# DeepTract: A Probabilistic Deep Learning Framework for White Matter Fiber Tractography

## TL;DR

DeepTract introduces a deep learning framework that estimates white matter fiber orientations from diffusion weighted images without relying on predefined diffusion models, enabling both deterministic and probabilistic tractography.

## Contribution

It presents a novel recurrent neural network-based approach for fiber reconstruction that is data-driven and model-agnostic, outperforming traditional methods in certain evaluations.

## Key findings

- Competitive performance with state-of-the-art algorithms
- Effective probabilistic and deterministic tractography
- Qualitative bundle-specific tractography results

## Abstract

We present DeepTract, a deep-learning framework for estimating white matter fibers orientation and streamline tractography. We adopt a data-driven approach for fiber reconstruction from diffusion weighted images (DWI), which does not assume a specific diffusion model. We use a recurrent neural network for mapping sequences of DWI values into probabilistic fiber orientation distributions. Based on these estimations, our model facilitates both deterministic and probabilistic streamline tractography. We quantitatively evaluate our method using the Tractometer tool, demonstrating competitive performance with state-of-the art classical and machine learning based tractography algorithms. We further present qualitative results of bundle-specific probabilistic tractography obtained using our method. The code is publicly available at: https://github.com/itaybenou/DeepTract.git.