# StreamNet: A WAE for White Matter Streamline Analysis

arXiv: https://arxiv.org/abs/2209.01498 · HTML: https://mlsanity.com/paper/2209.01498/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 3 Sep 2022.

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Wasserstein Auto-Encoders](https://mlsanity.com/paper/1711.01558/) (2017)
- [Learning with a Wasserstein Loss](https://mlsanity.com/paper/1506.05439/) (2015)
- [Kernel Operations on the GPU, with Autodiff, without Memory Overflows](https://mlsanity.com/paper/2004.11127/) (2020)
- [Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance](https://mlsanity.com/paper/1805.11897/) (2018)
- [Filtering in tractography using autoencoders (FINTA)](https://mlsanity.com/paper/2010.04007/) (2020)
- [Alignment of Tractography Streamlines using Deformation Transfer via Parallel Transport](https://mlsanity.com/paper/2108.03697/) (2021)

## Built on by (most cited first, 2 of 2)

- [Understanding Galaxy Morphology Evolution Through Cosmic Time via Redshift Conditioned Diffusion Models](https://mlsanity.com/paper/2411.18440/) (2024)
- [Differentiable VQ-VAE's for Robust White Matter Streamline Encodings](https://mlsanity.com/paper/2311.06212/) (2023)

## Abstract (arXiv)

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.