Research map / Graph learning / Knowledge and temporal graphs
Cross-View Correspondence Reasoning Based on Bipartite Graph Convolutional Network for Mammogram Mass Detection
Yuhang Liu, Fandong Zhang, Qianyi Zhang, Siwen Wang, Yizhou Wang, Yizhou Yu
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 |
|---|---|---|---|
| Use cross-view bipartite graph reasoning in place of the single-view detector | Mask RCNN, FPN, DCN · DDSM | R@1.0: 83.9 -> 86.6 | Improved |
| Use cross-view bipartite graph reasoning in place of the single-view detector | Mask RCNN, FPN, DCN · In-house dataset | R@1.0: 87.8 -> 90.5 | Improved |
| Use pseudo landmarks rather than uniform grids (ablation) | BG-RCNN · DDSM | R@0.5: 76.4 -> 79.5 | Improved |
| Vary the number of nodes across the tested configurations (ablation) | BG-RCNN · DDSM | R@0.5: 75.7; 79.5; 79.5; 76.0; 78.8 | Mixed |
| Use kNN node mapping instead of fixed-region cropping (ablation) | BG-RCNN with V21, U25 · DDSM | R@0.5: 76.4 -> 79.8 | Improved |
| Use kNN node mapping instead of fixed-region cropping (ablation) | BG-RCNN with V66, U71 · DDSM | R@0.5: 75.3 -> 79.1 | Improved |
| Vary k in kNN mapping (ablation) | BG-RCNN with V21, U25 · DDSM | R@0.5: 79.8; 79.5; 79.5 | No clear effect |
| Vary k in kNN mapping (ablation) | BG-RCNN with V66, U71 · DDSM | R@0.5: 77.7; 78.8; 79.1 | Improved |
| Add the geometric edge component (ablation) | BG-RCNN with semantic edges · DDSM | R@0.5: 77.7 -> 79.5 | Improved |
| Add the semantic edge component (ablation) | BG-RCNN with geometric edges · DDSM | R@0.5: 78.4 -> 79.5 | Improved |
Closest papers by meaning
- Act Like a Radiologist: Towards Reliable Multi-View Correspondence Reasoning for Mammogram Mass Detection (TPAMI 2021 · similarity 0.93)
- CSC-PA: Cross-image Semantic Correlation via Prototype Attentions for Single-network Semi-supervised Breast Tumor Segmentation (CVPR 2025 · similarity 0.82)
- NaFV-Net: An Adversarial Four-view Network for Mammogram Classification (AAAI 2025 · similarity 0.81)
- Cross-Modal Interactive Perception Network with Mamba for Lung Tumor Segmentation in PET-CT Images (CVPR 2025 · similarity 0.80)
- Interactive Medical Image Analysis with Concept-based Similarity Reasoning (CVPR 2025 · similarity 0.80)
- TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor Analysis (ICLR 2026 · 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.
