TY - GEN
T1 - Instance-Specific Augmentation of Brain MRIs with Variational Autoencoders
AU - Middleton, Jon Anthony
AU - Bauer, Marko
AU - Johansen, Jacob
AU - Nielsen, Mads
AU - Sommer, Stefan Horst
AU - Pai, Akshay Sadananda Uppinakudru
PY - 2023
Y1 - 2023
N2 - Spatial data augmentation is a standard technique for regularizing deep segmentation networks that are tasked with localizing medical abnormalities. However, a typical spatial augmentation scheme is built upon ad hoc selections of spatial transformation parameters which are not determined by the data set and therefore may not capture spatial variations in the data. For segmentation networks trained in the low-data regime, these ad hoc transformation techniques often fail to encourage better generalization. To address this problem, we propose a variational autoencoder framework for spatial data augmentation. We show how this framework provides a natural, data-driven approach to probabilistic, instance-specific spatial augmentation. Further, we observe that U-Nets trained on data augmented using this framework compare favorably with U-Nets trained using standard spatial augmentation methods.
AB - Spatial data augmentation is a standard technique for regularizing deep segmentation networks that are tasked with localizing medical abnormalities. However, a typical spatial augmentation scheme is built upon ad hoc selections of spatial transformation parameters which are not determined by the data set and therefore may not capture spatial variations in the data. For segmentation networks trained in the low-data regime, these ad hoc transformation techniques often fail to encourage better generalization. To address this problem, we propose a variational autoencoder framework for spatial data augmentation. We show how this framework provides a natural, data-driven approach to probabilistic, instance-specific spatial augmentation. Further, we observe that U-Nets trained on data augmented using this framework compare favorably with U-Nets trained using standard spatial augmentation methods.
U2 - 10.1007/978-3-031-25046-0_5
DO - 10.1007/978-3-031-25046-0_5
M3 - Article in proceedings
SN - 978-3-031-25045-3
T3 - Lecture Notes in Computer Science
SP - 49
EP - 58
BT - Medical Applications with Disentanglements
PB - Springer
T2 - First International Workshop, MILLanD 2022
Y2 - 22 September 2022
ER -