icometrix, Leuven, Belgium.
Department of Informatics, Technical University of Munich, Munich, Germany.
PLoS One. 2023 Mar 30;18(3):e0283610. doi: 10.1371/journal.pone.0283610. eCollection 2023.
Current guidelines for CT perfusion (CTP) in acute stroke suggest acquiring scans with a minimal duration of 60-70 s. But even then, CTP analysis can be affected by truncation artifacts. Conversely, shorter acquisitions are still widely used in clinical practice and may, sometimes, be sufficient to reliably estimate lesion volumes. We aim to devise an automatic method that detects scans affected by truncation artifacts.
Shorter scan durations are simulated from the ISLES'18 dataset by consecutively removing the last CTP time-point until reaching a 10 s duration. For each truncated series, perfusion lesion volumes are quantified and used to label the series as unreliable if the lesion volumes considerably deviate from the original untruncated ones. Afterwards, nine features from the arterial input function (AIF) and the vascular output function (VOF) are derived and used to fit machine-learning models with the goal of detecting unreliably truncated scans. Methods are compared against a baseline classifier solely based on the scan duration, which is the current clinical standard. The ROC-AUC, precision-recall AUC and the F1-score are measured in a 5-fold cross-validation setting.
The best performing classifier obtained an ROC-AUC of 0.982, precision-recall AUC of 0.985 and F1-score of 0.938. The most important feature was the AIFcoverage, measured as the time difference between the scan duration and the AIF peak. When using the AIFcoverage to build a single feature classifier, an ROC-AUC of 0.981, precision-recall AUC of 0.984 and F1-score of 0.932 were obtained. In comparison, the baseline classifier obtained an ROC-AUC of 0.954, precision-recall AUC of 0.958 and F1-Score of 0.875.
Machine learning models fed with AIF and VOF features accurately detected unreliable stroke lesion measurements due to insufficient acquisition duration. The AIFcoverage was the most predictive feature of truncation and identified unreliable short scans almost as good as machine learning. We conclude that AIF/VOF based classifiers are more accurate than the scans' duration for detecting truncation. These methods could be transferred to perfusion analysis software in order to increase the interpretability of CTP outputs.
目前急性脑卒中 CT 灌注（CTP）的指南建议扫描持续时间至少为 60-70 秒。但即便如此，CTP 分析也可能受到截断伪影的影响。相反，较短的采集在临床实践中仍然被广泛使用，有时也足以可靠地估计病变体积。我们旨在设计一种自动检测受截断伪影影响的扫描的方法。
通过连续删除最后一个 CTP 时间点，从 ISLES'18 数据集模拟较短的扫描持续时间，直到达到 10 秒的持续时间。对于每个截断系列，定量灌注病变体积，如果病变体积与原始未截断系列有较大偏差，则将该系列标记为不可靠。之后，从动脉输入函数（AIF）和血管输出函数（VOF）中提取九个特征，并使用这些特征拟合机器学习模型，以检测不可靠的截断扫描。方法与仅基于扫描持续时间的基线分类器进行比较，这是当前的临床标准。在 5 折交叉验证设置中测量 ROC-AUC、精度-召回 AUC 和 F1 分数。
表现最好的分类器获得了 0.982 的 ROC-AUC、0.985 的精度-召回 AUC 和 0.938 的 F1 分数。最重要的特征是 AIFcoverage，定义为扫描持续时间与 AIF 峰值之间的时间差。当使用 AIFcoverage 构建单个特征分类器时，获得了 0.981 的 ROC-AUC、0.984 的精度-召回 AUC 和 0.932 的 F1 分数。相比之下，基线分类器获得了 0.954 的 ROC-AUC、0.958 的精度-召回 AUC 和 0.875 的 F1 分数。
使用 AIF 和 VOF 特征训练的机器学习模型可以准确检测因采集时间不足而导致的不可靠的脑卒中病变测量值。AIFcoverage 是截断的最具预测性特征，它几乎可以与机器学习一样准确地识别不可靠的短扫描。我们得出结论，基于 AIF/VOF 的分类器比扫描持续时间更准确，用于检测截断。这些方法可以转移到灌注分析软件中，以提高 CTP 输出的可解释性。
