文献速递脑血管病

深度学习衍生的高级神经影像特征可预测大血管闭塞的临床结局

Deep Learning-Derived High-Level Neuroimaging Features Predict Clinical Outcomes for Large Vessel Occlusion.
PubMed 文献 · Stroke · 2020-04-06

本研究为多中心回顾性研究,纳入2013至2018年接受机械取栓的前循环大血管闭塞患者,利用深度学习模型从治疗前弥散加权成像数据中提取影像特征,并预测90天改良Rankin量表评分0-2分的良好临床结局。结果显示,卷积神经网络模型的AUC为0.81±0.06,显著优于阿尔伯塔卒中项目早期CT评分(0.63±0.05)和缺血核心体积(0.64±0.05),外部验证中同样表现更优。

要点

  • 深度学习模型从治疗前DWI提取特征预测大血管闭塞取栓后良好结局。
  • 模型AUC 0.81±0.06,优于ASPECTS和缺血核心体积模型。
  • 外部验证中深度学习模型预测能力仍显著优于标准影像生物标志物。

核心结论

  • 深度学习模型从治疗前神经影像数据中获取的预后信息多于标准影像生物标志物,可能成为有效的预后影像标志物。

研究设计与样本

  • 多中心回顾性研究,纳入2013至2018年接受机械取栓的前循环大血管闭塞患者,推导队列250例,验证队列74例。

主要发现

  • 卷积神经网络模型预测良好临床结局的AUC为0.81±0.06,高于ASPECTS模型的0.63±0.05和缺血核心体积模型的0.64±0.05。
  • 外部验证中卷积神经网络模型的AUC显著优于其他两个模型。

关键数值与推荐

  • 预测目标为90天随访时改良Rankin量表评分0至2分定义为良好临床结局。
  • 卷积神经网络模型AUC为0.81±0.06,ASPECTS模型为0.63±0.05,缺血核心体积模型为0.64±0.05。

临床怎么用

  • 该深度学习模型或可作为辅助工具,从治疗前DWI数据中预测大血管闭塞患者取栓后的临床结局。

局限性

  • 需要前瞻性验证研究确认其临床价值。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

Background and Purpose- For patients with large vessel occlusion, neuroimaging biomarkers that evaluate the changes in brain tissue are important for determining the indications for mechanical thrombectomy. In this study, we applied deep learning to derive imaging features from pretreatment diffusion-weighted image data and evaluated the ability of these features in predicting clinical outcomes for patients with large vessel occlusion. Methods- This multicenter retrospective study included patients with anterior circulation large vessel occlusion treated with mechanical thrombectomy between 2013 and 2018. We designed a 2-output deep learning model based on convolutional neural networks (the convolutional neural network model). This model employed encoder-decoder architecture for the ischemic lesion segmentation, which automatically extracted high-level feature maps in its middle layers, and used its information to predict the clinical outcome. Its performance was internally validated with 5-fold cross-validation, externally validated, and the results compared with those from the standard neuroimaging biomarkers Alberta Stroke Program Early CT Score and ischemic core volume. The prediction target was a good clinical outcome, defined as a modified Rankin Scale score at 90-day follow-up of 0 to 2. Results- The derivation cohort included 250 patients, and the validation cohort included 74 patients. The convolutional neural network model showed the highest area under the receiver operating characteristic curve: 0.81±0.06 compared with 0.63±0.05 and 0.64±0.05 for the Alberta Stroke Program Early CT Score and ischemic core volume models, respectively. In the external validation, the area under the curve for the convolutional neural network model was significantly superior to those for the other 2 models. Conclusions- Compared with the standard neuroimaging biomarkers, our deep learning model derived a greater amount of prognostic information from pretreatment neuroimaging data. Although a confirmatory prospective evaluation is needed, the high-level imaging features derived by deep learning may offer an effective prognostic imaging biomarker.

来源:Stroke,查看原文。版权归原作者所有。

引用

  1. Nishi H, Oishi N, Ishii A, et al. Deep Learning-Derived High-Level Neuroimaging Features Predict Clinical Outcomes for Large Vessel Occlusion. Stroke. 2020. PMID: 32248769. doi:10.1161/STROKEAHA.119.028101

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。