Research map / Detection and segmentation / CNN features
CC-SAM: Enhancing SAM with Cross-feature Attention and Context for Ultrasound Image Segmentation
Shreyank N Gowda, David A Clifton
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 frozen pretrained ResNet50 branch (ablation) | SAMUS baseline · TN3K | Dice (%): 84.45 -> 84.91 | Improved |
| add variational attention fusion (VAF) (ablation) | SAMUS baseline · TN3K | Dice (%): 84.45 -> 85.55 | Improved |
| add GPT-4 text prompts instead of point prompts (ablation) | SAMUS baseline · BUSI | Dice (%): 85.77 -> 87.92 | Improved |
| add text prompts on top of ResNet50 + VAF (ablation) | CC-SAM · TN3K | Dice (%): 85.72 -> 87.11 | Improved |
| add VAF and text prompt on top of ResNet50 (ablation) | CC-SAM · BUSI | Dice (%): 88.45 -> 89.51 | Improved |
| CC-SAM versus SAMUS on foundation-model benchmark | CC-SAM · TN3K (US30K) | Dice (%): 83.05 -> 85.59 | Improved |
| CC-SAM versus FAT-Net on CAMUS-MYO Hausdorff distance | CC-SAM · CAMUS-MYO | Hausdorff distance: 15.93 vs 16.11 | Hurt |
| CC-SAM on unseen datasets (generalization) | CC-SAM · unseen DDTI, UDIAT, HMC-QU | seen-to-unseen performance drop | Improved |
Closest papers by meaning
- Enhancing SAM with Efficient Prompting and Preference Optimization for Semi-supervised Medical Image Segmentation (CVPR 2025 · similarity 0.90)
- Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding (CVPR 2024 · similarity 0.90)
- U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understanding (ICLR 2026 · similarity 0.87)
- MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation (CVPR 2024 · similarity 0.87)
- Towards a Comprehensive, Efficient and Promptable Anatomic Structure Segmentation Model Using 3D Whole-Body CT Scans (AAAI 2025 · similarity 0.86)
- BLO-SAM: Bi-level Optimization Based Finetuning of the Segment Anything Model for Overfitting-Preventing Semantic Segmentation (ICML 2024 · similarity 0.86)
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.
