时间卷积神经网络与图卷积网络用于MEG数据中的癫痫棘波检测
Time CNN and Graph Convolution Network for Epileptic Spike Detection in MEG Data
AI总结:
针对MEG棘波检测,提出Time CNN与GCN结合的方法,利用传感器空间关系,参数少,在平衡和不平衡数据集上分别取得76.7%和25.5%的F1分数,优于现有方法。
摘要:
脑磁图(MEG)记录中,癫痫患者的信号表现出棘波,这是该病理的典型生物标志物。检测这些棘波能够准确定位触发癫痫发作的脑区。棘波检测通常由人工完成。然而,由于MEG数据的复杂性,这是一项繁重且容易出错的任务。为解决这一问题,我们提出了一种一维时间卷积神经网络(Time CNN)与图卷积网络(GCN)相结合的方法,用于将MEG记录的短时间帧分类为包含棘波或不包含棘波。与其他近期方法相比,我们的模型需要训练的参数更少,并且我们提出使用GCN来考虑MEG传感器的空间关系。我们的模型产生了临床相关的结果,并超越了基于深度学习的最新方法,在平衡数据集上达到了76.7%的分类f1分数,在现实的高度不平衡数据集上,针对棘波类别达到了25.5%的f1分数。
英文摘要:
Magnetoencephalography (MEG) recordings of patients with epilepsy exhibit spikes, a typical biomarker of the pathology. Detecting those spikes allows accurate localization of brain regions triggering seizures. Spike detection is often performed manually. However, it is a burdensome and error prone task due to the complexity of MEG data. To address this problem, we propose a 1D temporal convolutional neural network (Time CNN) coupled with a graph convolutional network (GCN) to classify short time frames of MEG recording as containing a spike or not. Compared to other recent approaches, our models have fewer parameters to train and we propose to use a GCN to account for MEG sensors spatial relationships. Our models produce clinically relevant results and outperform deep learning-based state-of-the-art methods reaching a classification f1-score of 76.7% on a balanced dataset and of 25.5% on a realistic, highly imbalanced dataset, for the spike class.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。