This illustration provides a high level overview of the various steps involved in PIANO™, our automated structural MRI processing "pipeline". PIANO™ is a configurable, modular, pipeline-based system for fully-automated processing of multi-modality images. PIANO™ is designed for high-throughput processing of large-scale, multi-center, neuroimaging data. Briefly 3D T1-weighted MRI scans underwent:

• Image non-uniformity correction using the N3 algorithm, brain masking, and linear spatial transformation to “stereotaxic space”.
• Exploratory, voxelwise deformation-based morphometry (DBM) analysis generated from the nonlinear deformation fields associated with the spatial transformation.
• The stereotaxic volumes were segmented into gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) using an internally-trained deep-learning model.
• Voxelwise analysis of the gray matter density was derived from the underlying normalized T1-weighted images in combination with the tissue classification.
• Regional volume-based morphometry was then performed on pre-defined ROIs. Specific ROIs were defined anatomically, explicitly on a template, or generated implicitly using a deep-learning model (hippocampus), and were combined with subject-specific tissue classification, as needed.