Research map / Detection and segmentation / CNN features
Conformable Convolution for Topologically Constrained Learning of Complex Anatomical Structures
Yousef Yeganeh, Goktug Guvercin, Nassir Navab, Azade Farshad
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 Conform layer to UNet | UNet · CHASE DB1 | errBeta0: 26.9 -> 21.6 | Improved |
| add Conform layer to Y-Net | Y-Net · CHASE DB1 | errBeta0: 27.9 -> 21.1 | Improved |
| add Conform layer to UNet | UNet · ISBI12 | errBeta1: 23.5±4.1 -> 7.9±2.9 | Improved |
| add Conform layer to SCOPE + clDice | SCOPE + clDice · CHASE DB1 | errBeta1: 1.6 -> 2.1 | Hurt |
| add Conform layer to SCOPE + Dice | SCOPE + Dice · CHASE DB1 | Dice (%): 80.0 -> 79.2 | Hurt |
| add Conform layer to SCOPE + clDice | SCOPE + clDice · CHASE DB1 | errBeta0: 24.2 -> 21.5 | Improved |
| add Conform layer to UNet | UNet · CHASE DB1 | Dice (%): 79.3 -> 79.7 | No clear effect |
| Conform instead of Deform conv | Deform · HT29 | errChi: 13.3 -> 6.1 | Improved |
| Conform instead of Deform conv | Deform · HT29 | Dice (%): 95.8 -> 94.6 | Hurt |
| Conform instead of DSC | DSC · ISBI12 | errChi: 12.6 -> 8.4 | Improved |
| add generator filtration (ablation) | TPG · CHASE DB1 | errBeta0: 32.7 -> 21.6 | Improved |
| add Gaussian dilation (ablation) | TPG · CHASE DB1 | errBeta0: 23.4 -> 21.6 | Improved |
Closest papers by meaning
- A Topological Loss Function for Deep-Learning Based Image Segmentation Using Persistent Homology (TPAMI 2020 · similarity 0.90)
- Topology-Reinforced Swin Transformer for Medical Image Analysis (NeurIPS 2026 · similarity 0.89)
- TopoAgent: An Agentic Framework for Automated Topology Learning in Medical Imaging (ECCV 2026 · similarity 0.89)
- Topology-Aware Segmentation Using Discrete Morse Theory (ICLR 2021 · similarity 0.89)
- Learning Probabilistic Topological Representations Using Discrete Morse Theory (ICLR 2023 · similarity 0.88)
- Topograph: An Efficient Graph-Based Framework for Strictly Topology Preserving Image Segmentation (ICLR 2025 · similarity 0.87)
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.
