Sleep, as compared to wakefulness, is characterized by altered and reduced reactivity to external stimulation, but the brain mechanisms underlying these fundamental changes are not yet fully disclosed. On the other hand, some stimulus processing must be preserved allowing the sleeper to be aroused by personally meaningful or threatening stimuli. So far, mostly electrophysiological techniques, especially averaged event-related potentials (ERPs), have been used to investigate the brain's responsiveness to external stimuli, since electrophysiological measures are independent of behavioral responses or conscious awareness. In NREM sleep, several large amplitude ERP components are thought to reflect inhibition of information processing and may reflect the brain's capacity to generate delta frequency EEG activity, a marker of deep slow wave sleep [1].

The oddball paradigm, being a simple discrimination task, has been widely used to probe attentiveness in different vigilance states [1]–[5]. While active detection of stimulus deviance is associated with a P300 component during wakefulness, this component is not detectable when subjects either ignore or fail to detect the rare tone, or in consolidated NREM sleep [1], [5]. Similar, a mismatch negativity reflecting pre-attentive stimulus discrimination processes can be recorded during wakefulness, but is strongly reduced or absent in light NREM sleep [6], [7]. Furthermore, during NREM sleep an attenuation of the early N1 component has been observed, while P2 is enhanced, hypothesized to reflect decreased cortical excitability and increased inhibitory processes [1], [5], [8], [9]. In addition, sleep specific late ERP components such as the N350, P450, N550 and P900 arise. These components are most enhanced subsequent to rare stimuli, and have been found strongest with increased sleep pressure during the first half of the night [4] or following sleep fragmentation or sleep deprivation [10]–[12]. Taken together, it has been suggested that these late ERP components reflect inhibitory processes minimizing cognitive processing.

The late components N550 and P900 in NREM sleep are a reflection of the so called K-complex (KC), first described by Loomis et al. [13] as a prominent element of the human sleep EEG (for recent reviews, see e. g. [14], [15]). KCs may appear spontaneously, but can also be evoked by external stimuli. The functional significance of KCs, however, is still a matter of debate. As KCs can be elicited by cortical, thalamic or sensory stimuli, they are obviously involved in some form of information processing during NREM sleep. This has led to the notion of KCs being reactive micro-arousal processes without awakening [16]. Compatible with this notion, cortical reactivity was found increased in periods preceding KCs [17]. In turn, it has been hypothesized that KCs may also serve as a sleep protective mechanism by triggering anti-arousal reactions that support the consolidation and maintenance of sleep [15], [18]–[20]. Furthermore, Amzica and Steriade [21] suggested that KCs may represent the alternation between a state in which the cortical network would be ready to operate in case of danger (depolarizing phase) and a state where the brain is at rest, allowing replenishing of cellular energetic stores (hyperpolarizing phase).

First fMRI studies performed during NREM sleep applying acoustic stimulation showed contradictory results: Portas et al. [22] as well as Redcay et al. [23] and Wilke et al. [24] identified preserved activation of the primary auditory cortex in light NREM sleep in adults and children, respectively. However, these studies did not include EEG measurements to validate sleep during the actual fMRI data acquisition. The use of simultaneous EEG recordings and analysis of epochs directly related to sound presentation is mandatory to objectify sleep stages and to affirm sleep continuity. Other groups showed reduced or even inverted BOLD responses in the auditory cortex [25]–[27] in electrophysiologically verified sleep stages 1 and 2, respectively. All studies used different acoustic stimuli, e.g. personally relevant stimuli with strong arousal capacity such as the subject's own name, or less arousing stimuli like classical music or pure tones. In our earlier studies we observed a negative BOLD response (NBR) to acoustic stimuli presented in a block design during light NREM sleep, with paralleled increases in occurrence of KCs and delta activity [26], [27]. Using a different sensory modality, an NBR has also been obtained by Born et al. [28] for the primary and secondary visual cortex in response to appropriate visual stimuli during early NREM sleep. We proposed this NBR to reflect sleep inhibitory processes that eventually renders a function in consolidation and deepening of sleep.

Extending previous findings utilizing a block-presentation of stimulation, the present study aimed at a more precise description of auditory processing during light NREM sleep stage 2. To do so, an event-related acoustic oddball paradigm with rare tones interspersed in more frequent tones was applied. Experiments were designed to test the following hypotheses:

All 18 subjects were included for the analysis performed during wakefulness. For the sleep trial, one participant was not able to fall asleep at all and six participants only reached sleep stage 1 or spent less than 3 minutes continuously in stage 2. Another participant showed movement artifacts outside the tolerated range during the sleep recording. These subjects were excluded from further analysis. Finally, data from ten subjects (5 m/5 f, mean age 25.5±2.7 years) were used for further fMRI/EEG analyses focusing on sleep stage 2. Of these ten subjects, two subjects reached sleep stage 1 after less than one minute, three subjects after 3 minutes and five subjects after more than 5 minutes. Consolidated sleep stage 2 was reached after a mean latency of 10′13″±5′55″ min (range 0′44″–17′39″ minutes). fMRI volumes were extracted for continuous episodes in sleep stage 2 with an average duration of 14′55″±6′0″ minutes (range 8′54″–26′0″ minutes).

The present study combined fMRI/EEG to analyze the cerebral responses to auditory stimulation in light NREM sleep. Using an acoustic oddball paradigm, we revealed a prominent negative BOLD response (NBR) for rare tones compared to the background of frequent tones. This NBR occured independently of the generation of evoked KCs and was found predominantly in the motor cortex, the premotor and the supplementary motor areas, the bilateral dorsomedial PFC, and the bilateral amygdala. No wake-like activation of the auditory cortex was detected. Rare tones followed by an evoked KC, however, were associated with a wake-like activation of task-related areas in the temporal cortex, along with the right hippocampus.

The current study extends earlier findings on stimulus-induced NBR and its correlation with the increase in delta power during light NREM sleep [26], [27]. In contrast to our former report, no EEG frequency changes immediately after the rare tones were detected in the present study. Especially, no increase in higher frequency bands, an indicator of arousal, was found, and rather spurious slowing in the subsequent frequent epoch was observed. These differences to our earlier report can be attributed to the experimental design: The former data were based upon a paradigm with continuous stimulus presentation during blocks of 30 seconds, and the observed NBR and slowing of the EEG likely reflected habituation and longlasting sleep protective mechanisms. In the current study we used an event-related design which has stronger arousal capacities and which involves detection of tone deviance and related reflexive orienting responses. Still, the simultaneous EEG recordings confirmed stability of the sleep stage during the experiment.

During wakefulness, the detection of rare tones was accompanied by a MMN consistent with pre-attentive discrimination processes [34], [37]. An increased P300 was also observed, however, with rather small amplitude as compared to previously reported findings in active oddball paradigms [34], [37]. The fMRI activation pattern found for rare tones in wakefulness resembles the previously reported activation for the passive oddball paradigm, including predominantly superior temporal areas [38], [39]. In line with previous findings, P300 was not detectable in sleep stage 2, and sleep specific late ERP components arose [2], [40]. Furthermore, absence or strongly reduced amplitude of a MMN component has frequently been described during light NREM sleep [3], [6], [7], [41], suggesting that auditory processing is strongly affected during NREM sleep.

Noteworthy, the sleep-specific NBR was most pronounced in areas related to voluntary movements. We therefore submit that the transient suppression of brain areas involved in the generation and execution of motion activity is one of the factors that allows further consolidation of sleep. Reduced activity in the amygdala points towards altered processing of the emotional salience of the incoming stimulus during sleep [42]. In the passive oddball condition during wakefulness, the amygdala generally does not show specific activation for rare tones [43]. However, it was shown earlier that unpredictable irregularities in acoustic stimulus series as well as rare tones embedded in trains of frequent tones may lead to activation of the amygdala [44]. The amygdala has also been reported to constitute part of a network activated in the active oddball paradigm, both for rare and deviant tones [36]. Amygdala activation, however, is not prerequisite for target detection as demonstrated from lesion studies in epileptic patients [45]–[47]. Rather, it was suggested that salient stimuli lead to a reflexive orienting response with consequent preparative engagement of additional brain regions, including the amygdala, for the case of further sensory income [36]. During wakefulness, such an orienting reflex has been shown to be associated with an increased level of arousal, as reflected by EEG desynchronization, increased skin conductance and modulation of heart rate [48]. During sleep, autonomous arousal reaction may be suppressed in order to maintain and consolidate sleep. Accordingly, our EEG analysis during sleep did not reveal signs of such arousal reactions. Thus, we interpret the NBR in the amygdala as a sleep specific response, and submit that it reflects suppression of a reflexive orienting responses to the non-alarming, but unpredictable rare tone, supporting sleep protection by delimiting arousal reactions. We did neither observe activation of the auditory pathway nor the thalamus, in line with our previous work [26], [27] and data shown by Tanaka et al. in sleep stage 1 [25]. The opposed findings of Portas and colleagues [22], who reported preserved activation of the auditory cortex and thalamic regions during light NREM sleep, may originate from the use of more salient, especially personal stimuli such as the own names. Awakenings are highly likely to occur upon such stimuli and have indeed been reported by the authors for 30–50% of trials [22]. In addition, transient arousals during fMRI data acquisition may have remained undetected as EEG signals during scanning were not evaluated.

When segregating the rare tone with respect to appearance or non-appearance of an evoked KCs as the brain's prominent EEG response upon external stimulation, we found activation in the bilateral auditory cortex and the left middle and superior frontal cortex, precuneus, posterior cingulate, bilateral superior temporal cortex and the right hippocampus. As a whole, this network largely overlapped with the response to a novel (task-irrelevant) stimulus as compared to rare tones during wakefulness [36], with exception of the cingulate cortex and the right hippocampus. As anticipated by Sallinen [17], the sleeping brain may in fact be transiently more responsive to sensory events preceding a KC than preceding a non-KC response to a stimulus. The similarity of our results with the novelty oddball paradigm suggests an orienting response, in which the stimulus characteristics of the rare tone undergo a re-evaluation during sleep. This view is supported by a recent study reporting direct intrahippocampal ERP measurements in 16 epilepsy patients during a passive oddball paradigm. This study revealed involvement of hippocampal and parahippocampal structures in the preattentive processing of sound deviance during wakefulness [49]. Since the hippocampal potentials were shown to be reduced upon repetitive presentation of the rare tones, the authors proposed that they may be regarded as a central marker of an orienting response, facilitating the detection of sound deviance when sound discrimination becomes more difficult. Hippocampal and temporolateral activation as observed in our study may signify an update of stimulus characteristics during sleep. In summary, the general response to rare tones is reduced during sleep, however, a transiently more responsive brain state appears to occur in association with the generation of KC.

The precuneus, obviously playing a pivotal role in integrated tasks, reduces its activity during sleep [50], [51]. Thus, increased activity in the precuneus (and cingulate cortex) in response to rare tones eliciting KCs may be conceived as an additional signature of intensified stimulus processing.

Furthermore, we only observed BOLD activation in the superior frontocentral regions associated with KCs in a small number of areas. Given that KCs are the strongest of any evoked potentials recorded in humans [1], the finding that rare_KC events do not show a stronger correlate in the BOLD signal as compared to rare_w/oKC warrants further discussion. The strong topographical similarity of the NBR for both rare_KC and rare_w/oKC tones suggests common responses to the stimuli at the level of fMRI as e. g. reflected by the early N350 component with maximal values over vertex regions [32]. Bastien and Campbell [52] discussed whether evoked KCs are an all-or-none phenomenon: An external stimulus either elicits a KC or it does not, as averaging trials not showing an N550-P900 amplitude difference of at least 75 µV did not reveal any evidence of a N550 deflection at all. It was suggested that 'although the KC may occur in association with other indices of a defensive response, defensive responses also occur in the absence of the KC' [52]. Sleep defensive responses upon external stimulation as reflected by heart-rate acceleration was reported by Church et al. [53] to be independent of the occurrence of KCs [54]. This notion is now further supported by the present combined fMRI/EEG measurements that revealed an NBR response upon tone presentation, irrespective of the appearance of an evoked KC.

The discrepancy of a small difference in NBR between rare_KC and rare_w/oKC and a strong electrophysiological difference may further be related to the degree of synchronicity of the firing of cortical areas. While response to both types of rare tones may be associated with comparable metabolic demands, the electrophysiological response may not mount to a surface KC in the case of asynchronous firing. A recent computational study simulated KCs in terms of a mean field cortical model [55]. The authors interpreted the appearance of a KC as a momentary excursion of the cortex from a stable low-firing state to an unstable sleep specific high-firing state upon a small excitation. They observe a critical threshold for external disturbances, above which KCs are evoked, in accordance with the ‘all-or-none’ hypothesis. The momentarily increased stimulus transmission and processing may allow external stimuli to exceed this critical cortical threshold and may eventually lead to initiation of an evoked KC. However, our data suggest that the overall metabolic cerebral demand in regions showing highest EEG deflection during KCs is not strongly altered when the threshold for a KC is exceeded.

KCs have been postulated to have a diffuse cortical generator and represent a sleep specific, but modality independent response. This response does not depend on activation of the auditory pathway in the case of acoustic stimulation, or activation of the primary sensory pathway when elicited by inspiratory occlusion [14]. Therefore, increased activation of task-specific auditory pathways associated with evoked KC is unlikely to reflect the neural representation of the KC itself. Future studies should test this hypothesis by applying stimuli of different sensory modalities during NREM sleep fMRI experiments. Another option may be to target spontaneous KCs in undisturbed sleep without any external stimulation. However, to observe truly spontaneous KCs is technically demanding due to the noise during fMRI experiments.

Finally, our data only allow an indirect interpretation of the functional significance of KCs. We found that a brain state in which stimuli provoke an intensified brain activation (most closely resembling active novelty processing) is prone to generation of subsequent KCs. However, the passive oddball data collected during wakefulness do not directly support this notion. Still, it should be noted that the passive listening condition during wakefulness and the ‘passive’ condition of the subject while falling asleep and during established NREM sleep have categorically different qualities: During wakefulness, the subject retains awareness and can be instructed not to focus on deviant tones, while during sleep conscious control as necessary to follow task instruction cannot be maintained. Therefore, responses become automated and independent of any instruction. As these automated processes take over during sleep, external stimuli may be sporadically (re-)evaluated with respect to the level of novelty or deviation from the background. Our data show that rare tones followed by a KC exhibit signatures of increased activity, comparable with novelty processing as described by Kiehl et al. [36] during wakefulness. However, since EEG analysis did not reveal signs of arousal, we propose that the subsequently evoked KCs may rather reflect maintainance and consolidation of sleep than an arousal reaction.

The refractory period of KCs is roughly 10 seconds. Our design using an ISI of 2 seconds was optimized to measure KCs evoked by rare tones with a probability of 20%, thus roughly matching the refractory period. We intentionally avoided longer ISIs due to potential arousing effects of sparsely delivered tones. As a drawback of our design, we did not collect a sufficient number of KCs evoked by frequent tones, or spontaneous KCs, for fMRI analysis comparing different types of KCs. Regarding activation changes related to individual ERP components, the temporal resolution of BOLD signal changes in the order of several seconds did not allow to dissect the contribution of individual ERP components in our sample. Even more, if N550 and P900 represent opposing up and down states, the individual contributions may lead to a destructive interference of BOLD signal changes on the time-scale of fMRI measurements. Unfortunately, the limited number of KCs in our data do not allow to dissect contributions of these two ERP components. Further studies with larger numbers of KC events are required to disentangle possible different functional brain states associated with individual ERP components.

It has been shown earlier that the scanner noise leads to reduced ERP amplitudes, prolonged reaction times and decreased hit rates in active oddball paradigms [56], [57]. Generally reduced amplitudes in the electrophysiological measures during fMRI due the main magnetic field [33] have been accounted for by lowering the absolute amplitude threshold for identification of KCs during sleep. Otherwise, the influence of the scanner sound was considered to introduce similar reductions in ERP amplitudes during both wakefulness and sleep, still allowing for comparison of the respective ERP signals. However, our observations of rather small P300 amplitude differences between rare and frequent tones during wakefulness may in part be related to interference with the fMRI background noise.

Due to reduced quality of fMRI data caused by susceptibility artifacts in ventral frontal brain regions, we cannot fully exclude that such artifacts might delimit detection of KC related activity in ventral brain areas. However, as we observed significant activation changes in other basal brain regions like amygdala and hippocampus, a total loss of fMRI information in ventral frontal regions seems unlikely.

In conclusion, our data indicate altered acoustic processing during light NREM sleep in an oddball paradigm, showing strongly reduced activity of the auditory system in response to rare tones. We interpret a negative BOLD response in sensory motor areas and the amygdala as a sleep defensive mechanism delimiting reflexive orienting responses. Events followed by evoked KCs revealed increased activation of the auditory system and hippocampal and temporal structures probably reflecting increased responsiveness to the external stimuli and an updating of stimulus characteristics. However, other than expected, the strong electrophyiological signature of the K-complexes in frontocentral areas was not paralleled by corresponding BOLD increases. This dissociation between electrophysiological and metabolic correlates of KCs argues for increased cortical synchronization without additional metabolic demand.