The bottom-up information transfer process and top-down attention control underlying tonal working memory

Abstract

Tonal working memory has been less investigated by neuropsychological and neuroimaging studies and even less in terms of tonal working memory load. In this study, we analyzed the dynamic cortical processing process of tonal working memory with an original surface-space-based multivariate pattern analysis (sf-MVPA) method and found that this process constituted a bottom-up information transfer process. Then, the local cortical activity pattern, local cortical response strength, and cortical functional connectivity under different tonal working memory loads were investigated. No brain area's local activity pattern or response strength was significantly different under different memory loads. Meanwhile, the interactions between the auditory cortex (AC) and an attention control network were linearly correlated with the memory load. This finding shows that the neural mechanism underlying the tonal working memory load does not arise from changes in local activity patterns or changes in the local response strength, but from top-down attention control. Our results indicate that the implementation of tonal working memory is based on the cooperation of the bottom-up information transfer process and top-down attention control.

Keywords: attention; cortical activation pattern; functional connectivity; sf-MVPA; tonal working memory load.

FIGURE 1

Experimental procedure and behavioral results. (A) A sequence of piano tones (1–4 tones) was presented to subjects and after 20 s, another sequence of tones (same length) was presented. Subjects must answer whether these two sequences are the same. There were five conditions in total. Condition 0 referred to the control task, during which no sequence was presented and subjects had to answer “same” in the answer period. (B) Accuracy of the answers under different memory loads.

FIGURE 2

The analysis stream of sf-MVPA. (A) Double radius dividing method. We used this method to divide the template of fsaverage into labels as evenly as possible. Dividing was implemented according to the numerical order of the vertices. For a vertex (e.g., points A, D, and E) that was not grouped into a label, the vertices whose distances from the vertex were shorter than r were grouped into a label and painted green. The vertices whose distances from the vertex were longer than r but shorter than R (R = 2r) were painted yellow. For vertices that were painted color (e.g., points B and C) by the painting process of the former vertices, the painting and grouping process was forbidden. The large circle guarantees that the labels will not overlap. After the iteration process, the vertices painted yellow were grouped into the nearest label. (B) Searchlight on the surface space. The grid on the surface represents the labels. The yellow circle represents the searchlight. (C) The frame-by-frame training and classification process. The hexagons represent labels and the color on them represents the averaged strength of BOLD signal.

FIGURE 3

Sf-MVPA analysis results of 1–11 s and BOLD curves of 6 ROIs. (A) The sf-MVPA results of 1–11 s of tonal working memory vs. control task. (B) Average BOLD curves of 3 ROIs in the left hemisphere. (C) Average BOLD curves of 3 ROIs in the right hemisphere. AC, auditory cortex.

FIGURE 4

Sf-MVPA analysis results of 12–21 s and BOLD curves of 6 ROIs. (A) The sf-MVPA results of 12–21 s of tonal working memory vs. control task. (B) Average BOLD curves of 3 ROIs in the left hemisphere. (C) Average BOLD curves of 3 ROIs in the right hemisphere. AC, auditory cortex; PCG, precentral gyrus; SMA, supplementary motor area.

FIGURE 5

Bottom-up information transfer process and top-down attention control network during tonal working memory. (A) The information transfer process during tonal working memory. (B) The attention control network during tonal working memory. PCG, precentral gyrus; AC, auditory cortex; IPL, inferior parietal lobule; SMA, supplementary motor area; PFC, prefrontal cortex; PCC, posterior cingulate cortex; PCUN, precuneus.

FIGURE 6

Names and locations and regression analysis results of neural response strength of 12 ROIs. No brain area’s response strength was linearly correlated with memory load. AC, auditory cortex; PCG, precentral gyrus; SMA, supplementary motor area.

FIGURE 7

Results of functional connectivity analysis. (A) Brain areas whose functional connectivity strength with ROIs in the left hemisphere was linearly correlated with memory load. (B) Brain areas whose functional connectivity strength with ROIs in the right hemisphere was linearly correlated with memory load. AC, auditory cortex; PFC, prefrontal cortex; PCUN, precuneus; PCC, posterior cingulate cortex.