FastSurfer

FastSurfer is a fast and accurate deep-learning-based neuroimaging pipeline. This approach provides a full FreeSurfer alternative for volumetric analysis and surface-based thickness analysis.

Tables can't be imported directly. Please insert an image of your table which can be found here.

It consists of two main parts:

(i) FastSurferCNN - an advanced deep learning architecture capable of whole-brain segmentation into 95 classes, mimicking FreeSurfer’s anatomical segmentation and cortical parcellation (DKTatlas), in much less time than it would usually take with a standard FS segmentation and parcellation.

(ii) recon-surf - full FreeSurfer alternative for cortical surface reconstruction, mapping of cortical labels, and traditional point-wise and ROI thickness analysis in approximately 60 minutes.

The tool generates a report that provides volumetric and thickness measurements.

For more information visit: https://github.com/Deep-MI/FastSurfer

Required inputs

  • T1: T1 image. Must be labeled as 'T1' modality.

Settings

N/A

Output container files

  • aseg_stats.csv : Volumetric information.
  • aseg_stats_1.csv: Volumetric information.
  • aseg_stats_2.csv: Volumetric information.
  • report.pdf: PDF report.
  • volumetric.csv: Thickness measures.

References

FastSurfer: Henschel et al. 2020 FreeSurfer: Dale et al. 1999Fischl et al. 1999Fischl et al. 2000Fischl et al. 2002Fischl et al. 2004