Research map / Vision-language and multimodal / Multimodal LLMs
Rethinking Radiology Report Generation: From Narrative Flow to Topic-Guided Findings
Sheng Cheng, Devika Subramanian
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Argues that training radiology VLMs to mimic the narrative flow of expert reports encourages linguistic priors over visual grounding, and proposes topic-guided findings generation as an alternative.
Problem
Vision-language models for radiology report generation are trained to reproduce the narrative flow of human reports, which may weaken grounding in visual evidence and cause factual inaccuracies.
Approach
Reframes report generation from narrative flow to topic-guided findings, hypothesizing that organizing generation around topics rather than inter-sentence narrative reduces reliance on linguistic priors and improves visual grounding.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| train on single-topic queries instead of concatenated narrative of all topics (ablation) | LLaVA-TA with MLP+LLM tuning · MIMIC-CXR (topic-level) | RadGraph F1: 27.8 -> 46.5 | Improved |
| replace narrative reports with topic-decomposed data (LLaVA-T) (ablation) | LLaVA-Rad · MIMIC-CXR (report-level) | CheXpert Macro-F1-14: 40.1 -> 63.0 | Improved |
| add topic decomposition (ablation) | LLaVA-Rad · MIMIC-CXR (report-level) | RadGraph F1: 30.8 -> 34.2 | Improved |
| add anatomy masks when full LLM is tuned (ablation) | LLaVA-T · MIMIC-CXR (report-level) | RadGraph F1: 34.2 -> 34.3 | No clear effect |
| add anatomy masks when only MLP is tuned (ablation) | LLaVA-T · MIMIC-CXR (topic-level, MLP-only) | RadGraph F1: 5.8 -> 41.4 | Improved |
| add anatomy masks when only MLP is tuned (ablation) | LLaVA-T · IU-Xray (report-level, MLP-only) | RadGraph F1: 6.8 -> 34.0 | Improved |
| clean reports (remove comparisons and speculation) without topic split (ablation) | LLaVA-Rad · MIMIC-CXR (MLP+LLM) | RadGraph F1: 30.8 -> 32.4 | Improved |
| clean reports without topic split, MLP-only tuning (ablation) | LLaVA-Rad · MIMIC-CXR (MLP-only) | RadGraph F1: 19.8 -> 10.4 | Hurt |
| concatenate all topic sentences as target (allGTTopic) instead of original narrative (ablation) | LLaVA-Rad · MIMIC-CXR (MLP+LLM) | RadGraph F1: 30.8 -> 27.2 | Mixed |
| use topic-guided training instead of narrative training on out-of-distribution data | LLaVA-TA · IU-Xray (MLP+LLM) | RadGraph F1: 19.8 -> 31.4 | Improved |
| use topic-guided plus anatomy training vs narrative baseline | LLaVA-TA · MS-CXR | Hit score (%): 29.2 -> 59.2 | Improved |
| randomly drop 1-2 topics from 5% of training samples (ablation) | LLaVA-TA (MLP-only) · MIMIC-CXR | RadGraph F1: 41.4 -> 40.9 | No clear effect |
Closest papers by meaning
- LLM-RG4: Flexible and Factual Radiology Report Generation Across Diverse Input Contexts (AAAI 2025 · similarity 0.90)
- CURE: Curriculum-guided Multi-task Training for Reliable Anatomy Grounded Report Generation (CVPR 2026 · similarity 0.90)
- AHIVE: Anatomy-aware Hierarchical Vision Encoding for Interactive Radiology Report Retrieval (CVPR 2024 · similarity 0.89)
- Bootstrapping Large Language Models for Radiology Report Generation (AAAI 2024 · similarity 0.88)
- HC-LLM: Historical-Constrained Large Language Models for Radiology Report Generation (AAAI 2025 · similarity 0.88)
- S2D-Align: Shallow-to-Deep Auxiliary Learning for Anatomically-Grounded Radiology Report Generation (AAAI 2026 · 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.
