Research map / Vision-language and multimodal / Human and embodied modeling
A Self-Boosting Framework for Automated Radiographic Report Generation
Zhanyu Wang, Luping Zhou, Lei Wang, Xiu Li
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 image-text matching to the report-generation branch (ablation) | Radiographic report generation · IU-Xray | BLEU-4: 0.128 -> 0.155 | Improved |
| Add image-text matching to the report-generation branch (ablation) | Radiographic report generation · COV-CTR | BLEU-4: 0.573 -> 0.611 | Improved |
| Add feature-level loss (ablation) | Report generation with image-text matching · IU-Xray | BLEU-4: 0.155 -> 0.169 | Improved |
| Add feature-level loss (ablation) | Report generation with image-text matching · COV-CTR | BLEU-4: 0.611 -> 0.637 | Improved |
| Use self-boosted triplet loss for image-text matching (ablation) | Self-boosting report-generation framework · IU-Xray | BLEU-4: 0.155 -> 0.176 | Improved |
| Use self-boosted triplet loss for image-text matching (ablation) | Self-boosting report-generation framework · COV-CTR | BLEU-4: 0.611 -> 0.658 | Improved |
| Add reinforcement-learning refinement with CIDEr reward (ablation) | Self-boosting report-generation framework · IU-Xray | BLEU-4: 0.193 -> 0.208 | Improved |
| Add reinforcement-learning refinement with CIDEr reward (ablation) | Self-boosting report-generation framework · COV-CTR | BLEU-4: 0.672 -> 0.679 | Improved |
Closest papers by meaning
- DART: Disease-aware Image-Text Alignment and Self-correcting Re-alignment for Trustworthy Radiology Report Generation (CVPR 2025 · similarity 0.89)
- Automatic Radiology Reports Generation via Memory Alignment Network (AAAI 2024 · similarity 0.88)
- Bootstrapping Large Language Models for Radiology Report Generation (AAAI 2024 · similarity 0.88)
- DAMPER: A Dual-Stage Medical Report Generation Framework with Coarse-Grained MeSH Alignment and Fine-Grained Hypergraph Matching (AAAI 2025 · similarity 0.87)
- Image-aware Evaluation of Generated Medical Reports (NeurIPS 2024 · similarity 0.86)
- S2D-Align: Shallow-to-Deep Auxiliary Learning for Anatomically-Grounded Radiology Report Generation (AAAI 2026 · similarity 0.86)
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.
