Radiology Report Generation

Follow this topic Ask about this topic

Radiology report generation studies how to turn images such as chest X-rays, CT scans, and MRI into clinical findings and impressions. Common approaches use vision-language models with image-text alignment, anatomical or disease-specific features, retrieval of similar cases, and structured clinical concepts; newer systems also use agents, reinforcement learning, and prior studies to guide or refine reports. The field has improved on language and clinical-label benchmarks, but fluent text can still omit findings, invent details, or miss their location and change over time. A central challenge is evaluating factual accuracy and usefulness across hospitals and modalities, since text similarity alone does not reliably measure clinical correctness.

Latest papers

159 papers20 papers in the last four weeks, up 5% on the four weeks before. 0.1% of all new papers.

Concept-Enhanced Multimodal RAG: Towards Interpretable and Accurate Radiology Report Generation
Feb 17, 2026Marco Salmè, Federico Siciliano, Fabrizio Silvestri +3Radiology Report Generation Radiology VLMs
Department of Engineering, Research Unit of Artificial Intelligence and Computer Systems, Università Campus Bio-Medico of Roma, Rome, Italy. · Department of Computer, Control and Management Engineering, Sapienza University of Rome, Rome, Italy. · Department of Diagnostics and Intervention, Radiation Physics, Biomedical Engineering, Umeå University, Umeå, Sweden. +1
Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generation
Feb 17, 2026Kaito Baba, Risa Kishikawa, Satoshi KoderaRadiology Report Generation Multimodal Agents
Department of Cardiovascular Medicine The University of Tokyo Hospital, Tokyo, Japan
LEAD: Layer-wise Expert-aligned Decoding for Faithful Radiology Report Generation
Feb 4, 2026Ruixiao Yang, Yuanhe Tian, Di Dong +3Radiology Report Generation Language Model Decoding
Beijing Institute of Technology · Zhongguancun Academy · Zhongguancun Institute of Artificial Intelligence +1
RadJEPA: Radiology Encoder for Chest X-Rays via Joint Embedding Predictive Architecture
Jan 22, 2026Anas Anwarul Haq Khan, Mariam Husain, Pratik Jalan +1Radiology Report Generation Medical Imaging
Department of Computer Science (CSE), Indian Institute of Technology Bombay, India · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE · Department of Biomedical Engineering, Johns Hopkins University, USA +1
HERO: Hierarchical Evidential Reasoning Optimization for Radiology Report Generation via Reason-then-Summarize
Jan 6, 2026Kun Zhao, Guodong Liu, Hui Ji +7Radiology Report Generation Medical VLMs
University of Pittsburgh · Eli and Lilly Company · The University of Manchester +1
Automatic Fine-grained Segmentation-assisted Report Generation
Jul 22, 2025Frederic Jonske, Constantin Seibold, Osman Alperen Koras +6Radiology Report Generation Radiology VLMs
Institute for AI in Medicine, University Medicine Essen Girardetstraße 2, 45131 Essen, Germany
Region-Aware Multimodal Large Language Model via SlowFast Tokenization and Pseudo-Mask Guidance for 3D CT Report Generation
Jun 29, 2025Sunggu Kyung, Jinyoung Seo, Hyunseok Lim +7Radiology Report Generation 3D Medical Imaging
Department of Convergence Medicine, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea · University of Ulsan College of Medicine, Seoul, Republic of Korea · Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea
Improving Factuality of 3D Brain MRI Report Generation with Paired Image-domain Retrieval and Text-domain Augmentation
Nov 23, 2024Junhyeok Lee, Yujin Oh, Dahyoun Lee +9Radiology Report Generation Retrieval-Augmented Generation
Cancer Biology, Seoul National University College of Medicine, Korea · Radiology, Massachusetts General Hospital and Harvard Medical School, USA · Biomedical Systems Informatics, Yonsei University College of Medicine, Korea +10
Multimodal Large Language Model driven Radiology Report Generation with Clinical Knowledge Enhancement
Mar 11, 2024Miaojing Shi, Tianyu Cen, Zijie Yue +3Radiology Report Generation Radiology VLMs
College of Electronic and Information Engineering, Tongji University, Shanghai, China

Feb 17, 2026J/K move · Enter open · S save

Concept-Enhanced Multimodal RAG: Towards Interpretable and Accurate Radiology Report Generation

Marco Salmè, Federico Siciliano, Fabrizio Silvestri, Paolo Soda+2

Department of Engineering, Research Unit of Artificial Intelligence and Computer Systems, Università Campus Bio-Medico of Roma, Rome, Italy. · Department of Computer, Control and Management Engineering, Sapienza University of Rome, Rome, Italy. · Department of Diagnostics and Intervention, Radiation Physics, Biomedical Engineering, Umeå University, Umeå, Sweden.+1

Radiology Report Generation Radiology VLMs Multimodal RAG VLM Hallucination Mitigation Multimodal Model Interpretability Concept-Based Explanations

Open paper AskPDF arXiv

Radiology Report Generation (RRG) through Vision-Language Models (VLMs) promises to reduce documentation burden, improve reporting consistency, and accelerate clinical workflows. However, their clinical adoption remains limited by the lack of interpretability and the tendency to hallucinate findings misaligned with imaging evidence. Existing research typically treats interpretability and accuracy as separate objectives, with concept-based explainability techniques focusing primarily on transparency, while Retrieval-Augmented Generation (RAG) methods targeting factual grounding through external retrieval. We present Concept-Enhanced Multimodal RAG (CEMRAG), a unified framework that decomposes visual representations into interpretable clinical concepts and integrates them with multimodal RAG. This approach exploits enriched contextual prompts for RRG, improving both interpretability and factual accuracy. Experiments on MIMIC-CXR and IU X-Ray across multiple VLM architectures, training regimes, and retrieval configurations demonstrate consistent improvements over both conventional RAG and concept-only baselines on clinical accuracy metrics and standard NLP measures. These results challenge the assumed trade-off between interpretability and performance, showing that transparent visual concepts can enhance rather than compromise diagnostic accuracy in medical VLMs. Our modular design decomposes interpretability into visual transparency and structured language model conditioning, providing a principled pathway toward clinically trustworthy AI-assisted radiology.