Resolution- and Stimulus-agnostic Super-Resolution of Ultra-High-Field Functional MRI: Application to Visual Studies
This work addresses the challenge of high-resolution fMRI acquisition times for neuroscience researchers, offering a versatile tool that is incremental in applying super-resolution to fMRI.
The authors tackled the problem of long scan times in high-resolution fMRI by introducing a deep learning-based 3D super-resolution method that adapts to varying voxel sizes without retraining, enabling visualization of fine-scale motion-selective sites from lower resolution data and potentially reducing acquisition time.
High-resolution fMRI provides a window into the brain's mesoscale organization. Yet, higher spatial resolution increases scan times, to compensate for the low signal and contrast-to-noise ratio. This work introduces a deep learning-based 3D super-resolution (SR) method for fMRI. By incorporating a resolution-agnostic image augmentation framework, our method adapts to varying voxel sizes without retraining. We apply this innovative technique to localize fine-scale motion-selective sites in the early visual areas. Detection of these sites typically requires a resolution higher than 1 mm isotropic, whereas here, we visualize them based on lower resolution (2-3mm isotropic) fMRI data. Remarkably, the super-resolved fMRI is able to recover high-frequency detail of the interdigitated organization of these sites (relative to the color-selective sites), even with training data sourced from different subjects and experimental paradigms -- including non-visual resting-state fMRI, underscoring its robustness and versatility. Quantitative and qualitative results indicate that our method has the potential to enhance the spatial resolution of fMRI, leading to a drastic reduction in acquisition time.