Research map / Detection and segmentation / CNN features
MCPNet:Masked Coordinate Pooling-based Attention Network for Medical Landmark Detection
Gyu-Sung Ham, Gi Hyun Lim, Kanghan Oh
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 adaptive coordinate maps generated from Estat (ablation) | MCPNet · ISBI2015 Test1 | SDR@2mm (%): 87.04 -> 88.89 | Improved |
| add adaptive coordinate maps generated from Estat (ablation) | MCPNet · DHA | SDR@2mm (%): 96.33 -> 96.94 | Improved |
| add adaptive coordinate maps generated from Estat (ablation) | MCPNet · ISBI2015 Test1 | MRE (mm): 1.111 -> 1.074 | Improved |
| generate Sadapt from Estat instead of GAP of X (ablation) | MCPNet · ISBI2015 Test1 | SDR@2mm (%): 88.35 -> 88.89 | Improved |
| generate Sadapt from GAP of X instead of none (ablation) | MCPNet · ISBI2015 Test1 | SDR@2mm (%): 87.04 -> 88.35 | Improved |
| use 60 adaptive coordinate maps instead of 10 (ablation) | MCPNet · ISBI2015 Test1 | SDR@2mm (%): 87.62 -> 88.89 | Improved |
| use 60 adaptive coordinate maps instead of 100 (ablation) | MCPNet · DHA | MRE (mm): 0.601 -> 0.565 | Improved |
| widen U-Net to match MCPNet parameter count (ablation) | U-Net · ISBI2015 Test1 | SDR@2mm (%): 86.22 -> 86.35 | No clear effect |
| replace U-Net with MCPNet attention | U-Net · Chest X-ray | SDR@3px (%): 50.85 -> 55.33 | Improved |
| replace CBAM with MCPNet attention | CBAM · 3D Spine | MRE (mm): 6.3 -> 5.3 | Improved |
| replace PE with MCPNet | PE · 3D Skull CT | MRE (mm): 1.63 -> 1.58 | Improved |
| replace HTC with MCPNet | HTC · DHA | SDR@2mm (%): 96.84 -> 96.94 | Improved |
Closest papers by meaning
- Facial Landmark Detection with Tweaked Convolutional Neural Networks (TPAMI 2017 · similarity 0.85)
- One-Shot Medical Landmark Localization by Edge-Guided Transform and Noisy Landmark Refinement (ECCV 2022 · similarity 0.85)
- Domain Generalized Medical Landmark Detection via Robust Boundary-Aware Pre-Training (AAAI 2025 · similarity 0.85)
- Facial Landmarks Detection by Self-Iterative Regression Based Landmarks-Attention Network (AAAI 2018 · similarity 0.84)
- Structured Landmark Detection via Topology-Adapting Deep Graph Learning (ECCV 2020 · similarity 0.84)
- Continuous Landmark Detection With 3D Queries (CVPR 2023 · similarity 0.84)
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.
