Share Email Print
cover

Proceedings Paper • new

PADDIT: Probabilistic Augmentation of Data using Diffeomorphic Image Transformation
Author(s): Mauricio Orbes-Arteaga; Lauge Sørensen; Jorge Cardoso; Marc Modat; Sebastien Ourselin; Stefan Sommer; Mads Nielsen; Christian Igel ; Akshay Pai
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

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.

Paper Details

Date Published: 15 March 2019
PDF: 6 pages
Proc. SPIE 10949, Medical Imaging 2019: Image Processing, 109490S (15 March 2019); doi: 10.1117/12.2512520
Show Author Affiliations
Mauricio Orbes-Arteaga, Univ. of Copenhagen (Denmark)
Biomediq (Denmark)
Cerebriu (Denmark)
Lauge Sørensen, Univ. of Copenhagen (Denmark)
Biomediq (Denmark)
Cerebriu (Denmark)
Jorge Cardoso, King's College London (United Kingdom)
Marc Modat, King's College London (United Kingdom)
Sebastien Ourselin, King's College London (United Kingdom)
Stefan Sommer, Univ. of Copenhagen (Denmark)
Mads Nielsen, Univ. of Copenhagen (Denmark)
Biomediq (Denmark)
Cerebriu (Denmark)
Christian Igel , Univ. of Copenhagen (Denmark)
Akshay Pai, Univ. of Copenhagen (Denmark)
Biomediq (Denmark)
Cerebriu (Denmark)


Published in SPIE Proceedings Vol. 10949:
Medical Imaging 2019: Image Processing
Elsa D. Angelini; Bennett A. Landman, Editor(s)

© SPIE. Terms of Use
Back to Top