Peter Neher

Tractography Reproducibility Challenge with Empirical Data (TraCED): The 2017 ISMRM Diffusion Study Group Challenge

The paper evaluates tractography reproducibility using empirical data from a single healthy volunteer scanned on two scanners, finding high consistency among top algorithms but variability due to tract volume containment.

Limits to anatomical accuracy of diffusion tractography using modern approaches

This study evaluates modern diffusion tractography methods using a standardized challenge, finding no significant improvement in anatomical accuracy despite methodological advances.

Tractography-based connectomes are dominated by false-positive connections

The paper evaluates tractography methods by analyzing a simulated dataset, finding that most algorithms generate many false-positive connections.

Fiber tractography using machine learning

This paper introduces a machine learning-based fiber tractography method using random forest classification and evaluates it against state-of-the-art approaches using phantom and in vivo experiments.

Learn to Track: Deep Learning for Tractography

This paper applies deep learning to fiber tractography, showing models can generate streamlines from DWI data and outperform traditional methods in accuracy and false connection control.