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