• Corpus ID: 18559954

Direct White Matter Bundle Segmentation using Stacked U-Nets

@article{Wasserthal2017DirectWM,
  title={Direct White Matter Bundle Segmentation using Stacked U-Nets},
  author={Jakob Wasserthal and P. Neher and Fabian Isensee and Klaus Maier-Hein},
  journal={ArXiv},
  year={2017},
  volume={abs/1703.02036}
}
The state-of-the-art method for automatically segmenting white matter bundles in diffusion-weighted MRI is tractography in conjunction with streamline cluster selection. This process involves long chains of processing steps which are not only computationally expensive but also complex to setup and tedious with respect to quality control. Direct bundle segmentation methods treat the task as a traditional image segmentation problem. While they so far did not deliver competitive results, they can… 

Figures from this paper

Reproducible White Matter Tract Segmentation Using 3D U-Net on a Large-scale DTI Dataset
TLDR
A novel convolutional neural network based method to directly segment white matter tract trained on a low-resolution dataset of 9149 DTI images is developed and is expected to be applicable in clinical practice and in longitudinal analysis of white matter microstructure.
Automatic Segmentation of White Matter Tracts Using Multiple Brain MRI Sequences
TLDR
A novel neural architecture for the automatic segmentation of white matter tracts by fusing multiple MRI sequences is proposed and shown to compare favorably against state-of-the art methods (Vnet, TractSeg) on the Human Connectome Project (HCP) brain scans dataset for clinically important WM tracts.
Data-driven fiber tractography with neural networks
TLDR
This work presents a purely data-driven neural network regression model for fiber tractography, which benefits from additional data, which can be incorporated easily, even from different supervisors, and is robust to noise and variation in the data.
Entrack: A Data-Driven Maximum-Entropy Approach to Fiber Tractography
TLDR
The ability of the proposed generic machine learning method for probabilistic tractography to quantify the probability of a given fiber, which makes it a useful tool for outlier detection is highlighted.
HAMLET: Hierarchical Harmonic Filters for Learning Tracts from Diffusion MRI
TLDR
HAMLET is a novel tract learning algorithm, which, after training, maps raw diffusion weighted MRI directly onto an image which simultaneously indicates tract direction and tract presence, and is demonstrated to be robust and reliable.

References

SHOWING 1-10 OF 23 REFERENCES
Training shortest-path tractography: Automatic learning of spatial priors
Automatic Tractography Segmentation Using a High-Dimensional White Matter Atlas
TLDR
A new white matter atlas creation method that learns a model of the common white matter structures present in a group of subjects, enabling group comparison of white matter anatomy and results regarding the stability of the method and parameter choices are presented.
Atlas-Guided Cluster Analysis of Large Tractography Datasets
TLDR
A novel atlas-guided clustering framework for exploratory data analysis of large tractography datasets using an hierarchical cluster analysis approach that exploits the inherent redundancy in large datasets to time-efficiently group fiber tracts.
Automated Probabilistic Reconstruction of White-Matter Pathways in Health and Disease Using an Atlas of the Underlying Anatomy
TLDR
It is shown that, since the method does not constrain the exact spatial location or shape of the pathways but only their trajectory relative to the surrounding anatomical structures, a set a of healthy training subjects can be used to reconstruct the pathways accurately in patients as well as in controls.
Direct segmentation of the major white matter tracts in diffusion tensor images
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Active fibers: Matching deformable tract templates to diffusion tensor images
Multi-label segmentation of white matter structures: Application to neonatal brains
...
...