Identifying the engagement of a brain network during a targeted tDCS-fMRI experiment using a machine learning approach.
Identifying the engagement of a brain network during a targeted tDCS-fMRI experiment using a machine learning approach.
复制标题
DOI：
10.1371/journal.pcbi.1011012
复制
发表时间：
2023-04
影响因子：
4.3
通讯作者：
中科院分区：
文献类型：
--
作者：
经颅直流电刺激（tDCS）可以无创地调节行为，认知和生理脑功能，这取决于刺激的极性和剂量以及电极的蒙太奇。并发tDCS-fMRI提供了一种新的方式来探索非侵入性脑刺激的参数空间，并通知实验者以及参与者，如果一个目标的大脑区域或空间上分离的大脑区域的网络已从事和调制。我们比较了多电极（ME）与单电极（SE）蒙太奇以及两种活动条件与无刺激（NS）控制条件，以评估大脑网络的参与以及不同电极蒙太奇调节网络活动的能力。多电极导联针对右侧弓状束网络（AFN）的节点区域，阳极电极放置在后上级颞/中颞回（STG/MTG）、缘上回（SMG）、后额下回（IFG）的颅骨位置上，返回阴极电极放置在左侧眶上区域上。相比之下，单电极导联在AFN的结脑区域上仅使用一个阳极电极，但不同参与者的STG/MTG、SMG和后IFG之间的位置不同。全脑rs-fMRI大约每3秒获得一次。在扫描开始后3分钟打开tDCS刺激器。一个4D rs-fMRI数据集转换为动态功能连接（DFC）矩阵使用一组属于AFN以及其他不相关的大脑网络的ROI对。在这项研究中，我们评估了五种算法的性能，从三个条件（ME，SE，NS）的DFC矩阵分为三个不同的类别。使用K近邻（KNN）算法对ME条件进行分类，获得了0.92的最高准确度。换句话说，应用分类算法使我们能够识别AFN的接合，并且ME条件是实现这种接合的最佳蒙太奇。使用模型性能参数确定了对参与者的rs-fMRI数据分类做出主要贡献的前5个ROI对; ROI对主要位于右AFN内。这种使用分类算法方法的概念验证研究可以扩展到在参与者层面创建一个近实时反馈系统，以检测跨越多个脑叶的大脑网络的参与和调制。非侵入性脑刺激可以影响行为，感觉运动技能和认知，当这种功能/活动利用脑刺激靶向的大脑区域时。参数空间（刺激的剂量和持续时间;电极的大小、数量和蒙太奇）以及特定干预的最佳参数选择在许多研究中进行了积极探索。我们的目的是检查是否可以快速确定特定目标脑网络，即弓形束网络（跨越多个脑叶）的参与，以及多电极蒙太奇是否比单电极蒙太奇提供更强的参与。将机器学习技术应用于在同步脑刺激fMRI设置中获得的动态功能图像，使我们能够快速识别目标弓状束网络（AFN）的具体参与。我们的方法应用于AFN应被视为一个典型的例子，跨越多个叶的脑网络的功能活动可以通过靶向节点皮质接入点调制。类似的方法现在可以应用于其他网络。我们的概念验证研究可以扩展到为实验者以及大脑调制研究的参与者创建一个近实时的大脑网络参与反馈系统。
Transcranial direct current stimulation (tDCS) can noninvasively modulate behavior, cognition, and physiologic brain functions depending on polarity and dose of stimulation as well as montage of electrodes. Concurrent tDCS-fMRI presents a novel way to explore the parameter space of non-invasive brain stimulation and to inform the experimenter as well as the participant if a targeted brain region or a network of spatially separate brain regions has been engaged and modulated. We compared a multi-electrode (ME) with a single electrode (SE) montage and both active conditions with a no-stimulation (NS) control condition to assess the engagement of a brain network and the ability of different electrode montages to modulate network activity. The multi-electrode montage targeted nodal regions of the right Arcuate Fasciculus Network (AFN) with anodal electrodes placed over the skull position of the posterior superior temporal/middle temporal gyrus (STG/MTG), supramarginal gyrus (SMG), posterior inferior frontal gyrus (IFG) and a return cathodal electrode over the left supraorbital region. In comparison, the single electrode montage used only one anodal electrode over a nodal brain region of the AFN, but varied the location between STG/MTG, SMG, and posterior IFG for different participants. Whole-brain rs-fMRI was obtained approximately every three seconds. The tDCS-stimulator was turned on at 3 minutes after the scanning started. A 4D rs-fMRI data set was converted to dynamic functional connectivity (DFC) matrices using a set of ROI pairs belonging to the AFN as well as other unrelated brain networks. In this study, we evaluated the performance of five algorithms to classify the DFC matrices from the three conditions (ME, SE, NS) into three different categories. The highest accuracy of 0.92 was obtained for the classification of the ME condition using the K Nearest Neighbor (KNN) algorithm. In other words, applying the classification algorithm allowed us to identify the engagement of the AFN and the ME condition was the best montage to achieve such an engagement. The top 5 ROI pairs that made a major contribution to the classification of participant’s rs-fMRI data were identified using model performance parameters; ROI pairs were mainly located within the right AFN. This proof-of-concept study using a classification algorithm approach can be expanded to create a near real-time feedback system at a participant level to detect the engagement and modulation of a brain network that spans multiple brain lobes. Noninvasive brain-stimulation can affect behavior, sensorimotor skills, and cognition when this function/activity draws on brain regions that are targeted by brain-stimulation. The parameter space (dose and duration of stimulation; size, number, and montage of electrodes) and selection of optimal parameters for a particular intervention are actively explored in numerous research studies. We aimed to examine whether the engagement of a particular targeted brain network, the Arcuate Fasciculus Network (which spans multiple brain lobes), can be determined quickly and whether a multi-electrode montage provides stronger engagement than a single electrode montage. Applying machine learning techniques to dynamic functional images obtained in a simultaneous brain-stimulation-fMRI setting allowed us to quickly identify the specific engagement of the targeted Arcuate Fasciculus Network (AFN). Our approach applied to the AFN should be taken as a prototypical example that functional activity of brain networks spanning across multiple lobes can be modulated by targeting nodal cortical access points. Similar approaches can now be applied to other networks. Our proof-of-concept study can be expanded to create a near real-time feedback system of brain network engagement for the experimenter as well as the participant in a brain-modulation study.
登录
查看更多内容
影响因子：
5.7
作者：
Amadi U;Ilie A;Johansen-Berg H;Stagg CJ
通讯作者：
Stagg CJ
影响因子：
2.9
作者：
Hunter, Michael A.;Coffman, Brian A.;Gasparovic, Charles;Calhoun, Vince D.;Trumbo, Michael C.;Clark, Vincent P.
通讯作者：
Clark, Vincent P.
影响因子：
1.7
作者：
Fregni, F;Boggio, PS;Pascual-Leone, A
通讯作者：
Pascual-Leone, A
影响因子：
4.5
作者：
Dunn, Walter;Rassovsky, Yuri;Green, Michael F.
通讯作者：
Green, Michael F.
影响因子：
3.7
作者：
Allen, Elena A.;Damaraju, Eswar;Calhoun, Vince D.
通讯作者：
Calhoun, Vince D.