The fully automated PIANO™ pipeline for vertexwise shape analysis of subcortical structures was used to investigate PD, Prodromal and control populations. The registered anatomical images can be used to extract the outer surface of subcortical structures and compute vertexwise maps of the nonlinear deformations along the surface normal.
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, linear spatial transformation to “stereotaxic space”, and nonlinear transformation to a pre-defined “template space”.
- Computation of the nonlinear deformation fields associated with the spatial transformation to the template space.
- Specific Volume of Interests (VOIs) were defined anatomically, explicitly on a template, or generated implicitly using a deep-learning model, and were combined with subject-specific tissue classification as needed.
- The outer surfaces of the several VOIs, including the Thalamus, Hippocampus, Caudate, Putamen and Midbrain were automatically extracted using the Marching Cubes algorithm.
- The local deformation on the surfaces was quantified with the projection of the nonlinear template-to-subject transformation onto the normal vector to the template surface.
- Vertexwise shape analysis of the subcortical VOIs was derived from the underlying deformation maps along the normal to the outer surfaces.