Research map / Detection and segmentation / CNN features
Segmentation of Tubular Structures Using Iterative Training with Tailored Samples
Wei Liao
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 |
|---|---|---|---|
| iterative training with tailored samples instead of samples drawn directly along annotations | minimal path method with CNN · EPFL roads | centerline mean error (pixels): 1.71 -> 1.41 | Improved |
| iterative training with tailored samples vs Path-CNN | minimal path method with CNN · Toronto roads | centerline mean error (pixels): 3.65 -> 3.54 | Improved |
| iterative tailored-sample training instead of Path-CNN training | minimal path method · EPFL roads | mean Dice: 0.6322 -> 0.9125 | Improved |
| iterative tailored-sample training instead of Path-CNN training | minimal path method · DRIVE (3 train images) | mean Dice: 0.5470 -> 0.7578 | Improved |
| compare against FR-UNet on full DRIVE training set | proposed method · DRIVE (20 train images) | mean Dice: 0.8065 vs 0.8208 | Hurt |
| run more training iterations of the iterative scheme (ablation) | proposed method · all three datasets (validation Dice) | validation Dice | Improved |
| use CNN patch features in rectified patches vs per-pixel CNN weights (Dijkstra CNN) | minimal path method · EPFL roads | centerline mean error (pixels): 2.91 -> 1.41 | Improved |
Closest papers by meaning
- Progressive Minimal Path Method With Embedded CNN (CVPR 2022 · similarity 0.95)
- PointScatter: Point Set Representation for Tubular Structure Extraction (ECCV 2022 · similarity 0.89)
- Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures (ECCV 2024 · similarity 0.89)
- HarmonySeg: Tubular Structure Segmentation with Deep-Shallow Feature Fusion and Growth-Suppression Balanced Loss (ICCV 2025 · similarity 0.89)
- GraphMorph: Tubular Structure Extraction by Morphing Predicted Graphs (NeurIPS 2024 · similarity 0.88)
- SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation (NeurIPS 2025 · similarity 0.83)
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.
