Can point cloud networks learn statistical shape models of anatomies?
This work addresses the challenge of making SSM more accessible for medical imaging applications by leveraging point cloud deep learning, though it is incremental as it builds on existing networks.
The authors tackled the problem of constructing Statistical Shape Models (SSM) from unordered 3D point clouds, which are easier to acquire than traditional geometric proxies, by demonstrating that existing point cloud encoder-decoder networks can capture population-level statistical representations while reducing inference burden and relaxing input requirements.
Statistical Shape Modeling (SSM) is a valuable tool for investigating and quantifying anatomical variations within populations of anatomies. However, traditional correspondence-based SSM generation methods have a prohibitive inference process and require complete geometric proxies (e.g., high-resolution binary volumes or surface meshes) as input shapes to construct the SSM. Unordered 3D point cloud representations of shapes are more easily acquired from various medical imaging practices (e.g., thresholded images and surface scanning). Point cloud deep networks have recently achieved remarkable success in learning permutation-invariant features for different point cloud tasks (e.g., completion, semantic segmentation, classification). However, their application to learning SSM from point clouds is to-date unexplored. In this work, we demonstrate that existing point cloud encoder-decoder-based completion networks can provide an untapped potential for SSM, capturing population-level statistical representations of shapes while reducing the inference burden and relaxing the input requirement. We discuss the limitations of these techniques to the SSM application and suggest future improvements. Our work paves the way for further exploration of point cloud deep learning for SSM, a promising avenue for advancing shape analysis literature and broadening SSM to diverse use cases.