Klaus Hermann Maier-Hein

This paper develops a method using hyperspectral imaging and deep learning to classify tissues with high accuracy, showing that spectral variability is primarily due to tissue type.

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.

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

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.

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.