Non-local U-Net for Biomedical Image Segmentation
This addresses efficiency and effectiveness issues in biomedical image segmentation, particularly for 3D infant brain MR images, but appears incremental as it builds on the established U-Net architecture.
The authors tackled the limitation of local operators in U-Net for biomedical image segmentation by proposing non-local U-Nets with global aggregation blocks, achieving top performances with fewer parameters and faster computation on 3D infant brain MR image segmentation.
Deep learning has shown its great promise in various biomedical image segmentation tasks. Existing models are typically based on U-Net and rely on an encoder-decoder architecture with stacked local operators to aggregate long-range information gradually. However, only using the local operators limits the efficiency and effectiveness. In this work, we propose the non-local U-Nets, which are equipped with flexible global aggregation blocks, for biomedical image segmentation. These blocks can be inserted into U-Net as size-preserving processes, as well as down-sampling and up-sampling layers. We perform thorough experiments on the 3D multimodality isointense infant brain MR image segmentation task to evaluate the non-local U-Nets. Results show that our proposed models achieve top performances with fewer parameters and faster computation.