The Hippocampus and Neocortical Inhibitory Engrams Protect against Memory Interference

Abstract

Our experiences often overlap with each other, yet we are able to selectively recall individual memories to guide decisions and future actions. The neural mechanisms that support such precise memory recall remain unclear. Here, using ultra-high field 7T MRI we reveal two distinct mechanisms that protect memories from interference. The first mechanism involves the hippocampus, where the blood-oxygen-level-dependent (BOLD) signal predicts behavioral measures of memory interference, and representations of context-dependent memories are pattern separated according to their relational overlap. The second mechanism involves neocortical inhibition. When we reduce the concentration of neocortical GABA using trans-cranial direct current stimulation (tDCS), neocortical memory interference increases in proportion to the reduction in GABA, which in turn predicts behavioral performance. These findings suggest that memory interference is mediated by both the hippocampus and neocortex, where the hippocampus separates overlapping but context-dependent memories using relational information, and neocortical inhibition prevents unwanted co-activation between overlapping memories.

Keywords: EI balance; GABA; associative learning; hippocampus; inhibition; interference; memory; tDCS.

Figure 1

Experimental Design (A) Seven stimuli were used for the experiment, where each stimulus was an abstract shape which could appear in four possible rotations. (B–E) Example experimental protocol: (B) on day 1, participants learned seven associations between pairs of the seven stimuli shown in (A), and a contextual cue was provided using a yellow background. The associations could be arranged in a ring structure, although this was not explicitly shown to participants. (C) On day 2, participants learned seven associations between pairs of the seven stimuli. Four of the associations were different from those learned on day 1 as the position of stimuli 3 and 6 were swapped. A contextual cue was provided using a blue background, a different color from that used on day 1. To learn the associations on day 1 (D) and day 2 (E), participants performed a 3-alternative forced choice task where the appropriate background color was used to provide a contextual cue. (F) Schematic showing protocol used across all 3 days of the experiment. On day 1 and day 2, participants completed phase 1 (Figures S1A and S1B) and at least 5 blocks of phase 2 (Figures 1D and 1E) of the training task. On day 3 of the experiment, participants started with block 1 (“b1”) of the scan task, as shown in Figure 1G, before Magnetic Resonance Spectroscopy (MRS) measurements (“t1”) were taken to estimate baseline measures of 19 different metabolites. Anodal tDCS was then applied for a total of 20 min to induce EI imbalance, with MRS measurements (“t2”) taken during the first 10 min, before block 2 (“b2”) of the scan task commenced. After block 2 of the scan task, a third set of MRS measurements (“t3”) were obtained before participants exited the scanner to perform a surprise memory test. “b” indicates block of fMRI acquisition. “t” indicates time point of MRS acquisition. (G) During the scan task, participants observed pairs of stimuli presented consecutively against either a yellow or blue background. All possible pairs of stimuli were presented in a random order.

Figure 2

The Hippocampus Mediates Memory Interference (A–C) Hippocampal BOLD signal was higher on trials where there was opportunity for memory interference (i.e., when trials include stimuli 3 or 6 that have a different relational position between memory 1 and memory 2; contrast estimated across block 1 and block 2 of the fMRI task, thresholded at p < 0.01 for visualization). Hippocampal BOLD signal was significantly higher in right hippocampus (t₂₃ = 4.34, p = 0.015, FWE peak-corrected using a small-volume correction (SVC) method, (A), while a similar trend was observed in the left hippocampus (t₂₃ = 3.66, p = 0.056, FWE peak-corrected using a SVC method, (B). (C) Hippocampal BOLD signal across both hippocampi, for visualization. (D) After exiting the scanner on day 3, participants performed a surprise memory test. On each trial, participants were presented with a probe stimulus with the background color providing the contextual cue. They were then presented with three option stimuli and were required to choose the stimulus correctly paired with the probe stimulus in the absence of feedback. (E) Memory accuracy on the surprise memory test (mean, ± SEM), for memory 1 (“mem1”) and memory 2 (“mem2”). The more recent associations in memory 2 were remembered more accurately than those in memory 1 (paired t test: t₂₅ = 3.99, p < 0.001). (F) Foil trials on the surprise memory test shown in (D) were identified as those trials where one of the three stimuli was incorrect given the current context but correct in the alternative context. (G) Hippocampal ROI across both right and left hippocampi, used to perform SVC method in (A) and (B), to extract parameter estimates in (H), and to extract activity patterns for Representational Similarity Analysis (RSA) in Figure 3. (H) The hippocampal BOLD response to trials where there was opportunity for memory interference in block 1 (Figure 1F) predicted the number of foil errors, a behavioral index for memory interference, on the post-scan surprise memory test (Pearson’s correlation: r₂₃ = 0.54, p = 0.006, after accounting for differences in learning, see STAR Methods). “a.u.” refers to “arbitrary units.”

Figure 3

Hippocampal Representations Show Evidence for Contextual Pattern Separation, Organized by Relational Overlap For each trial in the scan task, the pattern of BOLD activity across voxels was extracted from the hippocampus (Figure 2G), and representational dissimilarity between all trials containing each of the 7 stimuli was assessed using representational similarity analysis (RSA). For example, representations of stimulus 1 in memory 1 included all pairs of stimuli shown on a yellow background that included stimulus 1 (i.e., 1–1, 1–2, … 1–7). (A) Representational dissimilarity matrix (RDM) showing the average representational dissimilarity between stimuli in memory 1 and memory 2, averaged across all participants, rank transformed and scaled into [0–1] for visualization. (B) The RDM for each participant was correlated with a model RDM shown in Figure S2D to test evidence for pattern separation of hippocampal representations by memory. Across participants, significant representational similarity within memory 1/2 versus between memory 1 and memory 2 was observed (Wilcoxon sign rank test: Z₂₃ = 3.34, p = < 0.001), even if stimuli 3 and 6 were excluded (see Figure S2G). Note: the dissimilarity of a trial to itself was excluded from the analysis. “a.u.” refers to “arbitrary units.” (C) The RDM for each participant was correlated with a model RDM shown in Figure S2E to test evidence for increased representational dissimilarity of stimuli that had different relative position across memory 1 and memory 2 (stimuli 3 and 6). Across participants, significantly greater representational dissimilarity between memory 1 and memory 2 was observed for stimuli 3 and 6 compared to all other stimuli (Wilcoxon sign rank test: Z₂₃ = 2.26, p = 0.024). “a.u.” refers to “arbitrary units.”

Figure 4

Manipulating Neocortical EI Balance using Brain Stimulation A) After the first scan task (block 1) and while participants lay in the scanner, anodal tDCS was applied to the aLOC, with the cathodal electrode placed over the contralateral supraorbital ridge. (B) Previously published data (Barron et al., 2016a) shows re-expression of associative memories during application of anodal tDCS. This aLOC region was the target location for the anodal tDCS electrode in the current experimental protocol. Orientation: neurological. (C) Blue: average location of the MRS voxel across participants. Red: average location of the anodal tDCS electrode across participants, projected into the brain (see STAR Methods). Orientation: neurological. (D) 10mm radius sphere defined around the peak tDCS electrode location for all participants (see STAR Methods), used as a region of interest and for small volume correction. Orientation: neurological. (E) MRS was used to quantify the concentration of GABA relative to total Creatine at three time points indicated in Figure 1F (shown: mean ± SEM). A significant reduction in relative GABA was observed during tDCS (“Before tDCS” – “During tDCS,” t₁₉ = 2.32, p = 0.016). (F) MRS was used to quantify the concentration of glutamate relative to total creatine at three time points indicated in Figure 1F (shown: mean ± SEM). A significant increase in relative glutamate was observed after the second scan-task (“Post-task” – “Before tDCS,” t₁₉ = 2.60, p = 0.018).

Figure 5

Memory Interference for More Remote Memories Increases with Brain Stimulation In all panels, “a.u.” refers to “arbitrary units”; XSS indicates cross-stimulus suppression; “b” indicates block of fMRI acquisition, as shown in Figure 1F; “t” indicates “time point” of MRS measurement acquisition, as shown in Figure 1F. (A) When participants performed the scan task in EI imbalance, we predicted an increase in XSS on trials where participants observed pairs of stimuli that were unassociated in the current context but directly associated in the alternative context, relative to control trials where participants observed pairs of stimuli that were unassociated in both contexts. This difference between control and XSS trials could be measured using the BOLD signal and was used as an index for neural memory interference. (B) Across participants, the decrease in relative GABA concentration observed during tDCS (“Before tDCS” – “During tDCS,” Figure 4E) positively predicted the increase in neural memory interference measured using fMRI cross-stimulus suppression (control – XSS for block 2 – block 1, memory 1 and memory 2) (Spearman correlation: r₁₇ = 0.55, p = 0.021, after accounting for changes in glutamate; see STAR Methods). (C) Across participants, the increase in cross-stimulus suppression used to measure memory interference (control – XSS for block 2 – block 1) positively predicted the percentage of foil errors participants made on the surprise memory test on day 3 (Spearman correlation: r₁₇ = 0.58, p = 0.013, after accounting for differences in learning and changes in relative GABA and glutamate). (D) Across participants, the increase in cross-stimulus suppression used to measure memory interference (control – XSS for block 2 – block 1, Figure 5A) negatively predicted average memory accuracy on the surprise memory test on day 3 (Spearman correlation: r₁₇ = −0.67, p = 0.003, after accounting for differences in learning and changes in relative GABA and glutamate). (E) Within an ROI defined from the peak average tDCS electrode location shown in Figure 4C, extracted parameter estimates for memory 1 (shown: mean ± SEM) revealed a significant increase in the fMRI cross-stimulus suppression measure for memory interference (control – XSS, as shown in (A)) from block 1 to 2 and during block 2 alone (control – XSS for block 2 – block 1: t₂₃ = 3.05, p = 0.006; control – XSS for block 2: t₂₃ = 3.00, p = 0.006). (F) Extracted parameter estimates from (E) split into the control and XSS conditions, as described in (A) (shown: mean ± SEM). (G) T-statistic map for cross-stimulus suppression index for neural memory interference during block 2 between unassociated stimuli in memory 1 that are directly associated in memory 2 relative to pairs of stimuli that are unassociated in both memories (threshold at p < 0.01 uncorrected for visualization). Orientation: neurological. (H) Illustrating the anatomical proximity between the effects shown in Figures 5G (red) and S4G (blue) and previously acquired dataset shown in Figure 4B (green). Orientation: neurological.

Figure 6

Relating Learning Accuracy to Neural Measures of Memory Interference In all panels, “a.u.” refers to “arbitrary units”; XSS indicates cross-stimulus suppression; “b” indicates block of fMRI acquisition, as shown in Figure 1F. (A) Across participants, learning accuracy for memory 2 (on day 2) positively predicted the cross-stimulus suppression index for neural memory interference (Spearman correlation: r₁₇ = 0.68, p = 0.003). (B) Across participants, learning accuracy for memory 1 (on day 1) showed a negative trend with the cross-stimulus suppression index for neural memory interference (Spearman correlation: r₁₇ = −0.47, p = 0.053). (C) During application of anodal tDCS in the second scan task (block 2, “b2”), the hippocampal BOLD response to trials where there was opportunity for memory interference did not predict behavioral measures of memory interference (Pearson correlation: r₂₃ = −0.06, p = 0.764). (D) Both groups of participants (see STAR Methods) who received tDCS (“MRI” and “tDCS”) showed higher normalized foil errors on the surprise memory test on day 3, relative to participants who received no intervention (“Behav”) (two-sample t test: t₄₄ = 2.89, p = 0.006) (shown: mean ± SEM). However, there was no difference in the percentage of foil errors made by participants who received tDCS and “Sham” (two-sample t test: t₃₈ = 0.66, p = 0.515). Normalized foil errors were defined as the percentage of foil errors on foil trials, after subtracting the percentage of non-foil errors on foil trials.