Deep learning of early brain imaging to predict post-arrest electroencephalography,Resuscitation

当前位置： X-MOL 学术 › Resuscitation › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Deep learning of early brain imaging to predict post-arrest electroencephalography
Resuscitation ( IF 6.5 ) Pub Date : 2022-01-15 , DOI: 10.1016/j.resuscitation.2022.01.004
Jonathan Elmer ₁ , Chang Liu ₂ , Matthew Pease ₃ , Dooman Arefan ₄ , Patrick J Coppler ₅ , Katharyn L Flickinger ₅ , Joseph M Mettenburg ₄ , Maria E Baldwin ₆ , Niravkumar Barot ₇ , Shandong Wu ₈

Affiliation

Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA; Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA; Neurology Division, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA.
Department of Bioengineering, Swanson School of Engineering, University of Pittsburgh, Pittsburgh, PA, USA.
Department of Neurosurgery, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA.
Department of Radiology, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA.
Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA.
Department of Neurology, Pittsburgh VA Medical Center, Pittsburgh, PA, USA.
Neurology Division, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA.
Department of Bioengineering, Swanson School of Engineering, University of Pittsburgh, Pittsburgh, PA, USA; Department of Radiology, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA; Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA, USA; Intelligent Systems Program, University of Pittsburgh, Pittsburgh, PA, USA.

Introduction

Guidelines recommend use of computerized tomography (CT) and electroencephalography (EEG) in post-arrest prognostication. Strong associations between CT and EEG might obviate the need to acquire both modalities. We quantified these associations via deep learning.

Methods

We performed a single-center, retrospective study including comatose patients hospitalized after cardiac arrest. We extracted brain CT DICOMs, resized and registered each to a standard anatomical atlas, performed skull stripping and windowed images to optimize contrast of the gray-white junction. We classified initial EEG as generalized suppression, other highly pathological findings or benign activity. We extracted clinical information available on presentation from our prospective registry. We trained three machine learning (ML) models to predict EEG from clinical covariates. We used three state-of-the-art approaches to build multi-headed deep learning models using similar model architectures. Finally, we combined the best performing clinical and imaging models. We evaluated discrimination in test sets.

Results

We included 500 patients, of whom 218 (44%) had benign EEG findings, 135 (27%) showed generalized suppression and 147 (29%) had other highly pathological findings that were most commonly (93%) burst suppression with identical bursts. Clinical ML models had moderate discrimination (test set AUCs 0.73–0.80). Image-based deep learning performed worse (test set AUCs 0.51–0.69), particularly discriminating benign from highly pathological findings. Adding image-based deep learning to clinical models improved prediction of generalized suppression due to accurate detection of severe cerebral edema.

Discussion

CT and EEG provide complementary information about post-arrest brain injury. Our results do not support selective acquisition of only one of these modalities, except in the most severely injured patients.

中文翻译：

早期脑成像的深度学习预测逮捕后脑电图

介绍

指南建议在逮捕后预后中使用计算机断层扫描 (CT) 和脑电图 (EEG)。CT 和脑电图之间的强关联可能会避免获得这两种模式的需要。我们通过深度学习量化了这些关联。

方法

我们进行了一项单中心回顾性研究，包括心脏骤停后住院的昏迷患者。我们提取了脑部 CT DICOM，将每个 DICOM 调整大小并注册到标准解剖图集，执行颅骨剥离和窗口化图像以优化灰白色交界处的对比度。我们将初始脑电图分类为广泛性抑制、其他高度病理性发现或良性活动。我们从我们的前瞻性登记处提取了展示时可用的临床信息。我们训练了三个机器学习 (ML) 模型来预测临床协变量的脑电图。我们使用三种最先进的方法使用相似的模型架构构建多头深度学习模型。最后，我们结合了表现最好的临床和影像学模型。我们评估了测试集中的歧视。

结果

我们纳入了 500 名患者，其中 218 名 (44%) 有良性脑电图表现，135 名 (27%) 表现出广泛抑制，147 名 (29%) 有其他高度病理性表现，最常见的 (93%) 爆发抑制和相同的爆发。临床 ML 模型具有适度的歧视（测试集 AUCs 0.73–0.80）。基于图像的深度学习表现更差（测试集 AUCs 0.51–0.69），尤其是区分良性和高度病理性发现。由于对严重脑水肿的准确检测，将基于图像的深度学习添加到临床模型中改善了对广泛抑制的预测。