Data augmentation via partial nonlinear registration for brain-age prediction


  • M.A. Schulz
  • A. Koch
  • V.E. Guarino
  • D. Kainmueller
  • K. Ritter


  • Lecture Notes in Computer Science


  • Lect Notes Comput Sci 13596: 169-178


  • Data augmentation techniques that improve the classification and segmentation of natural scenes often do not transfer well to brain imaging data. The conceptually most plausible augmentation technique for biological tissue, elastic deformation, works well on microscopic tissue but is limited on macroscopic structures like the brain, as the majority of mathematically possible elastic deformations of the human brain are anatomically implausible. Here, we characterize the subspace of anatomically plausible deformations for a participant’s brain image by nonlinearly registering the image to the brain images of several reference participants. Using the resulting warp fields for data augmentation outperformed both random elastic deformations and the non-augmented baseline in age prediction from T1 brain images.