Predicting functional outcome in patients with acute brainstem infarction using deep neuroimaging features
Predicting functional outcome in patients with acute brainstem infarction using deep neuroimaging features
复制标题
利用深层神经影像特征预测急性脑干梗死患者的功能结果
DOI：
10.1111/ene.15181
复制
发表时间：
2021-11-22
影响因子：
5.1
通讯作者：
Li, Zixiao
中科院分区：
文献类型：
--
作者：
Ding, Lingling;Liu, Ziyang;Li, Zixiao
背景与目的急性脑干梗死可导致严重的功能损害。我们的目的是利用卷积神经网络（cnn）提取的深度神经成像特征来预测急性脑干梗死患者的功能结局。方法全国多中心卒中登记研究纳入1482例急性脑干梗死患者。我们应用cnn从弥散加权成像中自动提取深层神经成像特征。基于临床特征、实验室特征、常规影像学特征（梗死体积、梗死数量）和深度神经影像学特征的深度学习模型被训练以预测脑卒中后3个月的功能结局。不良结局定义为3个月时改良Rankin量表得分为3分或更高。通过比较受者工作特性曲线下面积（AUC）对模型进行评价。结果仅基于cnn的14个深度神经影像学特征的模型在预测功能结局方面取得了极高的AUC(0.975)(95%置信区间[CI] = 0.934-0.997)，显著优于结合临床、实验室和常规影像学特征的模型（0.772,95% CI = 0.691-0.847, p < 0.001）。与传统的预后评分相比，深度神经成像模型也显示出显著的改善。在一项可解释性分析中，深度神经影像学特征显示与年龄、美国国立卫生研究院卒中量表评分、梗死体积和炎症因素有显著相关性。结论深度学习模型能够自动从常规影像学资料中提取客观的神经影像学特征，有助于预测脑干梗死患者3个月的功能结局，准确率很高。
Background and purpose Acute brainstem infarctions can lead to serious functional impairments. We aimed to predict functional outcomes in patients with acute brainstem infarction using deep neuroimaging features extracted by convolutional neural networks (CNNs). Methods This nationwide multicenter stroke registry study included 1482 patients with acute brainstem infarction. We applied CNNs to automatically extract deep neuroimaging features from diffusion-weighted imaging. Deep learning models based on clinical features, laboratory features, conventional imaging features (infarct volume, number of infarctions), and deep neuroimaging features were trained to predict functional outcomes at 3 months poststroke. Unfavorable outcome was defined as modified Rankin Scale score of 3 or higher at 3 months. The models were evaluated by comparing the area under the receiver operating characteristic curve (AUC). Results A model based solely on 14 deep neuroimaging features from CNNs achieved an extremely high AUC of 0.975 (95% confidence interval [CI] = 0.934-0.997) and significantly outperformed the model combining clinical, laboratory, and conventional imaging features (0.772, 95% CI = 0.691-0.847, p < 0.001) in prediction of functional outcomes. The deep neuroimaging model also demonstrated significant improvement over traditional prognostic scores. In an interpretability analysis, the deep neuroimaging features displayed a significant correlation with age, National Institutes of Health Stroke Scale score, infarct volume, and inflammation factors. Conclusions Deep learning models can successfully extract objective neuroimaging features from the routine radiological data in an automatic manner and aid in predicting the functional outcomes in patients with brainstem infarction at 3 months with very high accuracy.