Implementation considerations for deep learning with diffusion MRI streamline tractography
Cai, L. Y.; Lee, H. H.; Newlin, N. R.; Kim, M. E.; Moyer, D.; Rheault, F.; Schilling, K. G.; Landman, B. A.
Show abstract
One area of medical imaging that has recently experienced innovative deep learning advances is diffusion MRI (dMRI) streamline tractography with recurrent neural networks (RNNs). Unlike traditional imaging studies which utilize voxel-based learning, these studies model dMRI features at points in continuous space off the voxel grid in order to propagate streamlines, or virtual estimates of axons. However, implementing such models is nontrivial, and an open-source implementation is not yet widely available. Here, we describe a series of considerations for implementing tractography with RNNs and demonstrate they allow one to approximate a deterministic streamline propagator with comparable performance to existing algorithms. We release this trained model and the associated implementations leveraging popular deep learning libraries. We hope the availability of these resources will lower the barrier of entry into this field, spurring further innovation.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Stacked regressions and structured variance partitioning for interpretable brain maps 94%
- Using Mesoscopic Tract-Tracing Data to Guide the Estimation of Fiber Orientation Distributions in the Mouse Brain from Diffusion MRI 94%
- Classifyber, a robust streamline-based linear classifier for white matter bundle segmentation 94%
Similar papers in this journal
- Self-supervised segmentation and characterization of fiber bundles in anatomic tracing data 95%
- Enhancement of brain atlases with laminar coordinate systems: Flatmaps and barrel column annotations 95%
- Implicit Neural Representation of Multi-shell Constrained Spherical Deconvolution for Continuous Modeling of Diffusion MRI 94%
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.