Research map / Detection and segmentation / CNN features
TopoSeg: Topology-Aware Nuclear Instance Segmentation
Hongliang He, Jun Wang, Pengxu Wei, Fan Xu, Xiangyang Ji, Chang Liu, Jie Chen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add topology-aware loss to pixel-wise loss (ablation) | U-Net · MoNuSeg | AJI: 0.579 -> 0.619 | Improved |
| add topology-aware loss to pixel-wise loss (ablation) | U-Net · CPM17 | AJI: 0.666 -> 0.718 | Improved |
| add topology-aware loss to pixel-wise loss (ablation) | U-Net · PBNulei | PQ: 0.426 -> 0.425 | No clear effect |
| add topology-aware loss to pixel-wise loss (ablation) | U-Net · MoNuSeg | Hausdorff distance: 12.80 -> 9.647 | Improved |
| add adaptive image selection to topology loss (ablation) | TopoSeg · PBNulei | PQ: 0.425 -> 0.446 | Improved |
| use adaptive threshold instead of fixed thresholds (25/50/75%) for image selection (ablation) | TopoSeg · MoNuSeg | PQ: 0.606 -> 0.610 | Improved |
| use fixed 50% image selection on PBNulei (ablation) | TopoSeg · PBNulei | PQ: 0.425 -> 0.419 | Hurt |
| calculate topology loss on selected patches instead of whole image (ablation) | TopoSeg · PBNulei | PQ: 0.425 -> 0.498 | Improved |
| use hierarchical multi-scale patches instead of single-size patches (ablation) | TopoSeg · MoNuSeg | AJI: 0.628 -> 0.639 | Improved |
| use hierarchical patch selection on CPM17 (ablation) | TopoSeg · CPM17 | PQ: 0.675 -> 0.662 | No clear effect |
| use adaptive hierarchical patch selection (ablation) | TopoSeg · PBNulei | PQ: 0.425 -> 0.520 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CDNet — CDNet: Centripetal Direction Network for Nuclear Instance Segmentation (ICCV 2021) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Semi-supervised Segmentation of Histopathology Images with Noise-Aware Topological Consistency (ECCV 2024 · similarity 0.89)
- TopoSlide: Topologically-Informed Histopathology Whole Slide Image Representation Learning (CVPR 2026 · similarity 0.87)
- Topograph: An Efficient Graph-Based Framework for Strictly Topology Preserving Image Segmentation (ICLR 2025 · similarity 0.87)
- TopoFuse: Topology-Aware Tri-Planar Fusion for 3D Cryo-Electron Tomography Segmentation (ECCV 2026 · similarity 0.86)
- Mudslide: A Universal Nuclear Instance Segmentation Method (CVPR 2024 · similarity 0.85)
- MATCH: Multi-faceted Adaptive Topo-Consistency for Semi-Supervised Histopathology Segmentation (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
