We develop deep-learning and machine-learning methods for automated, accurate, and scalable analysis of brain MRI — enabling large-scale neuroimaging research and clinical applications.
We build open, validated computational tools for neuroimaging — from whole-brain segmentation pipelines to geometric shape analysis libraries.
Fast, accurate, deep-learning pipeline for whole-brain segmentation in under a minute and full surface reconstruction in about an hour. Produces FreeSurfer-conform outputs for large-cohort and clinical use.
Learn more →
GPU-accelerated Python toolkit for neuroimaging registration — same-modality, cross-modal, boundary-based, and multi-timepoint — plus transform and volume utilities. Replaces FreeSurfer's mri_robust_register, mri_coreg, and bbregister. Usable from the command line or as a library.
Learn more →
Automated geometry-based method for hippocampal shape and thickness analysis from structural MRI, enabling fine-grained morphometric studies of the hippocampus.
Learn more →
AI-powered neuroimaging platform combining an MRI viewer with integrated pipelines like FastSurfer. Run complex structural imaging workflows through a GUI or conversational AI — no command line required.
Learn more →
Cortical surface parcellation using projection-based 3D convolutional neural networks operating on spherical mesh representations.
Learn more →
Python library for geometric mesh processing and finite element method (FEM) differential geometry computations on triangular and tetrahedral meshes.
Learn more →We are based at DZNE Bonn and the Martinos Center for Biomedical Imaging at MGH / Harvard Medical School, Boston. Our lab welcomes people of any background.
We regularly organise FastSurfer workshops and training courses. Check the events page for upcoming dates.
Deep
Medical Imaging Lab
