Local opposite orientation preferences in V1: fMRI sensitivity to fine-grained pattern information

Abstract

The orientation of a visual grating can be decoded from human primary visual cortex (V1) using functional magnetic resonance imaging (fMRI) at conventional resolutions (2-3 mm voxel width, 3T scanner). It is unclear to what extent this information originates from different spatial scales of neuronal selectivity, ranging from orientation columns to global areal maps. According to the global-areal-map account, fMRI orientation decoding relies exclusively on fMRI voxels in V1 exhibiting a radial or vertical preference. Here we show, by contrast, that 2-mm isotropic voxels in a small patch of V1 within a quarterfield representation exhibit reliable opposite selectivities. Sets of voxels with opposite selectivities are locally intermingled and each set can support orientation decoding. This indicates that global areal maps cannot fully account for orientation information in fMRI and demonstrates that fMRI also reflects fine-grained patterns of neuronal selectivity.

Figure 1

Coarse-scale neural effects can give rise to spurious high-spatial frequency fMRI pattern information in the presence of a high-spatial frequence gain field across voxels. An illustration of how differences in sensitivity to local activation across voxels (the voxel gain field) can lead to spurious high-spatial- frequency information in fMRI patterns. The left column shows the effect of a gain field on a coarse scale homogenous effect and the right column shows the effect of gain field on a fine-grained heterogeneous effect. An important property of the gain field effect is that the signs of the true activation effects are preserved. Spatial filtering analyses will suggest high-spatial frequency information in either scenario (left and right). However, the signature of a fine-grained heterogeneous effect (right) is the presence of local opposite selectivities (right only). Note that in actual data the sign of effects can be inverted by fMRI noise; this effect is not illustrated in this figure.

Figure 2

Opposite orientation preferences intermingle within quarterfield patches in V1. (a) A visualization of how fMRI voxels were labeled as preferring radial and tangential orientation. The contrast t maps indicate the activation difference between the two displayed visual gratings. Activation is only shown for the four within-quarterfield ROIs, which are labeled clockwise from 1 to 4. Positive and negative t-values indicate either a radial or a tangential preference depending on the visual field they are in. This we have clarified by labeling local activation clusters with 0 and X when they have a tangential and radial preference respectively. Note that the activation map is unthresholded and that no inferences are made based on it. (b) Histograms showing the distribution of V1 voxels that prefer radial vs tangential orientation (left) and vertical vs horizontal orientation (right). These plots are based on all voxels in all four quarterfield ROIs across all participants. (c) A visualization of the proportion of V1 voxels preferring radial orientation (left, red), tangential orientation (left, blue), vertical orientation (right, red) and horizontal orientation (right, blue) across subjects and quarterfield ROIs.

Figure 3

Tangential and horizontal orientation preferences on their own allow for robust orientation decoding. (a) Bar plots summarizing grating orientation (left) and spiral sense (right) decodability when selecting all voxels (gray bars), voxel preferring radial/vertical preference (red bars) and voxel preferring tangential/horizontal preference (blue bars). (b) Bar plots summarizing how grating orientation (left) and spiral sense (right) decodability is affected by spatially shifting test patterns by 1, 2, 4 and 6 mm.

Figure 4

Tangential and horizontal orientation preference strength across V1 voxels replicates from training to test data. (a) Bar plots summarizing the average correlation between orientation preference strength across V1 voxels between training and testing data - using leave-one-subrun out cross-validation. Preference replicability is shown for all quarterfield ROIs combined (grey bars) for radial, tangential, vertical and horizontal orientation (left to right). In addition, preference replicability is shown separately for the four quarterfield ROIs (blue-green bars) and separately for the three eccentricity ROIs (yellow-red bars). Error bars depict the 95% confidence intervals based on bootstrap resampling (10.000) of the participant set.