Department of Mechatronics, Faculty of Engineering, Bulent Ecevit University, Zonguldak, Turkey.
Department of Software Engineering, Faculty of Engineering and Natural Sciences, Uskudar University, Istanbul, Turkey.
Clin EEG Neurosci. 2021 Jan;52(1):38-51. doi: 10.1177/1550059420916634. Epub 2020 Jun 3.
The human brain is characterized by complex structural, functional connections that integrate unique cognitive characteristics. There is a fundamental hurdle for the evaluation of both structural and functional connections of the brain and the effects in the diagnosis and treatment of neurodegenerative diseases. Currently, there is no clinically specific diagnostic biomarker capable of confirming the diagnosis of major depressive disorder (MDD). Therefore, exploring translational biomarkers of mood disorders based on deep learning (DL) has valuable potential with its recently underlined promising outcomes. In this article, an electroencephalography (EEG)-based diagnosis model for MDD is built through advanced computational neuroscience methodology coupled with a deep convolutional neural network (CNN) approach. EEG recordings are analyzed by modeling 3 different deep CNN structure, namely, ResNet-50, MobileNet, Inception-v3, in order to dichotomize MDD patients and healthy controls. EEG data are collected for 4 main frequency bands (Δ, θ, α, and β, accompanying spatial resolution with location information by collecting data from 19 electrodes. Following the pre-processing step, different DL architectures were employed to underline discrimination performance by comparing classification accuracies. The classification performance of models based on location data, MobileNet architecture generated 89.33% and 92.66% classification accuracy. As to the frequency bands, delta frequency band outperformed compared to other bands with 90.22% predictive accuracy and area under curve (AUC) value of 0.9 for ResNet-50 architecture. The main contribution of the study is the delineation of distinctive spatial and temporal features using various DL architectures to dichotomize 46 MDD subjects from 46 healthy subjects. Exploring translational biomarkers of mood disorders based on DL perspective is the main focus of this study and, though it is challenging, with its promising potential to improve our understanding of the psychiatric disorders, computational methods are highly worthy for the diagnosis process and valuable in terms of both speed and accuracy compared with classical approaches.
人类大脑的结构和功能连接复杂，具有独特的认知特征。评估大脑的结构和功能连接以及这些连接在神经退行性疾病诊断和治疗中的作用存在根本障碍。目前，没有一种临床特异性的诊断生物标志物能够确认重度抑郁症（MDD）的诊断。因此，基于深度学习（DL）探索情绪障碍的转化生物标志物具有很大的潜力，其最近强调的结果很有希望。在本文中，通过先进的计算神经科学方法与深度卷积神经网络（CNN）方法相结合，构建了基于脑电图（EEG）的 MDD 诊断模型。通过对 3 种不同的深度 CNN 结构（ResNet-50、MobileNet、Inception-v3）进行建模，分析 EEG 记录，以便将 MDD 患者和健康对照者进行分类。收集 EEG 数据用于 4 个主要频段（Δ、θ、α 和 β），并通过从 19 个电极收集数据提供位置信息的空间分辨率。在预处理步骤之后，使用不同的 DL 架构通过比较分类准确率来强调区分性能。基于位置数据的模型的分类性能，MobileNet 架构产生了 89.33%和 92.66%的分类准确率。对于频带，与其他频带相比，Delta 频带的预测准确率为 90.22%，ResNet-50 架构的 AUC 值为 0.9。该研究的主要贡献是使用各种 DL 架构描绘出独特的时空特征，将 46 名 MDD 患者与 46 名健康受试者区分开来。基于 DL 视角探索情绪障碍的转化生物标志物是本研究的主要重点，尽管具有挑战性，但具有改善我们对精神障碍理解的巨大潜力，与经典方法相比，计算方法在速度和准确性方面都非常适合诊断过程，具有很高的价值。
