X-ray super-resolution assessment via spatial filtering

Abstract

A technique is disclosed for analyzing and displaying the extent to which the images and structures inferred by a physically seeded multiscale network correspond to genuine resolution improvement and the extent to which they correspond to the hallucination of realistic looking structures. A selected reconstruction generated using a trained neural network is compared against a baseline representation (e.g., a baseline reconstruction) by calculating image similarity metrics between progressing spatially filtered versions of selected reconstruction. As the amount of spatial filtering increases, at some point the image similarity metrics will reach an extrema (e.g., a lowest distance between the images). At that extrema, the parameter(s) of the spatial filter can be used to identify a resolution score (e.g., a length scale) associated with that extrema. The resolution score is indicative of an amount of resolution recovery associated with the trained neural network with respect to the baseline.