Computational Diagnostics Lab, University of California, Los Angeles, CA 90024, USA; Department of Bioengineering, University of California, Los Angeles, CA 90024, USA.
Department of Radiology, University of California, Los Angeles, CA 90024, USA.
Comput Med Imaging Graph. 2021 Jun;90:101926. doi: 10.1016/j.compmedimag.2021.101926. Epub 2021 Apr 24.
Treatment of acute ischemic strokes (AIS) is largely contingent upon the time since stroke onset (TSS). However, TSS may not be readily available in up to 25% of patients with unwitnessed AIS. Current clinical guidelines for patients with unknown TSS recommend the use of MRI to determine eligibility for thrombolysis, but radiology assessments have high inter-reader variability. In this work, we present deep learning models that leverage MRI diffusion series to classify TSS based on clinically validated thresholds. We propose an intra-domain task-adaptive transfer learning method, which involves training a model on an easier clinical task (stroke detection) and then refining the model with different binary thresholds of TSS. We apply this approach to both 2D and 3D CNN architectures with our top model achieving an ROC-AUC value of 0.74, with a sensitivity of 0.70 and a specificity of 0.81 for classifying TSS < 4.5 h. Our pretrained models achieve better classification metrics than the models trained from scratch, and these metrics exceed those of previously published models applied to our dataset. Furthermore, our pipeline accommodates a more inclusive patient cohort than previous work, as we did not exclude imaging studies based on clinical, demographic, or image processing criteria. When applied to this broad spectrum of patients, our deep learning model achieves an overall accuracy of 75.78% when classifying TSS < 4.5 h, carrying potential therapeutic implications for patients with unknown TSS.
急性缺血性脑卒中（AIS）的治疗在很大程度上取决于发病时间（TSS）。然而，多达 25%的无目击者 AIS 患者可能无法获得 TSS。对于 TSS 未知的患者，当前的临床指南建议使用 MRI 来确定溶栓的资格，但影像学评估存在很大的读者间差异。在这项工作中，我们提出了利用 MRI 弥散系列基于临床验证的阈值来分类 TSS 的深度学习模型。我们提出了一种域内任务自适应迁移学习方法，该方法涉及在较简单的临床任务（中风检测）上训练模型，然后使用不同的 TSS 二进制阈值来细化模型。我们将这种方法应用于 2D 和 3D CNN 架构，我们的顶级模型在分类 TSS < 4.5 小时时的 ROC-AUC 值为 0.74，灵敏度为 0.70，特异性为 0.81。我们的预训练模型比从头开始训练的模型具有更好的分类指标，这些指标超过了应用于我们数据集的先前发表的模型的指标。此外，我们的流水线比以前的工作更能容纳更广泛的患者群体，因为我们没有根据临床、人口统计学或图像处理标准排除成像研究。当应用于这个广泛的患者群体时，我们的深度学习模型在分类 TSS < 4.5 小时时的总体准确率为 75.78%，这对 TSS 未知的患者具有潜在的治疗意义。
