深度学习在急性缺血性脑卒中患者机械取栓后再通首次通过效果预测中的应用。
A Deep Learning Approach to Predict Recanalization First-Pass Effect following Mechanical Thrombectomy in Patients with Acute Ischemic Stroke.
机构信息
From the Computational Diagnostics Lab (H.Z., J.S.P., Z.W., W.F.S., C.W.A.), University of California, Los Angeles, California.
Department of Bioengineering (H.Z., J.S.P., Z.W., C.W.A.), University of California, Los Angeles, California.
出版信息
AJNR Am J Neuroradiol. 2024 Aug 9;45(8):1044-1052. doi: 10.3174/ajnr.A8272.
BACKGROUND AND PURPOSE
Following endovascular thrombectomy in patients with large-vessel occlusion stroke, successful recanalization from 1 attempt, known as the first-pass effect, has correlated favorably with long-term outcomes. Pretreatment imaging may contain information that can be used to predict the first-pass effect. Recently, applications of machine learning models have shown promising results in predicting recanalization outcomes, albeit requiring manual segmentation. In this study, we sought to construct completely automated methods using deep learning to predict the first-pass effect from pretreatment CT and MR imaging.
MATERIALS AND METHODS
Our models were developed and evaluated using a cohort of 326 patients who underwent endovascular thrombectomy at UCLA Ronald Reagan Medical Center from 2014 to 2021. We designed a hybrid transformer model with nonlocal and cross-attention modules to predict the first-pass effect on MR imaging and CT series.
RESULTS
The proposed method achieved a mean 0.8506 (SD, 0.0712) for cross-validation receiver operating characteristic area under the curve (ROC-AUC) on MR imaging and 0.8719 (SD, 0.0831) for cross-validation ROC-AUC on CT. When evaluated on the prospective test sets, our proposed model achieved a mean ROC-AUC of 0.7967 (SD, 0.0335) with a mean sensitivity of 0.7286 (SD, 0.1849) and specificity of 0.8462 (SD, 0.1216) for MR imaging and a mean ROC-AUC of 0.8051 (SD, 0.0377) with a mean sensitivity of 0.8615 (SD, 0.1131) and specificity 0.7500 (SD, 0.1054) for CT, respectively, representing the first classification of the first-pass effect from MR imaging alone and the first automated first-pass effect classification method in CT.
CONCLUSIONS
Results illustrate that both nonperfusion MR imaging and CT from admission contain signals that can predict a successful first-pass effect following endovascular thrombectomy using our deep learning methods without requiring time-intensive manual segmentation.
背景与目的
血管内血栓切除术治疗大动脉闭塞性脑卒中患者后，首次通过效果（即 1 次尝试即可成功再通）与长期预后良好相关。预处理成像中可能包含可用于预测首次通过效果的信息。最近，机器学习模型在预测再通结果方面显示出了有前景的结果，尽管需要手动分割。在这项研究中，我们试图构建完全自动化的方法，使用深度学习从预处理 CT 和 MR 成像预测首次通过效果。
材料与方法
我们的模型是使用 2014 年至 2021 年期间在加州大学洛杉矶分校罗纳德·里根医疗中心接受血管内血栓切除术的 326 名患者的队列进行开发和评估的。我们设计了一个带有非局部和交叉注意模块的混合变压器模型，以预测 MR 成像和 CT 系列上的首次通过效果。
结果
该方法在 MR 成像的交叉验证受试者工作特征曲线（ROC-AUC）上的平均得分为 0.8506（标准差为 0.0712），在 CT 的交叉验证 ROC-AUC 上的平均得分为 0.8719（标准差为 0.0831）。在前瞻性测试集中进行评估时，我们提出的模型的平均 ROC-AUC 为 0.7967（标准差为 0.0335），平均敏感性为 0.7286（标准差为 0.1849）和特异性为 0.8462（标准差为 0.1216）用于 MR 成像，平均 ROC-AUC 为 0.8051（标准差为 0.0377），平均敏感性为 0.8615（标准差为 0.1131）和特异性为 0.7500（标准差为 0.1054），分别代表单独从 MR 成像首次分类首次通过效果和首次自动分类 CT 中的首次通过效果的方法。
结论
结果表明，使用我们的深度学习方法，入院时的非灌注 MR 成像和 CT 都包含可以预测血管内血栓切除术后首次通过效果的信号，而无需耗时的手动分割。
Zotero 插件