Differentiable VQ-VAE's for Robust White Matter Streamline Encodings
This addresses a limitation in neuroimaging analysis for researchers, though it is incremental as it builds on existing VQ-VAE methods.
The paper tackles the problem of encoding entire bundles of white matter streamlines, rather than single fibers, to preserve global geometric structure, and proposes a Differentiable VQ-VAE that achieves superior performance in encoding and synthesis compared to state-of-the-art autoencoders.
Given the complex geometry of white matter streamlines, Autoencoders have been proposed as a dimension-reduction tool to simplify the analysis streamlines in a low-dimensional latent spaces. However, despite these recent successes, the majority of encoder architectures only perform dimension reduction on single streamlines as opposed to a full bundle of streamlines. This is a severe limitation of the encoder architecture that completely disregards the global geometric structure of streamlines at the expense of individual fibers. Moreover, the latent space may not be well structured which leads to doubt into their interpretability. In this paper we propose a novel Differentiable Vector Quantized Variational Autoencoder, which are engineered to ingest entire bundles of streamlines as single data-point and provides reliable trustworthy encodings that can then be later used to analyze streamlines in the latent space. Comparisons with several state of the art Autoencoders demonstrate superior performance in both encoding and synthesis.