A Topology-Attention ConvLSTM Network and Its Application to EM Images
This work addresses segmentation accuracy for fine-scale structures in biomedical images, representing an incremental improvement with novel attention modules.
The paper tackled the problem of achieving high structural accuracy in 3D biomedical image segmentation by proposing a Topology-Attention ConvLSTM Network (TACNet), which outperformed baselines on topology-aware metrics.
Structural accuracy of segmentation is important for finescale structures in biomedical images. We propose a novel TopologyAttention ConvLSTM Network (TACNet) for 3D image segmentation in order to achieve high structural accuracy for 3D segmentation tasks. Specifically, we propose a Spatial Topology-Attention (STA) module to process a 3D image as a stack of 2D image slices and adopt ConvLSTM to leverage contextual structure information from adjacent slices. In order to effectively transfer topology-critical information across slices, we propose an Iterative-Topology Attention (ITA) module that provides a more stable topology-critical map for segmentation. Quantitative and qualitative results show that our proposed method outperforms various baselines in terms of topology-aware evaluation metrics.