PADDIT: Probabilistic Augmentation of Data using Diffeomorphic Image Transformation
This addresses the need for better segmentation accuracy in medical imaging for clinicians, but it is incremental as it builds on existing augmentation methods.
The paper tackled the problem of improving generalization in medical image segmentation by inducing invariance to non-linear shape variations in CNNs, and the result showed that CNNs trained with PADDIT outperformed those without augmentation or with generic augmentation in segmenting white matter hyperintensities from brain MRI scans.
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. We show that CNNs trained with PADDIT outperforms CNNs trained without augmentation and with generic augmentation in segmenting white matter hyperintensities from T1 and FLAIR brain MRI scans.