Stanford School of Medicine, Stanford, USA.
Department of Computer Science, Stanford University, Stanford, USA.
Sci Rep. 2023 Sep 26;13(1):16153. doi: 10.1038/s41598-023-42961-x.
We determined if a convolutional neural network (CNN) deep learning model can accurately segment acute ischemic changes on non-contrast CT compared to neuroradiologists. Non-contrast CT (NCCT) examinations from 232 acute ischemic stroke patients who were enrolled in the DEFUSE 3 trial were included in this study. Three experienced neuroradiologists independently segmented hypodensity that reflected the ischemic core on each scan. The neuroradiologist with the most experience (expert A) served as the ground truth for deep learning model training. Two additional neuroradiologists' (experts B and C) segmentations were used for data testing. The 232 studies were randomly split into training and test sets. The training set was further randomly divided into 5 folds with training and validation sets. A 3-dimensional CNN architecture was trained and optimized to predict the segmentations of expert A from NCCT. The performance of the model was assessed using a set of volume, overlap, and distance metrics using non-inferiority thresholds of 20%, 3 ml, and 3 mm, respectively. The optimized model trained on expert A was compared to test experts B and C. We used a one-sided Wilcoxon signed-rank test to test for the non-inferiority of the model-expert compared to the inter-expert agreement. The final model performance for the ischemic core segmentation task reached a performance of 0.46 ± 0.09 Surface Dice at Tolerance 5mm and 0.47 ± 0.13 Dice when trained on expert A. Compared to the two test neuroradiologists the model-expert agreement was non-inferior to the inter-expert agreement, [Formula: see text]. The before, CNN accurately delineates the hypodense ischemic core on NCCT in acute ischemic stroke patients with an accuracy comparable to neuroradiologists.
我们确定卷积神经网络（CNN）深度学习模型是否可以准确地将急性缺血性改变与神经放射科医生的非对比 CT 进行分割。这项研究纳入了 232 名急性缺血性中风患者的非对比 CT（NCCT）检查，这些患者都参与了 DEFUSE 3 试验。三位经验丰富的神经放射科医生分别对每一次扫描中的低密度区域进行分割，这些区域反映了缺血核心。经验最丰富的神经放射科医生（专家 A）的分割结果被用作深度学习模型训练的金标准。另外两位神经放射科医生（专家 B 和 C）的分割结果用于数据测试。232 项研究被随机分为训练集和测试集。训练集进一步随机分为 5 个部分，其中包括训练集和验证集。一个 3 维 CNN 架构被训练和优化，以从 NCCT 预测专家 A 的分割结果。使用一组体积、重叠和距离度量标准，分别使用非劣性阈值为 20%、3ml 和 3mm，来评估模型的性能。在专家 A 上训练的优化模型与测试专家 B 和 C 进行了比较。我们使用单侧 Wilcoxon 符号秩检验来检验模型-专家与专家间一致性的非劣效性。最终的缺血核心分割任务模型性能在容忍度为 5mm 时达到了 0.46±0.09 的表面 Dice 值，在训练专家 A 时达到了 0.47±0.13 的 Dice 值。与两位测试神经放射科医生相比，模型-专家的一致性不劣于专家间的一致性，[公式：见文本]。在急性缺血性中风患者中，CNN 可以准确地描绘 NCCT 上的低信号缺血核心，其准确性与神经放射科医生相当。
