IEEE Trans Neural Syst Rehabil Eng. 2023;31:2933-2943. doi: 10.1109/TNSRE.2023.3250958. Epub 2023 Jul 13.
Consciousness detection is important in diagnosis and treatment of disorders of consciousness (DOC). Recent studies have demonstrated that electroencephalography (EEG) signals contain effective information for consciousness state evaluation. We propose two novel EEG measures: the spatiotemporal correntropy and the neuromodulation intensity, to reflect the temporal-spatial complexity in brain signals for consciousness detection. Then, we build a pool of EEG measures with different spectral, complexity and connectivity features, and propose Consformer, a transformer network to learn an adaptive optimization of features for different subjects with the attention mechanism. Experiments are carried out using a large dataset of 280 resting-state EEG recordings of DOC patients. Consformer discriminates minimally conscious state (MCS) from vegetative state (VS) with an accuracy of 85.73% and an F1-score of 86.95%, which achieves the state-of-the-art performance.
意识检测在意识障碍（DOC）的诊断和治疗中很重要。最近的研究表明，脑电图（EEG）信号包含用于意识状态评估的有效信息。我们提出了两种新的 EEG 测量方法：时空相关熵和神经调制强度，以反映脑信号中的时-空复杂性，用于意识检测。然后，我们构建了一个具有不同频谱、复杂性和连通性特征的 EEG 测量池，并提出了 Consformer，一种使用注意力机制为不同个体学习自适应优化特征的 Transformer 网络。实验使用了一个包含 280 名 DOC 患者静息态 EEG 记录的大型数据集进行。Consformer 将最小意识状态（MCS）与植物状态（VS）区分开来，准确率为 85.73%，F1 得分为 86.95%，达到了最新水平。
