Feature Preserving Smoothing Provides Simple and Effective Data Augmentation for Medical Image Segmentation

In proceedings of Medical Image Computing and Computer Assisted Intervention (MICCAI), pages 116-126, Springer, 2020
 

Abstract

CNNs represent the current state of the art for image classification, as well as for image segmentation. Recent work suggests that CNNs for image classification suffer from a bias towards texture, and that reducing it can increase the network’s accuracy. We hypothesize that CNNs for medical image segmentation might suffer from a similar bias. We propose to reduce it by augmenting the training data with feature preserving smoothing, which reduces noise and high-frequency textural features, while preserving semantically meaningful boundaries. Experiments on multiple medical image segmentation tasks confirm that, especially when limited training data is available or a domain shift is involved, feature preserving smoothing can indeed serve as a simple and effective augmentation technique.

Images

Download Paper

Download Paper

Additional Material

  • Video (MPEG-4 video, 22 MB)

Bibtex

@INPROCEEDINGS{Sheikh:MICCAI20,
     author = {Sheikh, Rasha and Schultz, Thomas},
      pages = {116--126},
      title = {Feature Preserving Smoothing Provides Simple and Effective Data Augmentation for Medical Image
               Segmentation},
  booktitle = {Medical Image Computing and Computer Assisted Intervention (MICCAI)},
     series = {LNCS},
     volume = {12261},
       year = {2020},
  publisher = {Springer},
   abstract = {CNNs represent the current state of the art for image classification, as well as for image
               segmentation. Recent work suggests that CNNs for image classification suffer from a bias towards
               texture, and that reducing it can increase the network’s accuracy. We hypothesize that CNNs for
               medical image segmentation might suffer from a similar bias. We propose to reduce it by augmenting
               the training data with feature preserving smoothing, which reduces noise and high-frequency textural
               features, while preserving semantically meaningful boundaries. Experiments on multiple medical image
               segmentation tasks confirm that, especially when limited training data is available or a domain
               shift is involved, feature preserving smoothing can indeed serve as a simple and effective
               augmentation technique.}
}