Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 May:2024:10.1109/isbi56570.2024.10635543.
doi: 10.1109/isbi56570.2024.10635543. Epub 2024 Aug 22.

DIFFERENTIABLE VQ-VAE'S FOR ROBUST WHITE MATTER STREAMLINE ENCODINGS

Andrew Lizarraga  1 , Brandon Taraku  2 , Edouardo Honig  1 , Ying Nian Wu  1 , Shantanu H Joshi  2   3
Affiliations

DIFFERENTIABLE VQ-VAE'S FOR ROBUST WHITE MATTER STREAMLINE ENCODINGS

Andrew Lizarraga et al. Proc IEEE Int Symp Biomed Imaging. 2024 May.

Abstract

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.

Keywords: Differentiable; Diffusion Tractography; Gumbel Distribution; Streamlines; Vector Quantization.

PubMed Disclaimer

Figures

Fig. 2.1
Fig. 2.1
Schematic of the VQ-Diff Architecture.
Fig. 3.1
Fig. 3.1
Full subject reconstructions across architectures.
Fig. 3.2
Fig. 3.2
Visualization of the latent space.
Fig. 3.3
Fig. 3.3
Latent perturbations around the mean for the MCP bundle.
See this image and copyright information in PMC

References

    1. Zhong Shenjun, Chen Zhaolin, and Egan Gary, “Autoencoded Latent Representations of White Matter Streamlines for Quantitative Distance Analysis,” Neuroinformatics, vol. 20, no. 4, pp. 1105–1120, Oct 2022. - PMC - PubMed
    1. Lizarraga Andrew, Narr Katherine L., Donalds Kirsten A., and Joshi Shantanu H., “StreamNet: A WAE for White Matter Streamline Analysis,” in Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis, Erik Bekkers, Jelmer M. Wolterink, and Angelica Aviles-Rivero, Eds. 18 Nov 2022, vol. 194 of Proceedings of Machine Learning Research, pp. 172–182, PMLR.
    1. Chandio Bramsh Qamar, Chattopadhyay Tamoghna, Owens-Walton Conor, Villalon Reina Julio E., Nabulsi Leila, Thomopoulos Sophia I., Garyfallidis Eleftherios, and Thompson Paul M., “FiberNeat: Unsupervised White Matter Tract Filtering,” in 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2022, pp. 5055–5061. - PubMed
    1. Kingma Diederik P. and Welling Max, “Auto-Encoding Variational Bayes,” in 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14–16, 2014, Conference Track Proceedings, Bengio Yoshua and LeCun Yann, Eds., 2014.
    1. Feng Yixue, Chandio Bramsh Q, Thomopoulos Sophia I, Chattopadhyay Tamoghna, and Thompson Paul M, “Variational autoencoders for generating synthetic tractography-based bundle templates in a low-data setting,” bioRxiv, pp. 2023–02, 2023. - PubMed

LinkOut - more resources