Mouse Brain Extractor: Brain segmentation of mouse MRI using global positional encoding and SwinUNETR

In spite of the great progress that has been made towards automating brain extraction in human magnetic resonance imaging (MRI), challenges remain in the automation of this task for mouse models of brain disorders. Researchers often resort to editing brain segmentation results manually when automated methods fail to produce accurate delineations. However, manual corrections can be labor-intensive and introduce interrater variability. This motivated our development of a new deep-learning-based method for brain segmentation of mouse MRI, which we call Mouse Brain Extractor. We adapted the existing SwinUNETR architecture (Hatamizadeh et al., 2021) with the goal of making it more robust to scale variance. Our approach is to supply the network model with supplementary spatial information in the form of absolute positional encoding. We use a new scheme for positional encoding, which we call Global Positional Encoding (GPE). GPE is based on a shared coordinate frame that is relative to the entire input image. This differs from the positional encoding used in SwinUNETR, which solely employs relative pairwise image patch positions. GPE also differs from the conventional absolute positional encoding approach, which encodes position relative to a subimage rather than the entire image. We trained and tested our method on a heterogeneous dataset of N=223 mouse MRI, for which we generated a corresponding set of manually-edited brain masks. These data were acquired previously in other studies using several different scanners and imaging protocols and included