美国 NIRx 近红外脑功能成像系统 NIRScout

摘要 · 中文整理：本研究旨在利用功能近红外光谱（fNIRS）探究交互式与被动任务中大脑皮层血流动力学响应的性别差异。97名健康成年人（63名女性、34名男性）参与研究。受试者完成两项任务：交互式运动游戏与被动动作，并在五个皮层区域测量激活。氧合血红蛋白ΔHbO血流动力学响应幅值存在统计学显著差异，尤其在顶叶皮层，男性激活水平更高；差异在顶叶、前额叶、左半球与视觉皮层均保持显著。差异在被动任务中更为明显，可能提示男女采用不同的加工策略。尽管最大反应延迟时间tmax无显著组间差异，但男性在视觉皮层倾向于更长的时间。此外，男性中ΔHbO与tmax呈中等正相关，尤其在前额叶皮层。这些结果强调了在神经影像研究中考虑生物性别的重要性，并为后续分析指明了方向。

原文摘要：The present study aimed to investigate sex differences in the hemodynamic response of the cerebral cortex during interactive and passive tasks using functional near-infrared spectroscopy fNIRS. Ninety-seven healthy adults (63 women, 34 men) participated in the study. Participants performed two tasks: an interactive motor game and a passive hand movement, and activation was measured in five cortical regions. Statistically significant differences in the amplitude of the hemodynamic response of oxygenated haemoglobin ΔHbO levels were observed, particularly in the parietal cortex, where men showed higher activation levels. The differences remained significant in the parietal, prefrontal, left hemisphere, and visual cortex. The differences were more pronounced in the passive task, which may indicate different processing strategies in women and men. Although no significant group differences were found in the latency time of maximum reaction tmax, men tended to have longer times in the visual cortex. Additionally, a moderate positive correlation between ΔHbO and tmax was observed among men, particularly in the prefrontal cortex. These results highlight the importance of considering biological sex in neuroimaging studies and suggest directions for further analysis.

关键词：功能近红外光谱fNIRS、性别差异、Nefroball、交互式与被动任务

研究目标：探究在交互式（足部压力驱动游戏）与被动（节律性挤压但不影响游戏）任务中，男性与女性大脑皮层血流动力学响应（ΔHbO幅值与达峰延迟）是否存在差异，以及差异的区域与任务依赖性。

主要结论：男性在多个皮层区域尤其是顶叶皮层的ΔHbO显著高于女性，差异在被动任务中更为明显；达峰时间总体无显著差异，但男性前额叶ΔHbO与t_max呈中等正相关。结果提示性别应作为fNIRS研究中的生物学变量加以考虑，未来应扩展至双侧半球测量并采用更均衡的样本。

创新点：首次将Nefroball足部压力交互游戏系统与NIRScout fNIRS结合，在较大样本（97人）中系统比较交互式与被动任务下皮层血流动力学响应的性别差异，并同时分析幅值与时间（达峰延迟）两类指标。

后续建议：扩展光极布置至双侧半球以评估半球间差异；采用性别均衡的样本并进行功效分析；纳入性激素水平与月经周期等生理变量；结合EEG等多模态手段提升时间分辨率；考察不同年龄段以分离发育因素的影响

APA 引文：Jezierska, K., Turoń-Skrzypińska, A., Rotter, I., Syroka, A., & Rył, A. (2025). Sex differences in cortical hemodynamic responses during interactive and passive tasks: An fNIRS study using the Nefroball system. Sensors, 25(18), 5897. https://doi.org/10.3390/s25185897

仪器引用：An fNIRS system (NIRScout, NIRx Medical Technologies LLC, Glen Head, NY, USA) ... 16 near-infrared light emitters and 16 detectors

摘要 · 中文整理：本研究探索将功能近红外光谱（fNIRS）信号与现代机器学习技术结合、对特定解剖动作进行分类的潜力，以增加基于 fNIRS 的脑机接口（BCI）应用可用的控制命令数量。研究聚焦于新颖的单指敲击任务，这是 fNIRS 与 fMRI 研究中的经典任务，但以往仅限于左右手或少数手指。24 名右利手被试完成了单指敲击任务，数据由按国际 10-10 系统放置于运动皮层的十六个光源与探测器采集。以事件平均的氧合血红蛋白变化与脱氧血红蛋白变化作为特征，在具有挑战性的多类分类场景中评估多种机器学习模型的表现，方法包括线性判别分析、二次判别分析、多项逻辑回归、极端梯度提升与随机森林。研究提出了一种新的深度学习模型 Hemo-Net，由多路带不同滤波器的并行卷积层构成以提取特征。本文旨在探索 fNIRS 结合机器学习与深度学习方法在多类分类任务中的有效性。随机森林、极端梯度提升与 Hemo-Net 等复杂模型的测试集准确率相对高于线性判别分析、多项逻辑回归与二次判别分析。Hemo-Net 表现最佳，取得 76% 的最高测试集准确率；不过本研究的目标并非提升模型准确率本身，而是探究 fNIRS 是否具备可供现代机器学习与深度学习方法用于多类分类的神经特征，从而支撑脑机接口等应用。像单指运动这样的精细解剖动作用 fNIRS 数据做多类分类是困难的：多项逻辑回归与线性判别分析等传统模型的表现劣于随机森林与极端梯度提升等集成方法，而基于深度学习的 Hemo-Net 优于本研究评估的所有方法，展示了基于 fNIRS 的脑机接口应用的良好前景。

原文摘要：In this study, we explore the potential of using functional near-infrared spectroscopy (fNIRS) signals in conjunction with modern machine-learning techniques to classify specific anatomical movements to increase the number of control commands for a possible fNIRS-based brain-computer interface (BCI) applications. The study focuses on novel individual finger-tapping, a well-known task in fNIRS and fMRI studies, but limited to left/right or few fingers. Twenty-four right-handed participants performed the individual finger-tapping task. Data were recorded by using sixteen sources and detectors placed over the motor cortex according to the 10-10 international system. The event's average oxygenated Δ HbO and deoxygenated Δ HbR hemoglobin data were utilized as features to assess the performance of diverse machine learning (ML) models in a challenging multi-class classification setting. These methods include LDA, QDA, MNLR, XGBoost, and RF. A new DL-based model named "Hemo-Net" has been proposed which consists of multiple parallel convolution layers with different filters to extract the features. This paper aims to explore the efficacy of using fNRIS along with ML/DL methods in a multi-class classification task. Complex models like RF, XGBoost, and Hemo-Net produce relatively higher test set accuracy when compared to LDA, MNLR, and QDA. Hemo-Net has depicted a superior performance achieving the highest test set accuracy of 76%, however, in this work, we do not aim at improving the accuracies of models rather we are interested in exploring if fNIRS has the neural signatures to help modern ML/DL methods in multi-class classification which can lead to applications like brain-computer interfaces. Multi-class classification of fine anatomical movements, such as individual finger movements, is difficult to classify with fNIRS data. Traditional ML models like MNLR and LDA show inferior performance compared to the ensemble-based methods of RF and XGBoost. DL-based method Hemo-Net outperforms all methods evaluated in this study and demonstrates a promising future for fNIRS-based BCI applications.

关键词：功能近红外光谱（fNIRS）、深度学习、单指运动、分类、脑机接口（BCI）

研究目标：探索fNIRS信号是否包含足以区分右手五根手指单指敲击的神经特征，并评估传统机器学习与深度学习方法在此多分类任务上的可行性，以扩展fNIRS脑机接口的控制命令数量。

主要结论：fNIRS信号可用于精细解剖运动的多分类；RF、XGBoost等集成方法优于LDA、MNLR等传统模型，所提出的深度学习模型Hemo-Net取得最高76%的测试集准确率，展现了fNIRS脑机接口的潜力，但仍需更大数据集、更优模型与更低计算需求。

创新点：首次将fNIRS用于五指单指敲击的多分类任务；提出基于并行多尺度卷积（inception块）的Hemo-Net深度学习模型；系统比较了经典机器学习、集成学习与多种深度学习模型在同一fNIRS数据集上的表现。

后续建议：扩大样本量并结合迁移学习初始化模型权重以缓解过拟合；直接基于原始时间序列而非事件平均值建模以保留时间依赖结构并支持实时应用；利用GAN或VAE等生成模型进行数据增强；采用EEG-fNIRS混合模态提升时间分辨率与分类性能；引入短距离通道回归以去除表层生理干扰

APA 引文：Khan, H., Khadka, R., Sultan, M. S., Yazidi, A., Ombao, H., & Mirtaheri, P. (2024). Unleashing the potential of fNIRS with machine learning: classification of fine anatomical movements to empower future brain-computer interface. Frontiers in Human Neuroscience, 18, 1354143. https://doi.org/10.3389/fnhum.2024.1354143

仪器引用：A continuous-wave (λ1 = 760 nm, λ2 = 850 nm) optical tomography machine NIRScout (NIRx Medizintechnik GmbH, Germany) was used to acquire brain data with a sampling rate of 3.9063 Hz