Research map / Vision-language and multimodal / Human and embodied modeling
Knowledge-Driven Encode, Retrieve, Paraphrase for Medical Image Report Generation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 KERP instead of the strongest listed baseline | medical report generation · IU X-Ray | BLEU-1: 0.455 -> 0.482 | Helped |
| use KERP instead of the strongest listed baseline | medical report generation · IU X-Ray | CIDEr: 0.343 -> 0.280 | Hurt |
| use KERP instead of the strongest listed baseline | medical report generation · CX-CHR | ROUGE-L: 0.612 -> 0.618 | Helped |
| use KERP instead of the strongest listed baseline | medical report generation · CX-CHR | CIDEr: 2.895 -> 2.850 | Hurt |
| add the Paraphrase module to retrieved templates (ablation) | KER · IU X-Ray | BLEU-1: 0.455 -> 0.482 | Helped |
| add the Paraphrase module to retrieved templates (ablation) | KER · IU X-Ray | CIDEr: 0.318 -> 0.280 | Hurt |
| add the Paraphrase module to retrieved templates (ablation) | KER · CX-CHR | BLEU-1: 0.609 -> 0.673 | Helped |
| jointly train abnormality and disease classification using two graphs (ablation) | Ours-1Graph · IU X-Ray | Abnormality AUC: 0.674 -> 0.686 | Helped |
| jointly train abnormality and disease classification using two graphs (ablation) | Ours-1Graph · CX-CHR | Abnormality AUC: 0.721 -> 0.760 | Helped |
| use two graphs rather than DenseNet | classification · IU X-Ray | Disease AUC: 0.646 -> 0.726 | Helped |
| use two graphs rather than DenseNet | classification · CX-CHR | Disease AUC: 0.800 -> 0.862 | Helped |
Closest papers by meaning
- DAMPER: A Dual-Stage Medical Report Generation Framework with Coarse-Grained MeSH Alignment and Fine-Grained Hypergraph Matching (AAAI 2025 · similarity 0.86)
- LLaVA Needs More Knowledge: Retrieval Augmented Natural Language Generation with Knowledge Graph for Explaining Thoracic Pathologies (AAAI 2025 · similarity 0.86)
- Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval (ICLR 2025 · similarity 0.86)
- KPL: Training-Free Medical Knowledge Mining of Vision-Language Models (AAAI 2025 · similarity 0.85)
- Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis (CVPR 2025 · similarity 0.85)
- PromptMRG: Diagnosis-Driven Prompts for Medical Report Generation (AAAI 2024 · 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.