PDF(Pubmed)
Abstract：
UNASSIGNED: Computed Tomography Angiography (CTA) is the first line of imaging in the diagnosis of Large Vessel Occlusion (LVO) strokes. We trained and independently validated end-to-end automated deep learning pipelines to predict 3-month outcomes after anterior circulation LVO thrombectomy based on admission CTAs.
UNASSIGNED: We split a dataset of 591 patients into training/cross-validation (n = 496) and independent test set (n = 95). We trained separate models for outcome prediction based on admission \"CTA\" images alone, \"CTA + Treatment\" (including time to thrombectomy and reperfusion success information), and \"CTA + Treatment + Clinical\" (including admission age, sex, and NIH stroke scale). A binary (favorable) outcome was defined based on a 3-month modified Rankin Scale ≤ 2. The model was trained on our dataset based on the pre-trained ResNet-50 3D Convolutional Neural Network (\"MedicalNet\") and included CTA preprocessing steps.
UNASSIGNED: We generated an ensemble model from the 5-fold cross-validation, and tested it in the independent test cohort, with receiver operating characteristic area under the curve (AUC, 95% confidence interval) of 70 (0.59-0.81) for \"CTA,\" 0.79 (0.70-0.89) for \"CTA + Treatment,\" and 0.86 (0.79-0.94) for \"CTA + Treatment + Clinical\" input models. A \"Treatment + Clinical\" logistic regression model achieved an AUC of 0.86 (0.79-0.93).
UNASSIGNED: Our results show the feasibility of an end-to-end automated model to predict outcomes from admission and post-thrombectomy reperfusion success. Such a model can facilitate prognostication in telehealth transfer and when a thorough neurological exam is not feasible due to language barrier or pre-existing morbidities.
UNASSIGNED: We split a dataset of 591 patients into training/cross-validation (n = 496) and independent test set (n = 95). We trained separate models for outcome prediction based on admission \"CTA\" images alone, \"CTA + Treatment\" (including time to thrombectomy and reperfusion success information), and \"CTA + Treatment + Clinical\" (including admission age, sex, and NIH stroke scale). A binary (favorable) outcome was defined based on a 3-month modified Rankin Scale ≤ 2. The model was trained on our dataset based on the pre-trained ResNet-50 3D Convolutional Neural Network (\"MedicalNet\") and included CTA preprocessing steps.
UNASSIGNED: We generated an ensemble model from the 5-fold cross-validation, and tested it in the independent test cohort, with receiver operating characteristic area under the curve (AUC, 95% confidence interval) of 70 (0.59-0.81) for \"CTA,\" 0.79 (0.70-0.89) for \"CTA + Treatment,\" and 0.86 (0.79-0.94) for \"CTA + Treatment + Clinical\" input models. A \"Treatment + Clinical\" logistic regression model achieved an AUC of 0.86 (0.79-0.93).
UNASSIGNED: Our results show the feasibility of an end-to-end automated model to predict outcomes from admission and post-thrombectomy reperfusion success. Such a model can facilitate prognostication in telehealth transfer and when a thorough neurological exam is not feasible due to language barrier or pre-existing morbidities.
摘要：
■计算机断层扫描血管造影（CTA）是诊断大血管闭塞（LVO）中风的第一线成像。我们训练并独立验证了端到端自动化深度学习管道，以根据入院CTA预测前循环LVO血栓切除术后3个月的结果。
■我们将591名患者的数据集分为训练/交叉验证（n=496）和独立测试集（n=95）。我们只根据入院“CTA”图像训练单独的结果预测模型，“CTA+治疗”（包括血栓切除时间和再灌注成功信息），和“CTA+治疗+临床”(包括入院年龄，性别,和NIH中风量表)。根据3个月修改的Rankin量表≤2定义二元（有利）结果。该模型在我们的数据集上基于预训练的ResNet-503D卷积神经网络（“MedicalNet”）进行训练，并包括CTA预处理步骤。
■我们从5倍交叉验证中生成了一个集成模型，并在独立测试队列中进行了测试，曲线下的接收器工作特征面积(AUC，CTA的95%置信区间)为70(0.59-0.81)，CTA+治疗的\“0.79（0.70-0.89），“CTA+治疗+临床”输入模型为0.86(0.79-0.94)。“治疗+临床”逻辑回归模型的AUC为0.86(0.79-0.93)。
■我们的结果显示了端到端自动化模型预测入院和血栓切除术后再灌注成功结果的可行性。这样的模型可以促进远程医疗传输中的预测，并且当由于语言障碍或预先存在的疾病而无法进行彻底的神经学检查时。
■我们将591名患者的数据集分为训练/交叉验证（n=496）和独立测试集（n=95）。我们只根据入院“CTA”图像训练单独的结果预测模型，“CTA+治疗”（包括血栓切除时间和再灌注成功信息），和“CTA+治疗+临床”(包括入院年龄，性别,和NIH中风量表)。根据3个月修改的Rankin量表≤2定义二元（有利）结果。该模型在我们的数据集上基于预训练的ResNet-503D卷积神经网络（“MedicalNet”）进行训练，并包括CTA预处理步骤。
■我们从5倍交叉验证中生成了一个集成模型，并在独立测试队列中进行了测试，曲线下的接收器工作特征面积(AUC，CTA的95%置信区间)为70(0.59-0.81)，CTA+治疗的\“0.79（0.70-0.89），“CTA+治疗+临床”输入模型为0.86(0.79-0.94)。“治疗+临床”逻辑回归模型的AUC为0.86(0.79-0.93)。
■我们的结果显示了端到端自动化模型预测入院和血栓切除术后再灌注成功结果的可行性。这样的模型可以促进远程医疗传输中的预测，并且当由于语言障碍或预先存在的疾病而无法进行彻底的神经学检查时。
