Research map / Graph learning / Graph algorithms and clustering
Biologically-Constrained Graphs for Global Connectomics Reconstruction
Brian Matejek, Daniel Haehn, Haidong Zhu, Donglai Wei, Toufiq Parag, Hanspeter Pfister
Check 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 |
|---|---|---|---|
| Apply biologically constrained graph construction and global partitioning to the input segmentation | Connectome reconstruction pipeline · PNI Test One | Total VI: 0.491 -> 0.388; -20.9% | Improved |
| Apply biologically constrained graph construction and global partitioning to the input segmentation | Connectome reconstruction pipeline · PNI Test Two | Total VI: 0.416 -> 0.297; -28.7% | Improved |
| Apply biologically constrained graph construction and global partitioning to the input segmentation | Connectome reconstruction pipeline · Kasthuri Test | Total VI: 0.965 -> 0.815; -15.6% | Improved |
| Apply biologically constrained graph construction and global partitioning to the input segmentation | Connectome reconstruction pipeline · SNEMI3D | Total VI: 0.807 -> 0.647; -19.8% | Improved |
| Add morphology-based node generation for merging small segments (ablation) | Biologically-Constrained Graphs · PNI Test One | Correct small-segment merges: 305 / 521 (36.9%) -> 686 / 169 (80.2%) | Improved |
| Add morphology-based node generation for merging small segments (ablation) | Biologically-Constrained Graphs · PNI Test Two | Correct small-segment merges: 185 / 281 (39.7%) -> 444 / 75 (85.5%) | Improved |
| Add morphology-based node generation for merging small segments (ablation) | Biologically-Constrained Graphs · Kasthuri Test | Correct small-segment merges: 4,514 / 4,090 (52.5%) -> 6,623 / 2,020 (76.6%) | Improved |
| Add skeleton endpoint and geometric constraints to prune candidate edges (ablation) | Biologically-Constrained Graphs · PNI Test One | Candidate edges: 528 / 25,619 -> 417 / 10,074; 79.0% / 39.3% | Improved |
| Add skeleton endpoint and geometric constraints to prune candidate edges (ablation) | Biologically-Constrained Graphs · PNI Test Two | Candidate edges: 460 / 30,388 -> 370 / 11,869; 80.4% / 39.1% | Improved |
| Add skeleton endpoint and geometric constraints to prune candidate edges (ablation) | Biologically-Constrained Graphs · Kasthuri Test | Candidate edges: 1,193 / 43,951 -> 936 / 18,168; 78.5% / 41.3% | Improved |
| Add global graph optimization instead of greedy local agglomeration (ablation) | Biologically-Constrained Graphs · PNI Test One | VI Merge: 0.127 -> 0.115; -9.4% | Improved |
| Add global graph optimization instead of greedy local agglomeration (ablation) | Biologically-Constrained Graphs · PNI Test Two | VI Merge: 0.127 -> 0.097; -23.6% | Improved |
Closest papers by meaning
- Efficient Connectivity-Preserving Instance Segmentation with Supervoxel-Based Loss Function (AAAI 2025 · similarity 0.87)
- ConnectomeBench: Can LLMs proofread the connectome? (NeurIPS 2025 · similarity 0.86)
- Learning Multimodal Volumetric Features for Large-Scale Neuron Tracing (AAAI 2024 · similarity 0.86)
- MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation (NeurIPS 2026 · similarity 0.85)
- Cross-Dimension Affinity Distillation for 3D EM Neuron Segmentation (CVPR 2024 · similarity 0.85)
- $\textit{NeuroPath}$: A Neural Pathway Transformer for Joining the Dots of Human Connectomes (NeurIPS 2024 · similarity 0.84)
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.
