Diffusion MRI GAN synthesizing fibre orientation distribution data using generative adversarial networks.

Journal: Communications biology
PMID:

Abstract

Machine learning may enhance clinical data analysis but requires large amounts of training data, which are scarce for rare pathologies. While generative neural network models can create realistic synthetic data such as 3D MRI volumes and, thus, augment training datasets, the generation of complex data remains challenging. Fibre orientation distributions (FODs) represent one such complex data type, modelling diffusion as spherical harmonics with stored weights as multiple three-dimensional volumes. We successfully trained an α-WGAN combining a generative adversarial network and a variational autoencoder to generate synthetic FODs, using the Human Connectome Project (HCP) data. Our resulting synthetic FODs produce anatomically accurate fibre bundles and connectomes, with properties matching those from our validation dataset. Our approach extends beyond FODs and could be adapted for generating various types of complex medical imaging data, particularly valuable for augmenting limited clinical datasets.

Authors

  • Sebastian Vellmer
    Department of Neurosurgery, Charité Universitätsmedizin Berlin, Berlin, Germany. sebastian.vellmer@charite.de.
  • Dogu Baran Aydogan
    A.I. Virtanen Institute for Molecular Sciences, University of Eastern Finland, Kuopio, Finland.
  • Timo Roine
    Department of Neuroscience and Biomedical Engineering, Aalto University School of Science, Espoo, Finland.
  • Alberto Cacciola
    IRCCS Centro Neurolesi "Bonino Pulejo", S.S. 113, Via Palermo, C.da Casazza, 98124, Messina, Italy.
  • Thomas Picht
    Klinik für Neurochirurgie, Charité - Universitätsmedizin Berlin, Charitéplatz 1, 10117, Berlin, Deutschland. thomas.picht@charite.de.
  • Lucius S Fekonja
    Department of Neurosurgery, Charité Universitätsmedizin Berlin, Berlin, Germany. lucius.fekonja@charite.de.