Optogenetic drive of neocortical pyramidal neurons generates fMRI signals that are correlated with spiking activity

Abstract

Local fluctuations in the blood oxygenation level-dependent (BOLD) signal serve as the basis of functional magnetic resonance imaging (fMRI). Understanding the correlation between distinct aspects of neural activity and the BOLD response is fundamental to the interpretation of this widely used mapping signal. Analysis of this question requires the ability to precisely manipulate the activity of defined neurons. To achieve such control, we combined optogenetic drive of neocortical neurons with high-resolution (9.4 T) rodent fMRI and detailed analysis of neurophysiological data. Light-driven activation of pyramidal neurons resulted in a positive BOLD response at the stimulated site. To help differentiate the neurophysiological correlate(s) of the BOLD response, we employed light trains of the same average frequency, but with periodic and Poisson distributed pulse times. These different types of pulse trains generated dissociable patterns of single-unit, multi-unit and local field potential (LFP) activity, and of BOLD signals. The BOLD activity exhibited the strongest correlation to spiking activity with increasing rates of stimulation, and, to a first approximation, was linear with pulse delivery rate, while LFP activity showed a weaker correlation. These data provide an example of a strong correlation between spike rate and the BOLD response. This article is part of a Special Issue entitled Optogenetics (7th BRES).

Fig. 1

Light-evoked pyramidal cell spiking results in a consistent BOLD fMRI response in Thy1-ChR2-YFP mice. Activation was observed across all animals. For each individual animal, an anatomical coronal slice where the craniotomy was located and fiber optic inserted is presented (left). The region of stimulation is denoted by a white rectangle. “Localizer” runs consisted of 16 repetitions of 15 s on–15 s off light-pulses at 40 Hz/8 ms pulse duration (4–8 for each animal). A statistical parametric map of a positive BOLD response to light stimulation (P<0.05 corrected for multiple comparisons using family-wise error [FWE] correction) is overlaid to demonstrate the extent of response for each animal (right).

Fig. 2

High-pass filtered local field potentials (LFP) do not correlate with layer V pyramidal neurons spike activity. LFP acquired in in vivo neurophysiological experiments is traditionally recorded in alternating current coupled mode (effectively filtering frequencies below 0.1–1 Hz; e.g., see ref. Cardin et al., 2009). Consequently, voltage changes that take place on a timescale of seconds are abolished. We compared electrophysiological recordings using laminar probes (MUA and LFP in AC coupled mode [LFP]) and saline-filled glass pipettes (LFP in direct-current mode [dcLFP]) during optical stimulation (8 and 40 Hz at 2.7 ms pulse width). (A) MUA (band-pass filtered between 600 and 6000 Hz), as well as LFP and dcLFP (raw unfiltered signals) are depicted for a representative trial. (B) Firing rate (MUA) is elevated (n=2 animals) for 40 Hz compared to 8 Hz, while LFP power ratio (n=3 animals) decreased. Consistent with firing rate, dcLFP (n=3 animals) average voltage amplitude increased when light stimulation frequency increased. (C) Intracellular in vivo recordings in current clamp mode were carried out to measure the effects of frequency modulation on membrane potential, motivating recording LFP in direct current mode (dcLFP), and explaining power reductions observed with conventional LFP recordings. Here we plot the responses in a cell that showed light-driven subthreshold responses (as determined by latency) but no spiking. Average raw time series (unfiltered) for each condition (8 and 40 Hz with 2.7 ms pulse width) demonstrate the robust effect of 1 s train of light pulses on membrane potential. Notably, an overall shift in membrane potential is observed for 40 but not 8 Hz stimulation. Peak depolarization is equivalent between the two conditions but amplitude of oscillations differs. A quantification of this representative single trial is provided for mean membrane potential change (left), membrane potential modulation depth (middle) and power ratio (right). Mean membrane potential change was higher for 40 relative to 8 Hz, while modulation depth and power ratio, both reflecting the magnitude of oscillation, were higher for 8 relative to 40 Hz trains of light pulses.

Fig. 3

Fidelity of local field potential measurements. (A) A sine-wave at multiple frequencies (1, 2, 5, 10, 20, 50, 100, 200, 500, and 1000 Hz) was generated and passed into the amplifier through the headstage (left). The power of the recorded signal was computed and then interpolated at 8, 24, 40, 56, and 80 Hz (right). Comparison of 8 to 80 Hz of normalized power demonstrates that 0.7% reduction is observed. (B) The early, late and entire interval of optical stimulation is compared between the two principal methods for recording LFPs. As depicted, when power of the oscillatory neural activity recorded in direct current coupled mode LFP (dcLFP) is analyzed equivalently to the LFP recorded with the laminar electrodes (recorded in alternating current coupled mode), the resultant graphs show similar responses.

Fig. 4

Pyramidal neuron spiking and BOLD responses are greater for Poisson relative to periodic optical stimulation. (A) For each animal in the fMRI experiment (n=4), time series were extracted from a region of interest (ROI) identified in an independent localizer scan. The integrated BOLD response across the entire stimulation interval (2.5–17.5 s), as determined from the localizer scan, was computed. A monotonic increase in the BOLD signal as a function of stimulation rate and a greater signal increase for Poisson relative to periodic stimulation were observed. (B) Cell-attached single-unit activity (SUA) recordings demonstrated a monotonically increasing spiking rate for both stimulation regimes, and a greater signal increase was observed for Poisson than periodic stimuli. (C) Responses across neocortical layers were measured using 16-contact laminar electrodes with contacts spaced at 100 μm. The normalized responses for LFP power, MUA firing rate and direct current LFP (dcLFP) amplitude are plotted as a function of depth (100–1400 μm). During optical drive, MUA demonstrated a peak response at 700–800 μm with only baseline response elsewhere. In contrast, LFP demonstrated a response that was sustained from 100 μm to 700–800 μm, and dcLFP demonstrated a response that was elevated throughout and peaked at 700– 800 μm. (D) Poisson (red) and periodic (blue) regimes drove different LFP responses, yielding a decreased response when the rate of stimulation increased for periodic, and a constant response with a peak at 40–56 Hz for Poisson stimulation. The MUA did not differ between Poisson and periodic stimulation and demonstrated a monotonic increase at 700–800 μm depth for both regimes. (E) The dcLFP demonstrated an increased rate of stimulation for both stimulation regimes with an increased amplitude towards 700–800 μm that was followed by a slight drop at depth 1000 μm.

Fig. 5

BOLD signal time series can be derived from spiking activity. The time series of each measure (SUA and MUA firing rate, LFP power, and dcLFP amplitude) was down sampled to 2.5 s to match the resolution of the BOLD signal and was convolved with a canonical hemodynamic response function, yielding a predicted BOLD signal time series. Predicted time series were computed separately for Poisson and periodic regimes and are plotted here for 40 Hz stimulation rate. The response amplitude was determined by computing a least squares fit (black line) to the measured BOLD signal (Poisson —red line, shade [mean±sem]; Periodic—blue).

Fig. 6

Time series for Poisson (red) and periodic (blue) stimulation regimes at 40 Hz. Responses are depicted for BOLD percent signal modulation, SUA and MUA firing rate, LFP power, and dcLFP amplitude. Differences in the amplitude of response between early and late periods as a function of stimulation regimes motivated quantification of this modulation across the different measures.

Fig. 7

Analysis of early and late response components reveal similarity between the BOLD signal and spiking but not LFP measures. (A) Motivated by the differential dynamics observed in the time series of the BOLD signal and electrophysiological measures, we plot here early and late responses as a function of stimulation regime (Poisson and periodic) and frequency. Responses are depicted for BOLD percent signal modulation, SUA and MUA firing rate, dcLFP amplitude, and LFP, and gamma-bandpassed LFP (γLFP) power. (B) Neural to BOLD signal transfer functions were computed by fitting a 1st or 2nd order polynomial to each neural measure (SUA, MUA, LFP, dcLFP, and γLFP). A goodness-of-fit (r²) is plotted for 1st and 2nd order functions and the early and late response periods.