StreamNet: A WAE for White Matter Streamline Analysis

Andrew Lizarraga, Katherine L. Narr, Kirsten A. Donals, Shantanu H. Joshi
Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis, PMLR 194:172-182, 2022.

Abstract

We present StreamNet, an autoencoder architecture for the analysis of the highly heterogeneous geometry of large collections of white matter streamlines. This proposed framework takes advantage of geometry-preserving properties of the Wasserstein-1 metric in order to achieve direct encoding and reconstruction of entire bundles of streamlines. We show that the model not only accurately captures the distributive structures of streamlines in the population, but is also able to achieve superior reconstruction performance between real and synthetic streamlines. Experimental model performance is evaluated on white matter streamlines resulting from $T1$-weighted diffusion imaging of $40$ healthy controls using recent state of the art bundle comparison metric that measures fiber-shape similarities.

Cite this Paper


BibTeX
@InProceedings{pmlr-v194-lizarraga22a, title = {StreamNet: A WAE for White Matter Streamline Analysis}, author = {Lizarraga, Andrew and Narr, Katherine L. and Donals, Kirsten A. and Joshi, Shantanu H.}, booktitle = {Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis}, pages = {172--182}, year = {2022}, editor = {Bekkers, Erik and Wolterink, Jelmer M. and Aviles-Rivero, Angelica}, volume = {194}, series = {Proceedings of Machine Learning Research}, month = {18 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v194/lizarraga22a/lizarraga22a.pdf}, url = {https://proceedings.mlr.press/v194/lizarraga22a.html}, abstract = {We present StreamNet, an autoencoder architecture for the analysis of the highly heterogeneous geometry of large collections of white matter streamlines. This proposed framework takes advantage of geometry-preserving properties of the Wasserstein-1 metric in order to achieve direct encoding and reconstruction of entire bundles of streamlines. We show that the model not only accurately captures the distributive structures of streamlines in the population, but is also able to achieve superior reconstruction performance between real and synthetic streamlines. Experimental model performance is evaluated on white matter streamlines resulting from $T1$-weighted diffusion imaging of $40$ healthy controls using recent state of the art bundle comparison metric that measures fiber-shape similarities.} }
Endnote
%0 Conference Paper %T StreamNet: A WAE for White Matter Streamline Analysis %A Andrew Lizarraga %A Katherine L. Narr %A Kirsten A. Donals %A Shantanu H. Joshi %B Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis %C Proceedings of Machine Learning Research %D 2022 %E Erik Bekkers %E Jelmer M. Wolterink %E Angelica Aviles-Rivero %F pmlr-v194-lizarraga22a %I PMLR %P 172--182 %U https://proceedings.mlr.press/v194/lizarraga22a.html %V 194 %X We present StreamNet, an autoencoder architecture for the analysis of the highly heterogeneous geometry of large collections of white matter streamlines. This proposed framework takes advantage of geometry-preserving properties of the Wasserstein-1 metric in order to achieve direct encoding and reconstruction of entire bundles of streamlines. We show that the model not only accurately captures the distributive structures of streamlines in the population, but is also able to achieve superior reconstruction performance between real and synthetic streamlines. Experimental model performance is evaluated on white matter streamlines resulting from $T1$-weighted diffusion imaging of $40$ healthy controls using recent state of the art bundle comparison metric that measures fiber-shape similarities.
APA
Lizarraga, A., Narr, K.L., Donals, K.A. & Joshi, S.H.. (2022). StreamNet: A WAE for White Matter Streamline Analysis. Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis, in Proceedings of Machine Learning Research 194:172-182 Available from https://proceedings.mlr.press/v194/lizarraga22a.html.

Related Material