Research map / Detection and segmentation / CNN features
MedCAGD: Context-Aware Gated Decoder for Robust Medical Image Segmentation
Saad Wazir, Patrick Vibild, Dinh Tran, Seongah Kim, Daeyoung Kim
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 Bottleneck with global context injection to plain decoder (ablation) | MedCAGD decoder · Synapse | Dice: 73.91 -> 75.53 | Improved |
| add Context Aggregator with residual attention to Bottleneck decoder (ablation) | MedCAGD decoder · Synapse | Dice: 75.53 -> 83.57 | Improved |
| add Context Aggregator with residual attention (vs without RA) (ablation) | MedCAGD decoder · CellSeg | Dice: 82.60 -> 84.28 | Improved |
| add Refinement Block (ablation) | MedCAGD decoder · Synapse | Dice: 83.57 -> 85.19 | Improved |
| add SCA-Gate skip regulation (ablation) | MedCAGD decoder · Synapse | Dice: 85.19 -> 87.00 | Improved |
| add SCA-Gate skip regulation (ablation) | MedCAGD decoder · CellSeg | Dice: 84.62 -> 86.61 | Improved |
| add Stage 0 refinement pathway (ablation) | MedCAGD decoder · Synapse | Dice: 87.00 -> 87.21 | No clear effect |
| replace SCA-Gate with Attention U-Net gate (ablation) | MedCAGD decoder · Synapse | Dice: 87.00 -> 85.20 | Hurt |
| replace SCA-Gate with LGAG (EMCAD) (ablation) | MedCAGD decoder · CellSeg | Dice: 86.61 -> 81.99 | Hurt |
| enable both deep supervision and edge supervision (ablation) | MedCAGD · six benchmarks | Dice and HD95 | Improved |
| use larger input 512x512 with pvt_v2 (ablation) | MedCAGD · Synapse | Dice: 87.00 -> 87.99 | Improved |
| use MedCAGD instead of EMCAD decoder | MedCAGD · ACDC | Dice: 85.07 -> 87.54 | Improved |
Closest papers by meaning
- EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation (CVPR 2024 · similarity 0.89)
- ConDSeg: A General Medical Image Segmentation Framework via Contrast-Driven Feature Enhancement (AAAI 2025 · similarity 0.89)
- Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding (CVPR 2024 · similarity 0.88)
- Rethinking Decoder Design: Improving Biomarker Segmentation Using Depth-to-Space Restoration and Residual Linear Attention (CVPR 2025 · similarity 0.88)
- S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging (AAAI 2025 · similarity 0.87)
- Tyche: Stochastic In-Context Learning for Medical Image Segmentation (CVPR 2024 · 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.
