Research map / Detection and segmentation / CNN features
Neovascularization Segmentation via a Multilateral Interaction-Enhanced Graph Convolutional Network
Tao Chen, Dan Zhang, Da Chen, Huazhu Fu, Kai Jin, Shanshan Wang, Laurent David Cohen, Yitian Zhao, Quanyong Yi, Jiong Zhang
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 boundary auxiliary task (ablation) | U2Net multi-task (M0) · CNVSeg mixed devices, region segmentation | Dice: 0.8432 -> 0.8489 | Improved |
| add shape auxiliary task (ablation) | M1 · CNVSeg mixed devices, region segmentation | Dice: 0.8489 -> 0.8534 | Improved |
| add uncertainty estimation loss (ablation) | M2 · CNVSeg mixed devices, region segmentation | Dice: 0.8534 -> 0.8623 | Improved |
| add MIGR and MRGR modules (ablation) | M1 · CNVSeg mixed devices, region segmentation | Dice: 0.8489 -> 0.8566 | Improved |
| add MIGR and MRGR modules (ablation) | M2 · CNVSeg mixed devices, region segmentation | Dice: 0.8534 -> 0.8677 | Improved |
| add MIGR and MRGR modules (ablation) | M3 · CNVSeg mixed devices, region segmentation | Dice: 0.8623 -> 0.8721 | Improved |
| add MIGR and MRGR modules (ablation) | M3 · CNVSeg mixed devices, vessel segmentation | Dice: 0.8721 -> 0.8812 | Improved |
| add all components (boundary, shape tasks, uncertainty loss, MIGR, MRGR) to U2Net backbone (ablation) | U2Net · CNVSeg mixed devices, region segmentation | Dice: 0.8432 -> 0.8721 | Improved |
| use K=12 graph nodes instead of 6 (ablation) | MTG-Net · CNVSeg mixed devices, region segmentation | Dice: 0.8621 -> 0.8721 | Improved |
| use K=18 graph nodes instead of 12 (ablation) | MTG-Net · CNVSeg mixed devices, region segmentation | Dice: 0.8721 -> 0.8623 | Hurt |
| use K=24 graph nodes instead of 12 (ablation) | MTG-Net · CNVSeg mixed devices, region segmentation | Dice: 0.8721 -> 0.8767; time 84.06 s -> 106.24 s | Mixed |
| use Z=10 MC-dropout samples instead of 5 (ablation) | MTG-Net · CNVSeg mixed devices, region segmentation | Dice: 0.8614 -> 0.8721 | 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.
- MF-Net — MFNet: Multi-Filter Directive Network for Weakly Supervised Salient Object Detection (ICCV 2021) · better on 1 of 1 shared result
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
- MuTri: Multi-view Tri-alignment for OCT to OCTA 3D Image Translation (CVPR 2025 · similarity 0.83)
- HACDR-Net: Heterogeneous-Aware Convolutional Network for Diabetic Retinopathy Multi-Lesion Segmentation (AAAI 2024 · similarity 0.83)
- SIGraph: Saliency Image-Graph Network for Retinal Disease Classification in Fundus Image (AAAI 2025 · similarity 0.82)
- FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs (NeurIPS 2026 · similarity 0.81)
- DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentation (CVPR 2025 · similarity 0.81)
- vesselFM: A Foundation Model for Universal 3D Blood Vessel Segmentation (CVPR 2025 · similarity 0.81)
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.
