Instance-Specific Augmentation of Brain MRIs with Variational Autoencoders

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

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.
Original languageEnglish
Title of host publicationMedical Applications with Disentanglements : First MICCAI Workshop, MAD 2022, Held in Conjunction with MICCAI 2022, Singapore, September 22, 2022, Proceedings
Publication date2023
ISBN (Print)978-3-031-25045-3
ISBN (Electronic) 978-3-031-25046-0
Publication statusPublished - 2023
EventFirst International Workshop, MILLanD 2022: [Held in Conjunction with MICCAI 2022] - Singapore
Duration: 22 Sep 2022 → …


WorkshopFirst International Workshop, MILLanD 2022
Periode22/09/2022 → …
SeriesLecture Notes in Computer Science

ID: 334464739