Research map / Detection and segmentation / CNN features
Learning Active Contour Models for Medical Image Segmentation
Xu Chen, Bryan M. Williams, Srinivasa R. Vallabhaneni, Gabriela Czanner, Rachel Williams, Yalin Zheng
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 |
|---|---|---|---|
| Add AC loss instead of CE loss | U-Net · ACDC 2017 test, left ventricle | Hausdorff distance (mm): 18.29 (2.04) -> 17.36 (2.76) | Improved |
| Add AC loss instead of CE loss | U-Net · ACDC 2017 test, right ventricle | Hausdorff distance (mm): 23.76 (2.52) -> 22.94 (2.48) | Improved |
| Add AC loss instead of CE loss | U-Net · ACDC 2017 test, myocardium | Hausdorff distance (mm): 18.04 (1.97) -> 16.60 (2.05) | Improved |
| Add AC loss instead of CE loss | DenseNet · ACDC 2017 test, left ventricle | Hausdorff distance (mm): 5.43 (1.81) -> 4.73 (1.35) | Improved |
| Add AC loss instead of CE loss | DenseNet · ACDC 2017 test, right ventricle | Hausdorff distance (mm): 6.21 (1.05) -> 5.95 (0.99) | Improved |
| Add AC loss instead of CE loss | DenseNet · ACDC 2017 test, myocardium | Hausdorff distance (mm): 6.34 (1.56) -> 5.42 (1.10) | Improved |
| Add AC loss instead of the reported CE baseline | Dense-Net · ACDC 2017 test, left ventricle | Dice score: 0.950 -> 0.986 | Improved |
| Add AC loss instead of the reported CE baseline | Dense-Net · ACDC 2017 test, right ventricle | Dice score: 0.923 -> 0.940 | Improved |
| Add AC loss instead of the reported CE baseline | Dense-Net · ACDC 2017 test, myocardium | Dice score: 0.911 -> 0.969 | Improved |
| Add AC loss instead of the reported CE baseline | Dense-Net · ACDC 2017 test, left ventricle | Hausdorff distance (mm): 7.14 (N/A) -> 4.73 (1.35) | Improved |
| Add AC loss instead of the reported CE baseline | Dense-Net · ACDC 2017 test, right ventricle | Hausdorff distance (mm): 11.13 (N/A) -> 5.95 (0.99) | Improved |
| Add AC loss instead of the reported CE baseline | Dense-Net · ACDC 2017 test, myocardium | Hausdorff distance (mm): 8.69 (N/A) -> 5.42 (1.10) | Improved |
Closest papers by meaning
- Adaptive Region-Specific Loss for Improved Medical Image Segmentation (TPAMI 2023 · similarity 0.88)
- Deep Interactive Segmentation of Medical Images: A Systematic Review and Taxonomy (TPAMI 2024 · similarity 0.87)
- Generative Medical Segmentation (AAAI 2025 · similarity 0.86)
- Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation (NeurIPS 2024 · similarity 0.85)
- Tyche: Stochastic In-Context Learning for Medical Image Segmentation (CVPR 2024 · similarity 0.85)
- Combinatorial CNN-Transformer Learning with Manifold Constraints for Semi-supervised Medical Image Segmentation (AAAI 2024 · 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.
