Complementary topology of maintenance and manipulation brain networks in working memory

Abstract

AbstractWorking memory (WM) is assumed to consist of a process that sustains memory representations in an active state (maintenance) and a process that operates on these activated representations (manipulation). Prior fMRI studies have examined maintenance and manipulation in separate task conditions, whereas in real life these processes operate simultaneously. In the current study, the neural mechanisms of maintenance and manipulation were disentangled during the same task by parametrically varying these processes. During fMRI, participants maintained consonant letters in WM while sorting them in alphabetical order. Maintenance was investigated by varying the number of letters held in WM and manipulation by varying the number of moves required to sort the list alphabetically. The study yielded three main findings. First, the degree of both maintenance and manipulation demand had significant effects on behavior that were associated with different cortical regions: maintenance was associated with bilateral prefrontal and left parietal cortex, and manipulation with right parietal activity, a link that is consistent with the role of parietal cortex in symbolic computations. Second, univariate fMRI and tractography based on diffusion-weighted imaging showed that maintenance and manipulation regions are supported by two dissociable structural networks. Finally, maintenance and manipulation functional networks became increasingly segregated with increasing demand, possibly reflecting the protection of information held in WM from interference generated by manipulation operations. These results represent a novel approach to study the brain as an adaptive system that coordinates multiple ongoing cognitive processes.Significance StatementDespite the importance of working memory (WM) in everyday life, little is known about how the brain is able to simultaneously maintain and manipulate information stored in short-term memory buffers. We examined evidence for two distinct, concurrent cognitive functions supporting maintenance and manipulation abilities by testing brain activity as participants performed a WM alphabetization task. We found behavioral and neural evidence in support of dissociable cognitive functions associated with these two operations. Furthermore, we found that connectivity between these networks was increasingly segregated as difficulty increased, and that this effect was positively related to individual WM ability. These results provide evidence that network segregation may act as a protective mechanism to enable successful performance under increasing WM demand.