Corticospinal neurons in macaque ventral premotor cortex with mirror properties: a potential mechanism for action suppression?

Abstract

The discovery of "mirror neurons" in area F5 of the ventral premotor cortex has prompted many theories as to their possible function. However, the identity of mirror neurons remains unknown. Here, we investigated whether identified pyramidal tract neurons (PTNs) in area F5 of two adult macaques exhibited "mirror-like" activity. About half of the 64 PTNs tested showed significant modulation of their activity while monkeys observed precision grip of an object carried out by an experimenter, with somewhat fewer showing modulation during precision grip without an object or grasping concealed from the monkey. Therefore, mirror-like activity can be transmitted directly to the spinal cord via PTNs. A novel finding is that many PTNs (17/64) showed complete suppression of discharge during action observation, while firing actively when the monkey grasped food rewards. We speculate that this suppression of PTN discharge might be involved in the inhibition of self-movement during action observation.

Figure 1

Stimulation of the Pyramidal Tract (A) Antidromic volley, recorded during surgery in M41, from the cortical surface of M1 to stimulation of the ipsilateral PT (bipolar stimulation through two implanted electrodes 5 mm apart in PT, single biphasic shock, 200 μA). Vertical arrow indicates beginning of antidromic response (∼0.7 ms from PT stimulus onset at zero time). Average of 100 sweeps. (B–D) Short-latency EMG response in contralateral thenar muscles to PT stimulation (single bipolar shock 250 μA). These were recorded in M43 awake at the beginning (C), middle (D), and end (E) of the experimental period. Averages of 50 sweeps. (E) Transverse section through brainstem of M41, showing location of tip of posterior PT electrode on right (R) side and surrounding gliosis. PYR, pyramidal tract; IO, inferior olive; ML, medial lemniscus; MLF, medial longitudinal fasciculus; VI, abducens nucleus; XII, hypoglossal nerve.

Figure 2

Examples of Two Different Types of Response in F5 PTNs: One Activated during Action Observation and the Other Suppressed (A and K) Photo of monkey grasping a piece of food in a precision grip; (F and P) photo of experimenter grasping a piece of food in precision grip; (B and L) raster plots for two PTNs during self-grasp aligned to cue for onset of reach-to-grasp movement (indicated by black vertical lines); data from ten successive trials are shown. Note that there were several bursts of activity in both PTNs, associated with initial grasp of reward and then release of food at the mouth, with each burst associated with peaks of EMG activity in distal muscles, such as thenar (see traces in D and N). (G and Q) raster plots for two PTNs during ten trials of mirror testing (precision grip with object) aligned to the moment of contact of the experimenter's hand with the target object (indicated by black vertical lines). Light-blue circles on each trial indicate beginning of baseline interval for each trial (experimenter's hand motionless in full view of monkey), and magenta asterisks indicate beginning of experimenter's movement toward the object. (C, H, M, and R) Average firing rates based on rasters above (spikes/s); (D and N) superimposed records of EMG activity from three muscles (D: deltoid, ECU, and thenar; N: biceps, ECR-L, and thenar) during the same ten self-grasp trials as in (B) and (L), respectively; (I and S) superimposed records of EMG activity from all nine muscles during the same ten mirror testing trials shown in (G) and (Q), respectively. Muscles are divided into three groups of three records. EMG activity from the same trials are in same color; all EMGs are autoscaled to the maximum activity during self-grasp. Note almost complete absence of EMG activity during mirror testing (I and S). (E, J, O, and T) Antidromic responses from PTNs in response to PT stimulation, onset of PT stimulus is indicated by arrows, black curves are averages over tens of trials, antidromic spikes had constant latency throughout (facilitation cell [E and J] 2.4 ms, suppression cell [O and T] 2.8 ms) before (E and O) and after (J and T) mirror testing; red curves show collisions when a spontaneous spike appeared after the collision interval (indicated by dotted line): the antidromic spike was collided and absent from the record.

Figure 3

Population Summary of Activity in F5 PTNs (A) Population average of PTN firing rates during action observation of precision grip with an object and (B) for active grasp of a food reward by the monkey with its contralateral hand. Data plotted separately for mirror PTNs, which showed facilitation (n = 11, red) and suppression effects (n = 14, blue) during action observation, or no effect (non-mirror PTNs, n = 23, green). Dotted lines indicate standard error of the mean. Alignment at time zero in (A) is to the touch of magnetic sensor by experimenter and in (B) to the cue for the monkey to begin its reach-to-grasp movement. Note that both facilitation and suppression types of PTN increased their discharge during active grasp, with the increase beginning shortly after the cue and associated with the first burst of EMG activity in distal muscles. Firing rate for each PTN is in arbitrary units (a.u.): the rate was first normalized to unitary standard deviation over −2 to 2.5 s period, and then shifted to have average baseline (between −2 and −1) equal to zero. Data plotted are for PTNs recorded during sessions with no significant EMG activity during action observation.

Figure 4

PTN Activity during Observation of Grasp in Different Contexts (A–C) Raster plots and average firing rates during action observation of grasps carried out under three different conditions. The photographs show the actions as seen by the monkey. In (A), the experimenter performed a precision grip with an object present, in (B), a precision grip without an object being present, and in (C), the grasp was concealed from the monkey by the opaque walls of the food bowl. Background discharge in this F5 PTN was suppressed in all three conditions. Rasters and average firing rates aligned to the touch of magnetic sensor by experimenter's finger tip. Other notations as in Figure 2. (D–F) Percentage of PTNs recorded in EMG-free sessions (see Experimental Procedures), which exhibited significant “mirror-like” activity (p < 0.05, a Mann-Whitney U test) during the three grasp conditions. PTNs facilitated or suppressed during action observation in red and blue, respectively. PTNs with no mirror activity shown in unfilled segment.

Figure 5

Antidromic Latencies of F5 and M1 PTNs Distribution of antidromic latencies (ADLs) for PTNs in F5 (n = 64 in red; mean ADL 2.8 ± 1.5 ms) and in M1 (n = 100, open columns; mean ADL 1.5 ± 1.2 ms) and recorded in M41 and M43. The subset of F5 PTNs that showed “mirror-like” activity is shown in blue. The red vertical arrow indicates median value of ADLs for F5 PTNs (2.6 ms) and the black arrow for M1 PTNs (0.9 ms). These two populations were significantly different (p < 1e–6, Mann-Whitney U test). We did not find any significant difference between ADLs of mirror and non-mirror PTNs.