Detection of schizophrenia using hybrid of deep learning and brain effective connectivity image from electroencephalogram signal
Detection of schizophrenia using hybrid of deep learning and brain effective connectivity image from electroencephalogram signal
复制标题
DOI：
10.1016/j.compbiomed.2022.105570
复制
发表时间：
2022-04-30
影响因子：
7.7
通讯作者：
Shalbaf, Ahmad
中科院分区：
文献类型：
--
作者：
Bagherzadeh, Sara;Shahabi, Mohsen Sadat;Shalbaf, Ahmad
通过研究脑电图 (EEG) 信号记录的大脑活动来检测精神分裂症 (SZ) 等精神障碍是神经科学中一个有前途的领域。这项研究提出了一种混合大脑有效连接和深度学习框架，用于多通道脑电图信号的 SZ 检测。首先，基于传递熵 (TE) 方法测量有效连接矩阵，该方法根据每个受试者 19 个 EEG 通道的大脑信息流估计定向因果关系。然后，TE有效连接元素用颜色表示，形成19 x 19的连接图像，同时表示脑电信号的时间和空间信息。创建的图像用于作为迁移学习 (TL) 模型输入到名为 VGG-16、ResNet50V2、InceptionV3、EfficientNetB0 和 DenseNet121 的五个预训练卷积神经网络 (CNN) 模型中。最后，这些配备了长短期记忆 (LSTM) 模型的 TL 模型的深层特征可用于提取最具辨别力的时空特征，用于对 14 名健康对照中的 14 名 SZ 患者进行分类。结果表明，预训练的 CNN-LSTM 模型的混合框架比预训练的 CNN 模型取得了更高的精度。使用 EfficientNetB0-LSTM 模型通过 10 倍交叉验证方法获得了最高的平均准确度和 F1 分数，分别为 99.90% 和 99.93%。因此，来自 EEG 信号的大脑有效连接图像和预训练的 CNN-LSTM 模型的混合框架的卓越性能表明，所提出的方法非常有能力从健康对照中检测出 SZ 患者。
Detection of mental disorders such as schizophrenia (SZ) through investigating brain activities recorded via Electroencephalogram (EEG) signals is a promising field in neuroscience. This study presents a hybrid brain effective connectivity and deep learning framework for SZ detection on multichannel EEG signals. First, the effective connectivity matrix is measured based on the Transfer Entropy (TE) method that estimates directed causalities in terms of brain information flow from 19 EEG channels for each subject. Then, TE effective connectivity elements were represented by colors and formed a 19 x 19 connectivity image which, simultaneously, represents the time and spatial information of EEG signals. Created images are used to be fed into the five pretrained Convolutional Neural Networks (CNN) models named VGG-16, ResNet50V2, InceptionV3, EfficientNetB0, and DenseNet121 as Transfer Learning (TL) models. Finally, deep features from these TL models equipped with the Long Short-Term Memory (LSTM) model for the extraction of most discriminative spatiotemporal features are used to classify 14 SZ patients from 14 healthy controls. Results show that the hybrid framework of pre-trained CNN-LSTM models achieved higher accuracy than pre-trained CNN models. The highest average accuracy and F1-score were achieved using the EfficientNetB0-LSTM model through the 10-fold cross-validation method equal to 99.90% and 99.93%, respectively. Therefore, the superior performance of the hybrid framework of brain effective connectivity images from EEG signals and pre-trained CNN-LSTM models show that the proposed method is highly capable of detecting SZ patients from healthy controls.