值将患者分为 i）正常，ii）不确定，iii）异常。专家验证的放射学报告被视为金标准。使用 ROC 分析进行测试评估；将不确定结果汇总为病理预测以进行准确性测量。
在调查期间，有 208 例患者被转介进行头部 CT 检查，其中 111 例可纳入研究。77 例（69.4%）患者可明确归类为正常/异常。基于异常评分，区分正常与异常扫描的 AUC 为 0.98（95%CI 0.97-1.00）。敏感性、特异性、阳性和阴性预测值分别为 100%、40.6%、80.6%和 100%。
我们的研究表明，一种弱监督异常检测工具具有在头部 CT 中检测中风表现的潜力。在超过 2/3 的患者中，该工具以较高的准确率将患者明确分类为正常/异常。异常热图还为病理表现提供了指导，即使在不确定评分的情况下也是如此。
