Accelerating Prediction of Malignant Cerebral Edema After Ischemic Stroke with Automated Image Analysis and Explainable Neural Networks.
Accelerating Prediction of Malignant Cerebral Edema After Ischemic Stroke with Automated Image Analysis and Explainable Neural Networks.
复制标题
DOI：
10.1007/s12028-021-01325-x
复制
发表时间：
2022-04
影响因子：
3.5
通讯作者：
Dhar R
中科院分区：
文献类型：
--
作者：
Foroushani HM;Hamzehloo A;Kumar A;Chen Y;Heitsch L;Slowik A;Strbian D;Lee JM;Marcus DS;Dhar R
恶性脑水肿是中风的一种毁灭性并发症，如果在脑疝形成前不进行半颅骨切除术，会导致病情恶化和死亡。目前用于预测这种相对罕见的并发症的方法通常需要先进的成像，并且仍然受到次优性能的影响。我们进行了一项初步研究，以评估神经网络结合从常规CT成像中提取的数据是否可以增强对大型多样化卒中队列中水肿的预测。一项国际卒中队列研究的参与者中，自动成像管道回顾性提取了基线和24小时CT的体积数据，包括CSF体积和半球CSF体积比。使用一系列临床和成像数据训练完全连接和长短期记忆（LSTM）神经网络，以预测那些需要半颅骨切除术或死于中线移位的患者。这些模型的性能进行了测试，在与回归模型和水肿评分比较，使用交叉验证，以构建精度召回曲线。598例患者中有20例发生恶性水肿（12例需要手术，8例死亡）。回归模型提供了95%的召回率，但只有32%的精确度（精确-召回曲线下面积[AUPRC] 0.74），与水肿评分（精确度28%，AUPRC 0.66）相似。完全连接的网络并没有表现得更好（精确度33%，AUPRC 0.71），但LSTM模型在整个队列和NIHSS ≥ 8的亚组中提供了100%的召回率和87%的精确度（AUPRC为0.97）（p = 0.0001 vs.回归和完全连接模型）。提供最具预测重要性的特征是24小时测量的半球CSF比率和NIHSS评分。LSTM神经网络结合了从常规CT中提取的体积数据，在卒中后24小时内识别了所有恶性脑水肿病例，假阳性率明显低于完全连接的神经网络、回归模型和经验证的水肿评分。这项初步工作需要前瞻性验证，但提供了一个原则证明，即深度学习框架可以帮助在恶化之前选择手术患者。
Malignant cerebral edema is a devastating complication of stroke, resulting in deterioration and death if hemicraniectomy is not performed prior to herniation. Current approaches for predicting this relatively rare complication often require advanced imaging and still suffer from suboptimal performance. We performed a pilot study to evaluate whether neural networks incorporating data extracted from routine CT imaging could enhance prediction of edema in a large diverse stroke cohort. An automated imaging pipeline retrospectively extracted volumetric data, including CSF volumes and hemispheric CSF volume ratio, from baseline and 24-hour CTs performed in participants of an international stroke cohort study. Fully connected and long short-term memory (LSTM) neural networks were trained using serial clinical and imaging data to predict those who would require hemicraniectomy or die with midline shift. The performance of these models were tested, in comparison with regression models and the EDEMA score, using cross-validation to construct precision-recall curves. Twenty of 598 patients developed malignant edema (12 required surgery, 8 died). The regression model provided 95% recall but only 32% precision (area under precision-recall curve [AUPRC] 0.74), similar to the EDEMA score (precision 28%, AUPRC 0.66). The fully connected network did not perform better (precision 33%, AUPRC 0.71) but the LSTM model provided 100% recall, 87% precision (AUPRC of 0.97) in the overall cohort and the subgroup with NIHSS ≥ 8 (p=0.0001 vs. regression and fully connected models). Features providing the most predictive importance were the hemispheric CSF ratio and NIHSS score measured at 24-hours. A LSTM neural network incorporating volumetric data extracted from routine CTs identified all cases of malignant cerebral edema by 24-hours after stroke, with significantly fewer false positives than a fully connected neural network, regression model and the validated EDEMA score. This preliminary work requires prospective validation but provides proof-of-principle that a deep learning framework could assist in selecting patients for surgery, prior to deterioration.
登录
查看更多内容
影响因子：
8.3
作者：
Ong CJ;Gluckstein J;Laurido-Soto O;Yan Y;Dhar R;Lee JM
通讯作者：
Lee JM
影响因子：
28.1
作者：
Lundberg, Scott M.;Nair, Bala;Lee, Su-In
通讯作者：
Lee, Su-In
影响因子：
8.3
作者：
Broocks, Gabriel;Kemmling, Andre;Hanning, Uta
通讯作者：
Hanning, Uta
影响因子：
8.3
作者：
Kauw, Frans;Bennink, Edwin;van der Graaf, Y.
通讯作者：
van der Graaf, Y.
影响因子：
2.9
作者：
MacCallum, Caroline;Churilov, Leonid;Yan, Bernard
通讯作者：
Yan, Bernard