Emergence of a stable cortical map for neuroprosthetic control

Abstract

Cortical control of neuroprosthetic devices is known to require neuronal adaptations. It remains unclear whether a stable cortical representation for prosthetic function can be stored and recalled in a manner that mimics our natural recall of motor skills. Especially in light of the mixed evidence for a stationary neuron-behavior relationship in cortical motor areas, understanding this relationship during long-term neuroprosthetic control can elucidate principles of neural plasticity as well as improve prosthetic function. Here, we paired stable recordings from ensembles of primary motor cortex neurons in macaque monkeys with a constant decoder that transforms neural activity to prosthetic movements. Proficient control was closely linked to the emergence of a surprisingly stable pattern of ensemble activity, indicating that the motor cortex can consolidate a neural representation for prosthetic control in the presence of a constant decoder. The importance of such a cortical map was evident in that small perturbations to either the size of the neural ensemble or to the decoder could reversibly disrupt function. Moreover, once a cortical map became consolidated, a second map could be learned and stored. Thus, long-term use of a neuroprosthetic device is associated with the formation of a cortical map for prosthetic function that is stable across time, readily recalled, resistant to interference, and resembles a putative memory engram.

Figure 1. Experimental setup and stability of ensemble recordings.

(A) Schematics for manual control (MC) and brain control (BC). During MC, the animal physically performs a two-dimensional center-out task using the right upper extremity while the neural activity is recorded. Under BC, the animal performs a similar center-out task using a computer cursor under direct neural control through a decoder trained during MC. (B) Stability of putative single units across multiple days. Upper panels show a set of waveforms on day 1 versus day 19. The height and width of each box are 0.5 mV and 800 µs, respectively. (C) Stability of firing properties across time. Interspike interval (ISI) distributions are shown for days 1 and 19 for three representative units. There were no significant differences between each pair of distributions (p>0.05, Kolmogrov-Smirnov Test).

Figure 2. Brain control performance with practice.

(A) Changes in BC performance for consecutive days in the setting of a fixed decoder and a fixed set of units in two monkeys (inset = Monkey R). The top panel shows the mean accuracy per day, and the bottom panel shows the mean time to reach each target with training. Error bars represent ±2 standard errors of the mean (s.e.m.). (B) Trends of performance for select days for Monkey P. For each day, the moving average (i.e., percentage of correct trials for a moving window of 20 trials) of performance is shown. (C) Performance during the first 5 min of BC for each daily session. Each bar represents an initiated trial (red = error trial, blue = correct trial). (D) Left: representative examples of single-trial cursor trajectories during the initial (day 3, n = 1/target) and the late (day 13, n = 5/target) phases of BC performance. The targets are shown in grey. Right: color map of the comparison of mean trajectories for each day. Each pixel represents the pairwise correlation between the mean paths from the center to each of the eight targets. R = correlation coefficient.

Figure 3. Stable task performance is associated with stabilization of ensemble tuning properties.

(A) Tuning properties of a single unit in BC across multiple days. The top panel shows the spiking activity of a neuron during BC (n = 26 trials per target). The rasters are arranged to reflect the eight targets in the center-out task (target angles shown in red). Also shown are 200 randomly selected waveforms from two separate sessions (days 9 and 19). The inset shows overlapping tuning curves for each daily session for 10 consecutive days of BC. The shown voltage (V) is the peak-to-peak amplitude for both the shown waveforms. (B) Tuning properties of another unit in BC for ten consecutive days. The panel is arranged similarly to (A). (C) The three color maps to the left illustrate ensemble tuning in BC for days 3, 14, and 18 (specific units from [A] and [B] are labeled accordingly). The units were sorted on day 3 with respect to preferred direction. On the right is a color map of pairwise correlations of ensemble tuning (i.e., map) for each BC session. Warm colors represent a higher level of correlation. (D) Comparison of the learning rate with changes in ensemble tuning for two monkeys. The black solid line reproduces the learning rate from Figure 2. The red solid line represents the average correlation between a daily map and all other ensemble maps (directional tuning was assessed with 2 s of activity relative to intended target. The dotted red line shows the same relationship for directional tuning assessed with a 0.2-s window. The red line with superimposed red dots illustrates the relationship for directional tuning relative to actual cursor movements.

Figure 4. Stable long-term changes in the depth of modulation.

(A) Changes in the depth of modulation for a single unit accompanying increases in BC performance (Monkey R). Each dot represents the modulation depth of the neural firing rate (in hertz) for a given BC session. Representative tuning curves from the initial (days 1 and 3 in a lighter color), and late phases (days 4 and 8 in a darker color) of BC are shown in the upper left corner. The shaded circle around each dot identifies sessions represented by the tuning curves. The dotted grey line represents the mean depth of modulation for the respective cluster of dots. (B) Long-term changes in the depth of modulation for a representative single unit from Monkey P, arranged similarly to (A).

Figure 5. Dependence of BC performance on size of the neural ensemble.

Relationship between changes in the neural ensemble size and brain control performance after consolidation of an ensemble map. Plot of changes in BC performance (relative to performance at baseline) after random removal of one to six neurons from the neural ensemble. The error bars represent the standard error of the mean (s.e.m.). For experiments with an n = 1, only the mean is shown. For the respective experiments in which only one and six neurons were dropped, the s.e.m. was sufficiently small to be covered by the black dot. Number next to each point represents the number of separate experiments performed. The dotted line represents a linear fit (R = 0.95).

Figure 6. Map stabilization with a shuffled decoder.

(A) Comparison of the “offline” predictive ability of an intact and a shuffled decoder. The dark traces are the actual movements. The light blue traces are predictions with each decoder. For each set, the upper trace is the shoulder angular (Ang.) position, and the lower trace is the elbow angular position. R is the correlation between the actual and the predicted movements. (B) Temporal course of task performance (solid line) and map stabilization (red dots) for BC with a shuffled decoder. This plot is arranged similarly to Figure 3D. The color map inset shows the pairwise correlation among each daily ensemble tuning map.

Figure 7. Specificity of neural adaptations to the decoder.

(A) Reversible drop in performance with a change in the applied decoder. The upper panel compares the two applied decoders. Pair of bars shows the mean weight for each neuron in each decoder (paired t-test, an asterisk [*] indicates p<0.05, FDR corrected for multiple comparisons). The lower panel shows the number of correct and incorrect trials in the presence of Decoder_OLD (black bar) and Decoder_NEW (green bar). a.u., arbitrary units. (B) Changes in performance for similar trials (n = 4) in both monkeys with substitution of newly trained decoders (mean±standard error; ANOVA, p<10⁻⁵; the asterisk [*] indicates p<0.05, FDR corrected for multiple comparisons).

Figure 8. Simultaneous retention of two maps without interference.

(A) Changes in performance in the presence of two decoders over 4 d of training. Decoder_NEW (red bar) was introduced on day 1. Decoder_OLD (blue bar) represents the set of weights that were learned over the course of 19 d of training (as shown in Figures 2 and 3). The panels on the left show a moving average of the performance over the entire session (window size = 20 trials), and the panels on the right represent the mean session performance. (B) Changes in directional tuning for units during BC under Decoder_NEW and Decoder_OLD. Each inset (i–iii) shows the relationship (color convention as in [A]) for the firing rate versus direction (dotted line and filled circles, respectively). The error bars represent the s.e.m. The solid line represents the cosine fit for directional modulation of the firing rate. Shown on the right are 100 randomly selected waveforms for each unit under each of the two conditions. The numbers represent the preferred direction (PD). The asterisk (*) indicates p<0.005 for bootstrap analysis with correction of FDR for multiple comparisons.