Multimodal Integration and Vividness in the Angular Gyrus During Episodic Encoding and Retrieval

Abstract

Much evidence suggests that the angular gyrus (AnG) is involved in episodic memory, but its precise role has yet to be determined. We examined two possible accounts within the same experimental paradigm: the "cortical binding of relational activity" (CoBRA) account (Shimamura, 2011), which suggests that the AnG acts as a convergence zone that binds multimodal episodic features, and the subjectivity account (Yazar et al., 2012), which implicates AnG involvement in subjective mnemonic experience (such as vividness or confidence). fMRI was used during both encoding and retrieval of paired associates. During study, female and male human participants memorized picture-pairs of common objects (in the unimodal task) or of an object-picture and an environmental sound (in the crossmodal task). At test, they performed a cued-recall task and further indicated the vividness of their memory. During retrieval, BOLD activation in the AnG was greatest for vividly remembered associates, consistent with the subjectivity account. During encoding, the same effect of vividness was found, but this was further modulated by task: greater activations were associated with subsequent recall in the crossmodal than the unimodal task. Therefore, encoding data suggest an additional role to the AnG in crossmodal integration, consistent with its role at retrieval proposed by CoBRA. These results resolve some of the puzzles in the literature and indicate that the AnG can play different roles during encoding and retrieval as determined by the cognitive demands posed by different mnemonic tasks.SIGNIFICANCE STATEMENT We offer new insights into the multiplicity of processes that are associated with angular gyrus (AnG) activation during encoding and retrieval of newly formed memories. We used fMRI while human participants learned and subsequently recalled pairs of objects presented to the same sensory modality or to different modalities. We were able to show that the AnG is involved when vivid memories are created and retrieved, as well as when encoded information is integrated across different sensory modalities. These findings provide novel evidence for the contribution of the AnG to our subjective experience of remembering alongside its role in integrative processes that promote subsequent memory.

Keywords: angular gyrus; cued recall; episodic memory; multimodal integration; vividness.

Figure 1.

Schematic illustration of the scanned part of the experimental paradigm. During the study phase, participants generated an association between a picture and a sound (in the crossmodal task; left) or between two pictures (in the unimodal task; right), with different tasks on different days. There were 120 stimulus pairs in total, 80 seen for the first time in the study phase (“nonrepeated”) and 40 seen twice before in a separate phase outside the scanner (“repeated”; see Materials and Methods). In the test phase, a cue picture was presented and participants recalled the associated sound (in the crossmodal task) or picture (in the unimodal task). Use of the same stimuli in both tasks is for illustrative purposes: in reality, each stimulus was only used in one task.

Figure 2.

Number of responses for each response type in the crossmodal task (dark gray) and the unimodal task (light gray). Error bars indicate SEs for each condition separately. ***p < 0.001.

Figure 3.

Contrasts of beta values of the fitted model in the AnG (collapsed across left and right AnG). Each plot represents a planned contrast: the CoBRA account (left; greater recall success effect for crossmodal than unimodal) and the subjectivity account (right; linear trend of vivid > nonvivid > fail) during study (top) and test (bottom). Error bars represent Satterthwaite approximation of the pooled SE and were computed for each condition separately. **p < 0.01; ***p < 0.005.

Figure 4.

Brain regions showing stronger BOLD response for successful versus failure recall at study (left) and test (right). p < 0.05 FWE cluster-level corrected with voxel-level threshold at p < 0.0001 (uncorrected). Data are shown on sagittal, coronal, and axial slices of the group-averaged brain (n = 21).