PADDIT: Probabilistic Augmentation of Data using Diffeomorphic Image Transformation

TY - CHAP

T1 - PADDIT

T2 - Medical Imaging 2019: Image Processing

AU - Orbes-Arteaga, Mauricio

AU - Sørensen, Lauge

AU - Cardoso, Jorge

AU - Modat, Marc

AU - Ourselin, Sebastien

AU - Sommer, Stefan

AU - Nielsen, Mads

AU - Igel, Christian

AU - Pai, Akshay

PY - 2019/3/15

Y1 - 2019/3/15

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85068345087&partnerID=8YFLogxK

U2 - 10.1117/12.2512520

DO - 10.1117/12.2512520

M3 - Conference paper

AN - SCOPUS:85068345087

VL - 10949

BT - Medical Imaging 2019

A2 - Angelini, Elsa D.

A2 - Angelini, Elsa D.

A2 - Angelini, Elsa D.

A2 - Landman, Bennett A.

PB - SPIE

Y2 - 19 February 2019 through 21 February 2019

ER -