Language is processed in widely distributed neural networks including the frontal operculum (Broca’s region) in the dominant hemisphere and its right hemispheric homolog, as well as parietotemporal areas of the left hemisphere (Pulvermüller, 2002; Pulvermüller et al., 2009; Giraud and Poeppel, 2012; Poeppel et al., 2012). Measuring the information flow between those core regions is important for understanding the function of the language network (Singer, 1999; Varela et al., 2001; Buzsaki, 2004). Information flow across nodes of a network can be studied by recording synchronizations of spontaneous cortical oscillations. For instance, a study (Giraud et al., 2007) tried to link auditory structural characteristics of speech and spontaneous brain oscillations within networks important for speech perception and production. Others have examined transient event-related phase synchronizations between two brain areas (Lachaux et al., 1999; Pulvermüller, 2002) or the phase resetting of a cortical oscillation by a perceptual stimulus (Friston et al., 1997; Rizzuto and Kahana, 2001). However, sensory stimuli or cognitive task manipulations can affect in parallel several cortical areas. On the other hand, controlled perturbations applied directly to well-defined brain regions offer a superior strategy to gain insights into the casual interactions between nodes of a given large-scale brain network. Here we applied this strategy to gain insights into the dynamics across the language network.

We applied single pulses of brain magnetic resonance imaging (MRI)-guided (neuronavigated) transcranial magnetic stimulation (TMS) to the pars opercularis of the left frontal operculum and recorded TMS-evoked cortical responses with electroencephalography (EEG) to gain insights into the connectivity dynamics across interhemispheric and intrahemispheric connections of the language network. The use of neuronavigated TMS is important to ensure precise targeting of a given brain region (Gugino et al., 2001; Bashir et al., 2011). We examined the modulation of TMS-evoked cortical responses induced by continuous theta-burst stimulation (cTBS), a noninvasive stimulation protocol that has been shown not only to decrease the excitability of the targeted area (Huang et al., 2005) but also to modulate brain oscillations and synchronizations (Vernet et al., 2013). CTBS can provide longer-lasting modulatory effects with shorter stimulation time than traditional repetitive TMS, which can have important clinical implications.

We hypothesized that such an approach, using task-free and externally triggered oscillations, would provide more direct physiological evidence for connectivity mechanisms. Furthermore, synchronization and desynchronization of these task-free oscillations in response to the plasticity-inducing cTBS protocol could provide information relevant to a future noninvasive intervention for the rehabilitation of patients with aphasia (Miniussi and Thut, 2009). Specifically, we hypothesized that cTBS to the left pars opercularis would change interhemispheric synchronization of TMS-evoked potential (TEP) between the left and the right pars opercularis and intrahemispheric interactions between the left pars opercularis and the left supramarginal and left superior temporal areas.

Figure 2 summarizes the significant results of modulation of TEP synchronization induced by cTBS of the left pars opercularis. Please note that no other significant modulations of TEP synchronization across the studied ROIs were found. By EEG frequency bands, the significant findings were as follows:

cTBS to the left pars opercularis induced significant changes in phase synchronization of TEPs evoked from the left pars opercularis. Specifically, we found: (1) a significant increase in the gamma frequency between the left and right pars opercularis at an early (250–350 ms) time window and a similar increase between the left pars opercularis and the left posterior language areas at a later time period (600–700 ms); and (2) a significant increase in the theta and delta bands between the left pars opercularis and the posterior language areas. These results provide novel insights into the interhemispheric and intrahemispheric dynamics of the language network in healthy young individuals.

cTBS is a TMS protocol that has been primarily used to induce a decrease of excitability in the stimulated area. Indeed, it has been shown that cTBS applied over M1 can induce depression of the MEPs subsequently evoked by single-pulse TMS (Huang et al., 2005). However, recent studies using TMS coupled with EEG, magnetoencephalography (MEG) and/or magnetic resonance spectroscopy have revealed that cTBS also has an impact on local and remote oscillatory systems, on synchronization, and on inhibitory γ-aminobutyric acid (GABA) concentration level (Allen et al., 2014; Du et al., 2018).

Here, we found that cTBS over the left pars opercularis induced an increase of synchronization in the gamma band in early TEPs (250 to 350 ms time window) and in late TEPs (600–700 ms). GABAergic interneurons are known to be the source of the generation of gamma oscillation (Wang and Buzsáki, 1996). Our finding of increased gamma-band synchronization after cTBS might be caused by increased activity of local inhibitory interneurons subtending the inhibitory interaction between the left and right pars opercularis region. Studies using spinal epidural recordings have shown that cTBS applied over M1 suppresses the earliest I1-wave (Di Lazzaro et al., 2005), which is primarily derived from GABA-related interneuronal circuits within the human motor cortex (Ziemann et al., 1998). Thus, cTBS might have decreased cortical excitability in the left pars opercularis and increased inhibition, which led to a change in TMS-evoked EEG gamma synchronization. Alternatively, the increase of gamma coherence might be related to the gamma frequency (50 Hz) embedded in the cTBS pattern.

Interesting deficits of gamma oscillations have been reported in patients with schizophrenia. Ferrarelli et al. (2008) showed that gamma activity evoked by single-pulse TMS applied over the dorsolateral prefrontal cortex was significantly decreased within the first 100 ms after TMS in schizophrenic patients compared to healthy controls. In such patients, spontaneous gamma activity did not show any differences between patients and healthy controls, emphasizing the utility of TMS and specifically the use of TMS–EEG to reveal physiological abnormalities.

Interhemispheric interactions between the left and right pars opercularis regions have been studied as a way to promote language function recovery following stroke. Some have argued that a stroke can impair the normal interhemispheric inhibition balance between the lesioned area and its homolog in the intact hemisphere. If so, decreasing the excitability of the latter area, for example, with noninvasive brain stimulation, might decrease the excessive inhibition it exerts on the former area and thus promote recovery. Consistent with such notions, Naeser et al. (2005) observed significant and persistent improvement in picture-naming abilities in patients with nonfluent aphasia after low frequency rTMS targeting the right frontal operculum. In healthy individuals, similar effects of rTMS on interhemispheric inhibitory interactions between homolog areas of the language network have been shown in studies using positron emission tomography (Thiel et al., 2006), functional MRI (Andoh and Paus, 2011), and behavioral responses (Cappelletti et al., 2008). In the present study, we show for the first time that such interhemispheric interactions might be subtended by synchronization in the gamma band, and that appears possible to modulate it by noninvasive stimulation of the left pars opercularis.

Beyond interhemispheric interactions, our results confirm the relevance of interregional gamma band synchronization within brain networks previously shown in cognition and perception (Sarnthein et al., 1998; Rose and Büchel, 2005; Buschman and Miller, 2007) and language learning (de Diego-Balaguer et al., 2011). For instance, Miltner et al. (1999) showed that intrahemispheric coherence in the gamma band increased during the formation of percepts and memory, linguistic processing, and other behavioral and perceptual functions. Another study showed a greater functional connectivity between the frontal and parietal cortices within the gamma band during successful recollection, as opposed to merely experiencing a feeling of familiarity (Burgess and Ali, 2002). In the language network, an MEG study by Duesburg et al. (2012) reported that a covert verb generation task increased gamma band synchronization among regions activated during the task, in particular, the inferior frontal gyrus and the medial frontal gyrus. A similar result of gamma band phase locking was observed during a silent reading task (Hirata et al., 2010). Our results provide further support for the relevance of phase coherence among gamma rhythms within the language network.

It is also worth noting that local cell assemblies in the cortex are thought to form functional units through synchronous activation in the gamma range (Engel and Singer, 2001; Bastiaansen and Hagoort, 2013). Oscillations may function as nested sets, where lower-frequency activity binds higher-frequency activity (Lisman and Buzsáki, 2008). Theta bursts occur during the up-phase of delta activity (Lakatos et al., 2005), and gamma bursts occur during the up-phase of theta activity (Lisman and Buzsáki, 2008). Thus, it has been suggested that local modules of high-frequency gamma can be functionally linked in temporal synchrony with distant modules via lower frequency theta and gamma band regulation. Bastiaansen et al. (2005) showed that the left hemisphere theta activity might be related to the processing of words with extensive semantic stores. The present results, showing increases of gamma TEP synchronization in a late time window (600–700 ms) between the left pars opercularis and the left supramarginal area, may be related to local processes associated with feature binding (Gray and Singer, 1989; Tallon-Baudry et al., 1998), whereas the increases in TEP synchronization in the theta band at the 450 to 550 ms time window between the left pars opercularis area and left supramarginal area might serve as a long-range synchronization between frontal and parietal cortices (von Stein and Sarnthein, 2000; Mellem et al., 2013).

Delta oscillations, on the other hand, have been mainly associated with slow-wave sleep and anesthesia, which are states without conscious awareness. However, delta oscillations might also play a role during wakefulness. For instance, high delta (approximately 3 Hz) appears to organize gamma oscillations during memory retrieval tasks (Burgess and Ali, 2002). Thus, the dissociation of changes in PLV induced by real cTBS within the delta band might be related to different functions and also warrant further study.

We also found a significant decrease in phase synchronization of high beta band in sham condition only between left pars opercularis and left superior temporal areas at T0. Although the PLV was relatively low compared to real cTBS condition, this decrease might have been related to functional changes in this network. There was some evidence that shows decreased coherence in beta band coherence after stimulation of the motor cortex with inhibitory protocol (Mima et al., 2003; Tamura et al., 2005), but also after periods of rest (Fuggetta et al., 2007). Recent evidence also showed a decrease in beta wave at 100–200 ms after sham cTBS (Opitz et al., 2015), in congruence with our sham result. Thus, the decrease in high beta coherence we observed in the sham condition could be related either to a placebo effect of the stimulation, or to the fact that the participants were at rest during the stimulation. We cannot entirely exclude the possible influence of the previous stimulation session due to relatively short washout period (at least 48 h), although studies using a single-session cTBS protocol with usual intensity (such as the one used in the present study) have been reported to last its effects approximately only 20–60 min (Huang et al., 2005; Chung et al., 2016).

Our results provide novel insights into the interhemispheric and intrahemispheric dynamics of activity across nodes of the language network and illustrate the potential of using noninvasive brain stimulation for their controlled modulation. Such findings may have implications for the future development of noninvasive stimulation protocols to promote recovery of aphasia.

The datasets generated for this study are available on request to the corresponding author.

The studies involving human participants were reviewed and approved by Beth Israel Deaconess Medical Center, Boston, MA, USA. The patients/participants provided their written informed consent to participate in this study.

W-KY, SB, and AP-L designed the study. A-KB, FI-M, ME, and MV collected the data. W-KY and J-HK analyzed the data. W-KY, MV, J-HK, A-KB, FI-M, ME, SB, and AP-L wrote the main manuscript text. All authors reviewed the manuscript.

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.