CompareNet: Anatomical Segmentation Network with Deep Non-local Label Fusion

TL;DR

CompareNet is a novel deep learning framework that improves anatomical segmentation accuracy by integrating non-local label fusion with feature extraction and similarity learning, trained end-to-end.

Contribution

It introduces a deep non-local label fusion network with voxel-wise classification and end-to-end training, enhancing segmentation accuracy and robustness.

Findings

Outperforms state-of-the-art methods on IBSRv2 and MICCAI 2012 datasets.

Achieves higher accuracy in brain segmentation tasks.

Demonstrates robustness to pathological variations.

Abstract

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.