Using High Spatial Resolution to Improve BOLD fMRI Detection at 3T

Abstract

For different functional magnetic resonance imaging experiments using blood oxygenation level-dependent (BOLD) contrast, the acquisition of T2*-weighted scans at a high spatial resolution may be advantageous in terms of time-course signal-to-noise ratio and of BOLD sensitivity when the regions are prone to susceptibility artifacts. In this study, we explore this solution by examining how spatial resolution influences activations elicited when appetizing food pictures are viewed. Twenty subjects were imaged at 3 T with two different voxel volumes, 3.4 μl and 27 μl. Despite the diminution of brain coverage, we found that high-resolution acquisition led to a better detection of activations. Though known to suffer to different degrees from susceptibility artifacts, the activations detected by high spatial resolution were notably consistent with those reported in published activation likelihood estimation meta-analyses, corresponding to taste-responsive regions. Furthermore, these regions were found activated bilaterally, in contrast with previous findings. Both the reduction of partial volume effect, which improves BOLD contrast, and the mitigation of susceptibility artifact, which boosts the signal to noise ratio in certain regions, explained the better detection noted with high resolution. The present study provides further evidences that high spatial resolution is a valuable solution for human BOLD fMRI, especially for studying food-related stimuli.

Fig 1. Graphical outline of the stimulation protocol used in this fMRI experiment.

Stimuli were presented according to a block design involving food-related and non-food-related blocks. During the presentation of food images, participants were asked to imagine the taste of the viewed food, as if they were actually eating it. Each image was separated by a fixation cross and a rest period was placed between two blocks.

Fig 2. Masks showing the voxels contributing to the group analysis for the two conditions.

Fig 3. Group statistical parametric maps for the comparison of significantly activated regions detected under LR and HR conditions for the contrast between viewing food and non-food pictures.

Activations were successively shown in the OFC (y = 35/39), anterior insula (y = 3/6), amygdala (y = 0) and insula (y = -5/-9) using a voxel-wise p<0.001 uncorrected threshold, with an extent threshold of 5 voxels (neurologic orientation, right-on-right). Under such conditions, the activations observable in the left amygdala and right OFC with LR do not resist to the Q _FDR < 0.05 threshold used in Table 2.