Research map / Vision-language and multimodal / Human and embodied modeling
A Disease-Aware Dual-Stage Framework for Chest X-ray Report Generation
Puzhen Wu, Hexin Dong, Yi Lin, Yihao Ding, Yifan Peng
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 DASTs and DVAF fusion to visual-token baseline (ablation) | Report generator · CheXpert Plus test | CIDEr: 0.193 -> 0.206 | Improved |
| add DMSR retrieval of similar exemplar (ablation) | Report generator with DASTs+DVAF · CheXpert Plus test | CIDEr: 0.206 -> 0.227 | Improved |
| add DMSR retrieval (ablation) | Report generator with DASTs+DVAF · IU X-Ray test | CIDEr: 0.597 -> 0.634 | Improved |
| add DASTs and DVAF (ablation) | Report generator · IU X-Ray test | BLEU4: 0.161 -> 0.175 | Improved |
| use DVAF instead of simple concatenation (ablation) | DASTs fusion · CheXpert Plus test | CIDEr: 0.188 -> 0.206 | Improved |
| use DVAF instead of mean pooling (ablation) | DASTs fusion · IU X-Ray test | CIDEr: 0.553 -> 0.597 | Improved |
| use full method versus MambaXray | Ours · CheXpert Plus test | clinical F1: 0.335 -> 0.361 | Improved |
| use full method versus MambaXray | Ours · MIMIC-CXR test | CIDEr: 0.241 -> 0.232 | Hurt |
| use full method versus MambaXray | Ours · MIMIC-CXR test | BLEU4: 0.133 -> 0.131 | No clear effect |
| use full method versus MambaXray | Ours · IU X-Ray test | CIDEr: 0.524 -> 0.634 | Improved |
Closest papers by meaning
- Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report Generation (CVPR 2025 · similarity 0.90)
- Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models (CVPR 2024 · similarity 0.89)
- DART: Disease-aware Image-Text Alignment and Self-correcting Re-alignment for Trustworthy Radiology Report Generation (CVPR 2025 · similarity 0.89)
- CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays (NeurIPS 2025 · similarity 0.89)
- RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Chest X-ray with Zero-Shot Multi-Task Capability (NeurIPS 2025 · similarity 0.88)
- BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays (NeurIPS 2024 · similarity 0.88)
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.
