FastSurfer: A pipline for fast and accurate neuroimaging using deep learning

David Kügler1, Leonie Henschel1, Sailesh Conjeti1, Santiago Estrada1, Kersten Diers1, Bruce Fischl2, Martin Reuter1

1 German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany
2 A.A. Martinos Center for Biomedical Imaging, MGH, Boston MA, USA

take this

Traditional neuroimage analysis pipelines involve computationally intensive, time-consuming optimization steps, and thus, do not scale well to large cohort studies. FastSurfer is a fast deep-learning based alternative for the automated processing of structural human MRI brain scans, including surface reconstruction and cortical parcellation. FastSurfer consists of an advanced deep learning architecture (FastSurferCNN) used to segment a whole brain MRI into 95 classes in under 1 min, and a surface pipeline building upon this high-quality brain segmentation. FastSurferCNN features superior performance across five different datasets where it consistently outperforms existing deep learning approaches in terms of accuracy by a margin. Further, we perform fast cortical surface reconstruction and thickness analysis by introducing a spectral spherical embedding and by directly mapping the cortical labels from the image to the surface.

To enable the usage in applied research and for the sustainability of the pipeline FastSurfer is extensively validated. This validation includes a measurement of generalizability to different scanners, disease states, as well as an unseen acquisition sequence, demonstrates increased test-retest reliability, and increased sensitivity to disease effects relative to traditional FreeSurfer. In conslusion, FastSurfer is a reliable full FreeSurfer alternative for volumetric analysis (within 1 minute) and surface-based thickness analysis (within only around 1h + optionally 30 min for group registration).