Content-specific fronto-parietal synchronization during visual working memory

Abstract

Lateral prefrontal and posterior parietal cortical areas exhibit task-dependent activation during working memory tasks in humans and monkeys. Neurons in these regions become synchronized during attention-demanding tasks, but the contribution of these interactions to working memory is largely unknown. Using simultaneous recordings of neural activity from multiple areas in both regions, we find widespread, task-dependent, and content-specific synchronization of activity across the fronto-parietal network during visual working memory. The patterns of synchronization are prevalent among stimulus-selective neurons and are governed by influences arising in parietal cortex. These results indicate that short-term memories are represented by large-scale patterns of synchronized activity across the fronto-parietal network.

Fig. 1

Task dependence of fronto-parietal coherence. (A) Timeline of the identity-matching task. During visual fixation, a sample stimulus, consisting of 1 of 3 possible objects positioned at 1 of 3 possible locations, was presented for 500 ms, followed by a random delay of 800-1200 ms. At the end of the delay a match stimulus was presented, consisting of the previous sample object (target) and a distracter object positioned at 2 out of 3 possible locations. A saccadic eye movement to the target was rewarded with juice (14). (B) Example of the signals recorded on a single trial in monkey A. Top two traces: broadband signals from area PEC of the parietal cortex (PEC, green) and dorsolateral prefrontal cortex (dPFC, purple). Bottom two traces: horizontal and vertical eye position. (C,D) Time-frequency coherence spectrum (C) and average relative phase between 15 and 25 Hz (D) locked to the sample presentation (all stimuli, correct trials, 400 ms window, 50 ms step). In B-D, and in all subsequent figures, the vertical lines show the onset and offset of the sample. Time-frequency distributions in this and subsequent figures are interpolated at 1 Hz and 2 ms resolution.

Fig. 2

Content specific fronto-parietal synchronization during working memory. (A) Time-frequency coherence spectra for an LFP pair for the three sample objects presented at one location. (B) Coherence selectivity index as a function of time and frequency (CSI(t,f)) for the same pair showing significant selectivity (significance threshold at p < .02 indicated by white contours) during the delay period. (C) Median value of CSI(t,f) for LFP pairs showing selectivity for the sample identity (upper) and location (lower) during the delay. (D) Mean rank-ordered coherence (± SEM) in the 12-22 Hz band for the same identity selective pairs as in the upper plot of C. (E) Mean standard deviation of the relative phase (± SEM) in the 12-22 Hz band for the same identity selective pairs as in the upper plot of C. In plots D, E and Figure 3A, the two SEMs were calculated with the number of pairs or sessions as the degree of freedom.

Fig. 3

Fronto-parietal interactions are dominated by parietal-to-frontal influences. (A) Time course of WGC in the 12-22 Hz frequency range for all identity selective pairs (mean ± SEM; n = 438). (B, C) Bar charts of the incidence of significant WGC directional differences with respect to cortical area for all the signal pairs in A. (D) Example of the SFC for a LIP unit and the field recorded in area 8AD. Dashed line indicates confidence limit (p < .01, randomized surrogate). (E) Percentage of fronto-parietal pairs with significant SFC between 12 and 22 Hz. The unit activity was recorded in the labeled areas. See Tables S1 and S3 for abbreviations and sample sizes. (F) Percentage of significant PPC_unit–PFC_lfp pairs with respect to the parietal area in which the unit activity was recorded and split according to the stimulus selectivity of the cellular responses.