A Topology-Attention ConvLSTM Network and Its Application to EM Images
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 18 of its 29 references that are in the map. First posted on arXiv 7 Feb 2022.
Builds on
18 of 29 references.
References · 18
- 2017Attention Is All You Needcited by 59,932
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2017Non-local Neural Networkscited by 2,290
- 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
- 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
- 2018Self-Attention Generative Adversarial Networkscited by 809
- 2017A Structured Self-attentive Sentence Embeddingcited by 318
- 2019Topology-Preserving Deep Image Segmentationcited by 198
- 2017Beyond the Pixel-Wise Loss for Topology-Aware Delineationcited by 82
- 2021Topology-Aware Segmentation Using Discrete Morse Theorycited by 75
- 2015Efficient piecewise training of deep structured models for semantic segmentationcited by 71
- 2017DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understandingcited by 71
6 more
- 2019Explicit topological priors for deep-learning based image segmentation using persistent homologycited by 30
- 2016Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentationcited by 25
- 2013Confidence sets for persistence diagramscited by 17
- 2013Machine learning of hierarchical clustering to segment 2D and 3D imagescited by 11
- 2018Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomicscited by 6
- 2017Large Scale Image Segmentation with Structured Loss based Deep Learning for Connectome Reconstructioncited by 5
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 1.
2 papers.