Perceived and mentally rotated contents are differentially represented in cortical depth of V1

Abstract

Primary visual cortex (V1) in humans is known to represent both veridically perceived external input and internally-generated contents underlying imagery and mental rotation. However, it is unknown how the brain keeps these contents separate thus avoiding a mixture of the perceived and the imagined which could lead to potentially detrimental consequences. Inspired by neuroanatomical studies showing that feedforward and feedback connections in V1 terminate in different cortical layers, we hypothesized that this anatomical compartmentalization underlies functional segregation of external and internally-generated visual contents, respectively. We used high-resolution layer-specific fMRI to test this hypothesis in a mental rotation task. We found that rotated contents were predominant at outer cortical depth bins (i.e. superficial and deep). At the same time perceived contents were represented stronger at the middle cortical bin. These results identify how through cortical depth compartmentalization V1 functionally segregates rather than confuses external from internally-generated visual contents. These results indicate that feedforward and feedback manifest in distinct subdivisions of the early visual cortex, thereby reflecting a general strategy for implementing multiple cognitive functions within a single brain region.

Fig. 1. Experimental methods.

A On each trial, participants viewed a sample grating and then had 6 seconds to rotate it 60° (<, >) or 120° (≪, ≫) to the left or to the right. After the mental rotation interval, participants had 2 seconds to report whether a probe grating was tilted clockwise or counterclockwise compared to the mentally rotated grating. B We used a set of three stimuli, 15°, 75°, and 135° oriented gratings. As a result of the mental rotation, each stimulus could be turned into one of the other two stimuli. For example, rotation of a 15° grating (red arrow) for 60° clockwise results in a 75° grating or rotation of a 135° grating (blue arrow) 120° counterclockwise results in a 15° grating. C This panel shows classifiers’ decisions in an example trial, in which a 15° grating was rotated into a 75° grating. We aggregated results across trials by counting how often classifiers predicted the presented orientation, the rotated orientation, and the unused orientation. The shaded area denotes the time interval chosen for the in-depth analysis (measurements at 8 and 10 seconds).

Fig. 2. Results.

A Coronal, axial, and sagittal slices of the average EPI image of a representative participant, overlaid with cortical depth bins approximating cortical layers (superficial, middle, and deep) from an equi-volume model (see Methods). The cortex is mapped within the region of V1 with voxel eccentricity values 0–3°. B Classifier decisions in V1 over the time interval measured at 8 and 10 seconds after the rotation onset for the presented, mentally rotated and unused gratings in the outer cortical bins (average of the superficial and deep bin) and the middle cortical bin (N = 23 participants; see Supplementary Fig. 3 for detailed analysis within an extended time interval and Supplementary Fig. 4 for analyses across all time points). Perceptual contents were more strongly represented at the middle cortical depth, whereas mentally rotated contents were dominant at the outer cortical bin. C Comparing classifier decisions between all three cortical bins (superficial vs. middle vs. deep) reveals that the difference between perceived and rotated contents is most pronounced between the middle and superficial depths. All error bars denote standard error of mean over subjects. ⁺p < 0.09, *p < 0.05, **p < 0.01, ***p < 0.001.