This paper introduces a network for volumetric segmenta-tion that learns from sparsely annotated volumetric images. We out-line 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 rep-resentative, 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 im-plementation 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 pro-posed method on a complex, highly variable 3D structure, the Xenopus kidney, and achieve good results for both use cases.
CITATION STYLE
Cicek, O., Abdulkadir, A., Lienkamp, S. S., Brox, T., & Ronneberger, O. (2016). 3D U-Net : Learning Dense Volumetric. Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016, 424–432. Retrieved from http://arxiv.org/abs/1606.06650
Mendeley helps you to discover research relevant for your work.