3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

Medical Image Computing and Computer-Assisted Intervention (MICCAI), Springer, LNCS, Vol.9901: 424--432, Oct 2016
Download the publication : cicek16miccai.pdf [592Ko]  

    Publisher's link :

Download code :

Abstract: This paper introduces a network for volumetric segmentation that learns from sparsely annotated volumetric images. We outline two attractive use cases of this method: (1) In a semi-automated setup, the user annotates some slices in the volume to be segmented. The network learns from these sparse annotations and provides a dense 3D segmentation. (2) In a fully-automated setup, we assume that a representative, sparsely annotated training set exists. Trained on this data set, the network densely segments new volumetric images. The proposed network extends the previous u-net architecture from Ronneberger et al. by replacing all 2D operations with their 3D counterparts. The implementation performs on-the-fly elastic deformations for efficient data augmentation during training. It is trained end-to-end from scratch, i.e., no pre-trained network is required. We test the performance of the proposed method on a complex, highly variable 3D structure, the Xenopus kidney, and achieve good results for both use cases.

Images and movies


BibTex references

  author       = "Ö. \c{C}i\c{c}ek and A. Abdulkadir and S.S. Lienkamp and T. Brox and O. Ronneberger",
  title        = "3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation",
  booktitle    = "Medical Image Computing and Computer-Assisted Intervention (MICCAI)",
  series       = "LNCS",
  volume       = "9901",
  pages        = "424--432",
  month        = "Oct",
  year         = "2016",
  editor       = "S. Ourselin, W.S. Wells, M.R. Sabuncu, G. Unal, and L. Joskowicz",
  publisher    = "Springer",
  note         = "(available on arXiv:1606.06650 [cs.CV])",
  keywords     = "Convolutional Neural Networks, 3D, Biomedical Volumetric Image Segmentation, Xenopus Kidney, Semi-automated, Fully-automated, Sparse Annotation",
  url          = "http://lmb.informatik.uni-freiburg.de//Publications/2016/CABR16"

Other publications in the database