Unsupervised Diffeomorphic Surface Registration and Non-Linear Modelling
This addresses the need for efficient and generalizable surface registration in medical imaging, though it is incremental as it builds on existing deep learning and deformation modeling techniques.
The paper tackles the problem of 3D surface registration in medical image analysis by proposing a one-step model using conditional variational autoencoders with diffeomorphic constraints, achieving competitive performance with higher compactness and improved generalisability compared to iterative and linear methods.
Registration is an essential tool in image analysis. Deep learning based alternatives have recently become popular, achieving competitive performance at a faster speed. However, many contemporary techniques are limited to volumetric representations, despite increased popularity of 3D surface and shape data in medical image analysis. We propose a one-step registration model for 3D surfaces that internalises a lower dimensional probabilistic deformation model (PDM) using conditional variational autoencoders (CVAE). The deformations are constrained to be diffeomorphic using an exponentiation layer. The one-step registration model is benchmarked against iterative techniques, trading in a slightly lower performance in terms of shape fit for a higher compactness. We experiment with two distance metrics, Chamfer distance (CD) and Sinkhorn divergence (SD), as specific distance functions for surface data in real-world registration scenarios. The internalised deformation model is benchmarked against linear principal component analysis (PCA) achieving competitive results and improved generalisability from lower dimensions.