3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
This work addresses the challenge of efficiently segmenting 3D medical images with limited manual annotation, which is incremental as it adapts an existing 2D method to 3D.
The paper tackles the problem of volumetric segmentation from sparse annotations by introducing a 3D U-Net that extends the 2D U-Net architecture to 3D, achieving good results on the Xenopus kidney dataset for semi-automated and fully-automated use cases.
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.