CompareNet: Anatomical Segmentation Network with Deep Non-local Label Fusion
This work addresses anatomical segmentation for medical imaging, particularly in brain analysis, with incremental improvements to existing non-local fusion strategies.
The authors tackled anatomical segmentation by proposing CompareNet, a deep non-local label fusion framework that incorporates feature extraction, similarity learning, and voxel-wise classification to improve accuracy and robustness. The results showed it outperformed state-of-the-art methods on IBSRv2 and MICCAI 2012 brain segmentation datasets.
Label propagation is a popular technique for anatomical segmentation. In this work, we propose a novel deep framework for label propagation based on non-local label fusion. Our framework, named CompareNet, incorporates subnets for both extracting discriminating features, and learning the similarity measure, which lead to accurate segmentation. We also introduce the voxel-wise classification as an unary potential to the label fusion function, for alleviating the search failure issue of the existing non-local fusion strategies. Moreover, CompareNet is end-to-end trainable, and all the parameters are learnt together for the optimal performance. By evaluating CompareNet on two public datasets IBSRv2 and MICCAI 2012 for brain segmentation, we show it outperforms state-of-the-art methods in accuracy, while being robust to pathologies.