Research map / Detection and segmentation / Tracking
Robust Landmark-Based Stent Tracking in X-Ray Fluoroscopy
Luojie Huang, Yikang Liu, Li Chen, Eric Z. Chen, Xiao Chen, Shanhui Sun
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 ResNet patch classifier refinement to U-Net detection (ablation) | landmark detector · In-house dataset | precision: 0.551 -> 0.927 | Improved |
| add ResNet patch classifier refinement to U-Net detection (ablation) | landmark detector · In-house dataset | recall: 0.918 -> 0.532 | Hurt |
| add GCN temporal tracking (separate learning) after detection refinement (ablation) | stent tracker · In-house dataset | accuracy: 0.511 -> 0.790 | Improved |
| train all modules end to end instead of separately (ablation) | stent tracker · In-house dataset | accuracy: 0.790 -> 0.831 | Improved |
| train all modules end to end instead of separately (ablation) | stent tracker · In-house dataset | F1: 0.883 -> 0.908 | Improved |
| train all modules end to end instead of separately (ablation) | stent tracker · In-house dataset | MAE: 0.596 -> 0.597 | No clear effect |
| use full proposed framework instead of CenterTrack DLA34 | stent tracker · In-house dataset | accuracy: 0.568 -> 0.831 | Improved |
| use full proposed framework instead of CenterTrack DLA34 | stent tracker · TAVI dataset | accuracy: 0.815 -> 0.882 | Improved |
| use full proposed framework instead of CenterTrack DLA34 | stent tracker · In-house dataset | MAE: 0.398 -> 0.597 | Hurt |
| heatmap regression instead of coordinate regression | landmark tracker · In-house dataset | recall: 0.604 -> 0.936 | Improved |
| use U-Net localization instead of CenterTrack DLA34 | localization · Inference speed | FPS: 10.1 -> 21.7 | Improved |
Closest papers by meaning
- DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentation (CVPR 2025 · similarity 0.83)
- Label-Efficient Data Augmentation with Video Diffusion Models for Guidewire Segmentation in Cardiac Fluoroscopy (AAAI 2025 · similarity 0.82)
- Intraoperative 2D/3D Image Registration via Differentiable X-ray Rendering (CVPR 2024 · similarity 0.81)
- Bridging Vision and Language for Robust Context-Aware Surgical Point Tracking: The VL-SurgPT Dataset and Benchmark (AAAI 2026 · similarity 0.80)
- GaraMoSt: Parallel Multi-Granularity Motion and Structural Modeling for Efficient Multi-Frame Interpolation in DSA Images (AAAI 2025 · similarity 0.80)
- PolyPose: Deformable 2D/3D Registration via Polyrigid Transformations (NeurIPS 2025 · similarity 0.80)
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.
