School of Mechanical Engineering, Pusan National University, 2 Busandaehak-ro, Geumjeong-gu, Busan 46241, Korea.
Department of Rehabilitation Medicine, Pusan National University School of Medicine and Biomedical Research Institute, Pusan National University Hospital, Busan 46241, Korea.
Curr Alzheimer Res. 2020;17(13):1145-1160. doi: 10.2174/1567205018666210212154941.
Early diagnosis of Alzheimer's disease (AD) is essential in preventing its progression to dementia. Mild cognitive impairment (MCI) can be indicative of early-stage AD. In this study, we propose a channel-wise feature extraction method of functional near-infrared spectroscopy (fNIRS) data to diagnose MCI when performing cognitive tasks, including two-back, Stroop, and semantic verbal fluency tasks (SVFT).
A new channel-wise feature extraction method is proposed as follows: A region-of-interest (ROI) channel is defined as such channel having a statistical difference (p < 0.05) in t-values between two groups. For each ROI channel, features (the mean, slope, skewness, kurtosis, and peak value of oxy- and deoxy-hemoglobin) are extracted. The extracted features for the two classes (MCI, HC) are classified using the linear discriminant analysis (LDA) and support vector machine (SVM). Finally, the classifiers are validated using the area under curve (AUC) of the receiver operating characteristics. Furthermore, the suggested feature extraction method is compared with the conventional approach. Fifteen MCI patients and fifteen healthy controls (HCs) participated in the study.
In the two-back and Stroop tasks, HCs showed activation in the ventrolateral prefrontal cortex (VLPFC). However, in the case of MCI, the VLPFC was not activated. Instead, Ch. 30 was activated. In the SVFT task, the PFC was activated in both groups, but the t-values of HCs were higher than those of MCI. For the SVFT, the classification accuracies using the proposed feature extraction method were 80.77% (LDA) and 83.33% (SVM), showing the highest among the three tasks; for the Stroop task, 79.49% (LDA) and 73.08% (SVM); and for the two-back task, 73.08% (LDA) and 69.23% (SVM).
The cognitive disparities between the MCI and HC groups were detected in the ventrolateral prefrontal cortex using fNIRS. The proposed feature extraction method has shown an improvement in the classification accuracies, see Subsection 3.3. Most of all, the suggested method contains a groupdistinction information per cognitive task. The obtained results successfully discriminated MCI patients from HCs, which reflects that the proposed method is an efficient tool to extract features in fNIRS signals.
早期诊断阿尔茨海默病（AD）对于预防其发展为痴呆至关重要。轻度认知障碍（MCI）可能是早期 AD 的表现。在这项研究中，我们提出了一种功能性近红外光谱（fNIRS）数据的通道特征提取方法，用于在执行认知任务（包括双任务、Stroop 任务和语义流畅性任务（SVFT））时诊断 MCI。
提出了一种新的通道特征提取方法：定义感兴趣区域（ROI）通道为两组间 t 值有统计学差异（p<0.05）的通道。对于每个 ROI 通道，提取特征（氧合和脱氧血红蛋白的均值、斜率、偏度、峰度和峰值）。使用线性判别分析（LDA）和支持向量机（SVM）对两类（MCI、HC）的提取特征进行分类。最后，使用接收者操作特征曲线（ROC）的 AUC 验证分类器。此外，还比较了所提出的特征提取方法与传统方法。15 名 MCI 患者和 15 名健康对照组（HCs）参加了这项研究。
在双任务和 Stroop 任务中，HCs 在腹外侧前额叶皮层（VLPFC）表现出激活。然而，在 MCI 病例中，VLPFC 未被激活，而 Ch.30 被激活。在 SVFT 任务中，两组均激活了 PFC，但 HCs 的 t 值高于 MCI。对于 SVFT，使用所提出的特征提取方法的分类准确率分别为 80.77%（LDA）和 83.33%（SVM），在三个任务中最高；对于 Stroop 任务，分别为 79.49%（LDA）和 73.08%（SVM）；对于双任务，分别为 73.08%（LDA）和 69.23%（SVM）。
使用 fNIRS 在腹外侧前额叶皮层检测到 MCI 和 HCs 组之间的认知差异。所提出的特征提取方法在分类准确率方面有所提高，见第 3.3 节。最重要的是，所提出的方法包含每个认知任务的组区分信息。所得结果成功地区分了 MCI 患者和 HCs，这反映了所提出的方法是提取 fNIRS 信号特征的有效工具。
