Data augmentation via partial nonlinear registration for brain-age prediction

Item Type:	Article
Title:	Data augmentation via partial nonlinear registration for brain-age prediction
Creators Name:	Schulz, M.A. and Koch, A. and Guarino, V.E. and Kainmueller, D. and Ritter, K.
Abstract:	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.
Keywords:	Brain Imaging, Machine Learning, Data Augmentation
Source:	Lecture Notes in Computer Science
Series Name:	Lecture Notes in Computer Science
Title of Book:	Machine Learning in Clinical Neuroimaging
ISSN:	0302-9743
ISBN:	978-3-031-17898-6
Publisher:	Springer
Volume:	13596
Page Range:	169-178
Date:	2022
Official Publication:	https://doi.org/10.1007/978-3-031-17899-3_17

Repository Staff Only: item control page