Temporal framing of thalamic relay-mode firing by phasic inhibition during the alpha rhythm

Abstract

Several aspects of perception, particularly those pertaining to vision, are closely linked to the occipital alpha (alpha) rhythm. However, how the alpha rhythm relates to the activity of neurons that convey primary visual information is unknown. Here we show that in behaving cats, thalamocortical neurons in the lateral geniculate nucleus (LGN) that operate in a conventional relay-mode form two groups where the cumulative firing is subject to a cyclic suppression that is centered on the negative alpha rhythm peak in one group and on the positive peak in the other. This leads to an effective temporal framing of relay-mode output and results from phasic inhibition from LGN interneurons, which in turn are rhythmically excited by thalamocortical neurons that exhibit high-threshold bursts. These results provide a potential cellular substrate for linking the alpha rhythm to perception and further underscore the central role of inhibition in controlling spike timing during cognitively relevant brain oscillations.

Figure 1

Naturally Occurring α Rhythms Are Related to Synchronized HT Bursting in a Subset of LGN TC Neurons (A) Simultaneous occipital EEG recording and recordings of local field oscillations (LFO) and TC neuron activity from the ipsilateral LGN during an α rhythm epoch in a behaving cat. The two unit recordings are from HT bursting TC neurons (underlined section is expanded below). (B) Cross-correlogram of the LGN and EEG recordings shown in (A) over an extended recording period (see also Figure S1). (C) (Top) Spike timing histogram for the neuron labeled HT2 (in A), constructed from 14 consecutive α rhythm epochs, indicates that while most spikes occur close to the negative LFO peak, a significant group (red arrows) also occurs near the positive peak. (Bottom) Cumulative spike timing histogram for 14 different HT bursting TC neurons shows a similar general form.

Figure 2

Relay-Mode Firing in LGN TC Neurons In Vivo and In Vitro Is Suppressed near the Negative or Positive Peak of the α Rhythm (A) LGN recordings, from a behaving cat, of the α rhythm and two tonic firing, i.e., relay-mode, TC neurons where the minimum amount of firing (green arrows) occurs close to the negative (top, in-phase suppression) and positive (bottom, antiphase suppression) LFO peaks. Corresponding spike timing histograms are on the right. (B) (Top) Cumulative spike timing histogram for 12 relay-mode TC neurons where minimum firing (dotted line) occurred close to the negative LFO peak (i.e., in-phase suppression). Note how this essentially translates to a cyclic facilitation centered on the positive LFO peak. (Bottom) Cumulative spike timing histogram for seven relay-mode TC neurons where minimum firing (dotted line) occurred close to the positive LFO peak (i.e., antiphase suppression), in this case essentially translating to a cyclic facilitation centered on the negative LFO peak. The light gray shaded area is the standard error. (C) Simultaneous in vitro LGN recordings of the Cch-induced α rhythm and two relay-mode TC neurons where the minimum amount of firing (green arrows) occurs close to the negative (top, in-phase suppression) and positive (bottom, antiphase suppression) LFO peaks. Note the similarity of the corresponding spike timing histograms, shown to the right, with those produced from the in vivo data. (D) (Top) Cumulative spike timing histogram for seven spontaneously active relay-mode TC neurons recorded in vitro where minimum firing occurred close to the negative LFO peak (i.e., in-phase suppression) has a similar form to that obtained from in vivo data. (Bottom) The cumulative spike timing histogram for five spontaneously active relay-mode TC neurons recorded in vitro where minimum firing occurred near the positive LFO peak (i.e., antiphase suppression) is also similar to its in vivo counterpart. Note: 50 μM Cch was present for all in vitro experiments depicted in this and subsequent figures.

Figure 3

Acitivity of Putative LGN Interneurons and PGN Neurons during α Activity in Naturally Waking Cats (A) (Left) LFP recording from the LGN bandpass filtered at 5–15 Hz (top) and corresponding firing rate histogram of a putative LGN interneuron (bottom). Note how periods of higher-amplitude α oscillations (light red bars) are accompanied by increased firing. (Right) Summary of firing rate changes in eight LGN interneurons during and outside α rhythm epochs (see Experimental Procedures). (B) (Left) LFP recording from the LGN bandpass filtered at 5–15 Hz (top) and corresponding firing rate histogram of a PGN neuron (bottom). Higher-amplitude α oscillations (light red bars) are correlated with decreased firing. (Right) Summary of firing rate changes in 10 PGN neurons during and outside α rhythm epochs. (C) (Top) Unit activity of a putative LGN interneuron recorded in vivo simultaneously with the LFO. The spike timing histogram for 10 consecutive α rhythm epochs is shown to the immediate right and reveals a preference for firing close to the negative LFO peak. The cumulative spike timing histogram for five distinct cells of this type is shown to the far right. (Bottom) Unit activity of a different LGN interneuron, again recorded in vivo along with the LFO. The underlined section (enlarged below) reveals unusual bursts where the first ISI is notably longer than subsequent ISIs. The spike timing histogram for 10 consecutive α rhythm epochs is shown to the immediate right (gray bars) and reveals that this cell preferentially fires near the positive LFO peak. This is due to the presence of prolonged bursts because the first spikes in a burst (green bars) occur preferentially near the negative LFO peak. The cumulative spike timing histogram for three distinct cells of this type is shown to the far right. (D) (Left) Cross-correlogram for an HT bursting TC neuron-interneuron pair in the LGN reveals a strong correlation between the firing of the two cells. (Right) Cross-correlogram for an interneuron-relay-mode TC neuron pair reveals that interneuron firing is related to a strong suppression of relay-mode firing (see also Figure S4). (E) (Left) Spike timing histogram for the only PGN neuron that was correlated with α activity. (Right) Cumulative spike timing histogram for the other nine PGN neurons recorded in vivo. Error bars represent mean ± SEM.

Figure 4

The Output of Relay-Mode TC Neurons In Vitro Is Closely Related to Their α-Rhythm-Derived Subthreshold Membrane Potential Dynamics (A) Simultaneous recording of the subthreshold membrane potential (bottom) in a relay-mode LGN TC neuron in vitro and the proximal LFO (top) (underlined section is expanded below). The LFO-triggered membrane potential average is shown on the right. Note the clear correlation between the LFO and membrane potential. (B) Same cell as in (A) during a brief period of spontaneous relay-mode firing. The underlined section (expanded below) shows the interruption and temporal offsetting of firing by transient hyperpolarizing excursions (green arrows) that are initiated close to the positive LFO peak (vertical dotted lines). The plot on the right shows the corresponding spike timing histogram, which reveals a clear suppression of firing near the positive LFO peak. The blue trace is the membrane potential average shown in (A) filtered at 2–20 Hz. Note the presence of two clear troughs (green arrows) and how action potential timing corresponds closely with subthreshold activity. (C) Grand averages (blue traces) of the time-normalized LFO-triggered subthreshold membrane potential average for the seven in-phase suppressed (left) and five antiphase suppressed (right) cells depicted in Figure 2D. The gray traces are scale-independent spline curves generated from the corresponding cumulative spike timing histograms in Figure 2D. Note the qualitative correspondence between subthreshold activity and action potential output.

Figure 5

Temporal Framing of Relay-Mode Firing In Vitro Results from GABAergic Inhibition (A) (Left) Cumulative spike timing histograms for four in-phase suppressed relay-mode TC neurons. (Right) This pattern is disrupted by 10 μM GBZ. (B) (Left) Cumulative spike timing histograms for three antiphase suppressed relay-mode TC neurons. (Right) Again, this pattern is disrupted by 10 μM GBZ. (C) Simultaneous recording of an LGN TC neuron at 0 mV with a Cs⁺/QX314-filled electrode and the proximal LFO. The underlined section (enlarged below) shows the presence of rhythmic (see auto-correlogram in the inset above), single (and occasional pairs of) IPSPs that mainly occur in phase with the negative LFO peaks (see E, left). These IPSPs are abolished by 10 μM GBZ. Overlays of several IPSPs (bottom panel) reveal the characteristic voltage-dependent GABA_A receptor-mediated IPSPs. (D) Simultaneous recording of a different LGN TC neuron at 0 mV with a Cs⁺/QX314-filled electrode and the proximal LFO. The underlined section (enlarged below) shows the presence of rhythmic (see autocorrelogram in the inset above) IPSP bursts that largely occur in phase with the positive LFO peaks (see F, left). These IPSPs are greatly suppressed by the combined application of NBQX and APV. Overlays of several IPSP bursts (bottom left) reveals that the main burst is often preceded by a single IPSP (green arrow). The average burst is shown to the right. (E) IPSP timing histograms for the TC neuron shown in (C) (left) and for four neurons that showed the same type of phasic inhibition (right). (F) IPSP timing histograms for the TC neuron shown in (D) (left) and for four neurons that showed the same type of phasic inhibition (right). Note: the effects of GBZ on HT bursting TC neurons are described in Supplemental Results Section D and Figure S8.

Figure 6

Firing of LGN Interneurons In Vitro Is Correlated with Ongoing α Activity and Can Occur in Two Distinct Modes (A) (Top left) Intracellular recording of an LGN interneuron in the absence of steady current and extracellular recording of the proximal LFO. (Bottom left) Injection of steady hyperpolarizing current exposes prominent excitatory synaptic input (underlined sections are expanded below). (Top right) Power spectra for the LFO (black line) and intracellular subthreshold activity (red line) reveal that the two signals share dominant frequency components. (Bottom right) EPSP timing histograms for the neuron on the left (left plot) and for five different LGN interneurons (right plot) reveal a strong correlation between synaptic events and α activity. (B) (Top) Intracellular recording of another LGN interneuron in the absence of steady current and extracellular recording of the proximal LFO (see also Figure S10B). The corresponding spike timing histogram is shown to the immediate right and a cumulative histogram for four distinct LGN interneurons recorded in the absence of steady current is on the far right. Both plots show that in this condition, firing predominantly occurs near the negative LFO peak. (Bottom) Following injection of 50 pA steady depolarizing current, the cell exhibits rhythmic bursting activity. The underlined section (enlarged below) reveals that individual bursts commonly exhibit a large interval after the first spike. The corresponding spike timing histogram (shown to the immediate right) now exhibits two peaks (green arrows), a small one near the negative LFO peak and a dominant one near the positive peak. The green bars depict the timing of only the first spikes in a burst and demonstrates that although the majority of action potentials in this situation occur near the positive LFO peak, bursts are nonetheless initiated near the negative peak (see also Figure S10A). To the far right is a cumulative spike timing histogram for four distinct LGN interneurons that exhibited similar bursting. (C) Bar graphs summarizing mean firing rate, EPSP amplitude, and individual EPSP frequency in LGN interneurons and PGN neurons recorded in the presence of 50 μM Cch (see also Figure S15C). (^∗∗p < 0.01; ^∗∗∗p < 0.001.) Error bars represent mean ± SEM.

Figure 7

LGN Interneurons Sense and Integrate Activity from the HT Bursting TC Neuron Network In Vitro (A) Subthreshold synaptic activity in an LGN interneuron (INT) and multiunit activity from closely situated HT bursting TC neurons (HT). The sections marked 1 and 2 (expanded below) reveal clear synchrony between HT bursting and synaptic activity in the interneuron. This is confirmed by the discrete cross-correlogram (individual EPSPs × extracellular spikes) shown on the top right and the average subthreshold interneuron activity (triggered by the start of each multiunit burst, shown in blue for reference purposes) shown on the bottom right. (B) Discrete cross-correlograms of the same type as those in A for six HT bursting TC neuron-interneuron pairs (left) and six relay-mode TC neuron-interneuron pairs (right) showing consistent synchronization between the former but not the latter. (C) Subthreshold synaptic activity in an LGN interneuron (INT) and unit activity from a closely situated HT bursting TC neuron (HT) in the presence of 50 μM Cch only (top) and following addition of NBQX and APV (bottom). The average subthreshold interneuron activity (triggered by burst start) for each condition, as well as following NBQX/APV washout, is shown on the right. These reveal that HT bursts are followed by a transient depolarization that is reversibly blocked by NBQX/APV. (D) (Top) Simultaneous intracellular recording of an LGN interneuron depolarized with 30 pA steady current and extracellular recording of a closely situated HT bursting TC neuron. (Bottom) Same recordings but with the interneuron not subject to any steady current. Shown to the right is the average subthreshold activity of the interneuron (black trace; triggered by HT burst start, see blue reference trace). The spike timing histograms for the interneuron relative to HT bursting for the situation where the interneuron is subject to steady depolarization (gray bars) and when steady current is absent (black bars) are shown below. Note that in the absence of depolarizing current, action potentials occur mainly close to onset of the average EPSP, whereas following steady depolarization they predominantly occur after the EPSP peak.

Figure 8

Schematic Representation of the Thalamic Circuitry Underlying the α-Rhythm-Derived Temporal Framing of Relay-Mode Firing HT bursting TC neurons (blue filled circles, HTB) form a GJ-coupled network in the LGN that generates synchronized oscillations at α frequencies. These cells may also couple via weak GJs (thin dotted lines) to a subset of TC neurons that exhibit conventional relay-mode firing (red filled circles, R-M). The main sequence of α-rhythm-related events that shape relay-mode firing, however, is as follows. First, HT bursting TC neurons provide a convergent excitation of local GABAergic interneurons (green filled circles, INT), probably via axon collaterals. This convergent excitation rhythmically drives interneuron firing, which can consist of either primarily single spike output (left side) or bursting (right), with bursting occurring when interneurons occupy a more excited state (see Figure 6B). During single spike output, action potentials in interneurons occur predominantly close to the negative α rhythm peak. In contrast, during bursting, a large interval between the first and second spikes in individual bursts means that action potentials are translated to occur mainly close to the positive α rhythm peak. These two forms of interneuron firing are then reflected in relay-mode TC neurons as mainly single IPSPs that occur near the negative α rhythm peak or IPSP bursts that occur near the positive α rhythm peak, respectively. Ultimately, these two forms of inhibition lead to a differential temporal framing of output from relay-mode TC neurons. Since HT bursting neurons and relay-mode cells are both TC neurons, they both receive retinal input, and send projections to the primary visual cortex. This means (1) that the α-rhythm-generating machinery in the LGN can be potentially perturbed or entrained by sensory input, and (2) that the neocortex not only receives modulated input from relay-mode TC neurons, but also receives a signal from the rhythmic network of cells that provides that modulation.