PADDIT: Probabilistic Augmentation of Data using Diffeomorphic Image Transformation

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

For proper generalization performance of convolutional neural networks (CNNs) in medical image segmentation, the learnt features should be invariant under particular non-linear shape variations of the input. To induce invariance in CNNs to such transformations, we propose Probabilistic Augmentation of Data using Diffeomorphic Image Transformation (PADDIT) – a systematic framework for generating realistic transformations that can be used to augment data for training CNNs. The main advantage of PADDIT is the ability to produce transformations that capture the morphological variability in the training data. To this end, PADDIT constructs a mean template which represents the main shape tendency of the training data. A Hamiltonian Monte Carlo(HMC) scheme is used to sample transformations which warp the training images to the generated mean template. Augmented images are created by warping the training images using the sampled transformations. We show that CNNs trained with PADDIT outperforms CNNs trained without augmentation and with generic augmentation (0.2 and 0.15 higher dice accuracy respectively) in segmenting white matter hyperintensities from T1 and FLAIR brain MRI scans.
Original languageEnglish
Title of host publicationProceedings, SPIE 10949, Medical Imaging 2019: Image Processing
Number of pages6
PublisherSPIE - International Society for Optical Engineering
Publication date2019
Chapter109490S
DOIs
Publication statusPublished - 2019
EventSPIE Medical Imaging - San Diego, United States
Duration: 16 Feb 201921 Feb 2019

Conference

ConferenceSPIE Medical Imaging
LandUnited States
BySan Diego
Periode16/02/201921/02/2019

Links

ID: 215456614