Clinically Accurate Chest X-Ray Report Generation
Not on the map. Why?
Abstract (arXiv)
The automatic generation of radiology reports given medical radiographs has significant potential to operationally and improve clinical patient care. A number of prior works have focused on this problem, employing advanced methods from computer vision and natural language generation to produce readable reports. However, these works often fail to account for the particular nuances of the radiology domain, and, in particular, the critical importance of clinical accuracy in the resulting generated reports. In this work, we present a domain-aware automatic chest X-ray radiology report generation system which first predicts what topics will be discussed in the report, then conditionally generates sentences corresponding to these topics. The resulting system is fine-tuned using reinforcement learning, considering both readability and clinical accuracy, as assessed by the proposed Clinically Coherent Reward. We verify this system on two datasets, Open-I and MIMIC-CXR, and demonstrate that our model offers marked improvements on both language generation metrics and CheXpert assessed accuracy over a variety of competitive baselines.
Key facts. Cited by 138 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Apr 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 16; 2022: 24; 2023: 30; 2024: 30; 2025: 22; 2026: 16.
138 papers.
Sort:
By area:
- 2022Making the Most of Text Semantics to Improve Biomedical Vision--Language Processingcited by 336
- 2023Towards Generalist Biomedical AIcited by 286
- 2022Cross-modal Memory Networks for Radiology Report Generationcited by 183
- 2023Conformal Language Modelingcited by 163
- 2024MAIRA-2: Grounded Radiology Report Generationcited by 140
- 2023Interactive and Explainable Region-guided Radiology Report Generationcited by 139
- 2021TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generationcited by 118
- 2023ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using Large Language Modelscited by 116
- 2021Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Trainingcited by 96
- 2022Improving Chest X-Ray Report Generation by Leveraging Warm Startingcited by 93
- 2021Chest ImaGenome Dataset for Clinical Reasoningcited by 89
- 2022Improving the Factual Correctness of Radiology Report Generation with Semantic Rewardscited by 82
38 more
- 2022Competence-based Multimodal Curriculum Learning for Medical Report Generationcited by 74
- 2023MAIRA-1: A specialised large multimodal model for radiology report generationcited by 72
- 2021Contrastive Attention for Automatic Chest X-ray Report Generationcited by 71
- 2024FairCLIP: Harnessing Fairness in Vision-Language Learningcited by 69
- 2022AlignTransformer: Hierarchical Alignment of Visual Regions and Disease Tags for Medical Report Generationcited by 65
- 2023KiUT: Knowledge-injected U-Transformer for Radiology Report Generationcited by 60
- 2022Cross-modal Prototype Driven Network for Radiology Report Generationcited by 58
- 2023Towards a Visual-Language Foundation Model for Computational Pathologycited by 52
- 2022Improving Radiology Report Generation Systems by Removing Hallucinated References to Non-existent Priorscited by 48
- 2021Progressive Transformer-Based Generation of Radiology Reportscited by 43
- 2023CLIP in Medical Imaging: A Surveycited by 40
- 2021Weakly Supervised Contrastive Learning for Chest X-Ray Report Generationcited by 39
- 2023ORGAN: Observation-Guided Radiology Report Generation via Tree Reasoningcited by 39
- 2023A Systematic Evaluation of GPT-4V's Multimodal Capability for Medical Image Analysiscited by 37
- 2021RATCHET: Medical Transformer for Chest X-ray Diagnosis and Reportingcited by 34
- 2023Cascaded Latent Diffusion Models for High-Resolution Chest X-ray Synthesiscited by 32
- 2022Explainable Deep Learning Methods in Medical Image Classification: A Surveycited by 31
- 2023WsiCaption: Multiple Instance Generation of Pathology Reports for Gigapixel Whole-Slide Imagescited by 31
- 2024Towards a Holistic Framework for Multimodal Large Language Models in Three-dimensional Brain CT Report Generationcited by 30
- 2024Libra: Leveraging Temporal Images for Biomedical Radiology Analysiscited by 29
- 2023Advancing Medical Imaging with Language Models: A Journey from N-grams to ChatGPTcited by 28
- 2022Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methodscited by 27
- 2021Automated Generation of Accurate & Fluent Medical X-ray Reportscited by 24
- 2022Graph Enhanced Contrastive Learning for Radiology Findings Summarizationcited by 24
- 2023Longitudinal Data and a Semantic Similarity Reward for Chest X-Ray Report Generationcited by 24
- 2024Large Language Models in Drug Discovery and Development: From Disease Mechanisms to Clinical Trialscited by 24
- 2023Unify, Align and Refine: Multi-Level Semantic Alignment for Radiology Report Generationcited by 23
- 2023Controllable Chest X-Ray Report Generation from Longitudinal Representationscited by 23
- 2024AutoRG-Brain: Grounded Report Generation for Brain MRIcited by 23
- 2023Rationalization for Explainable NLP: A Surveycited by 22
- 2023RECAP: Towards Precise Radiology Report Generation via Dynamic Disease Progression Reasoningcited by 22
- 2022CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generationcited by 21
- 2022Medical Image Captioning via Generative Pretrained Transformerscited by 20
- 2021Writing by Memorizing: Hierarchical Retrieval-based Medical Report Generationcited by 19
- 2024Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlookscited by 18
- 2022Attributed Abnormality Graph Embedding for Clinically Accurate X-Ray Report Generationcited by 17
- 2021Variational Topic Inference for Chest X-Ray Report Generationcited by 16
- 2022RepsNet: Combining Vision with Language for Automated Medical Reportscited by 14
50 most cited of 138 All 138 (JSON)
- 2026The Diagnosis a Reporter Leaves Unspoken: Surfacing Frozen Tumor Features for Brain-Tumor MRI Reporting2 Sep 2026
- 2026AFDBench: A Reasoning-First AI Scientist for NationalWeather Service Forecast Discussions25 Aug 2026
- 2026Example-based Robust Abnormality Detection with Minimal Annotations using Exemplar Med-DETR25 Aug 2026
- 2026MIRROR: Multimodal Intelligent Radiology Reasoning and Observation Reporter17 Aug 2026
- 2026Transition-Aware best-of-N sampling for Longitudinal Chest X-ray Reports23 Jun 2026
- 2026RadOT-Eval: Auditable Structured-Evidence Transport for Radiology Report Evaluation7 Jun 2026
- 2026RL-ACRGNet: Reinforcement Learning-Based Chest Radiology Report Generation Network1 Jun 2026
- 2026SDR: Set-Distance Rewards for Radiology Report Generation30 May 2026
- 2026CCS: Clinical Consensus Selection for Radiology Report Generation28 May 2026
- 2026Graph-Augmented Topological Internalization with Dual-Stream Classifiers for Medical Report Generation4 May 2026
- 2026CXRMate-2: Structured Multimodal Temporal Embeddings and Tractable Reinforcement Learning for Clinically Acceptable Chest X-ray Radiology Report Generation21 Apr 2026
- 2026Automated Histopathology Report Generation via Pyramidal Feature Extraction and the UNI Foundation Model18 Feb 2026
38 more
- 2026Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generation17 Feb 2026
- 2026BTReport: A Framework for Brain Tumor Radiology Report Generation with Clinically Relevant Features17 Feb 2026
- 2026Scaling medical imaging report generation with multimodal reinforcement learning23 Jan 2026
- 2026Hallucination Mitigating for Medical Report Generation22 Jan 2026
- 2025EIR: Enhanced Image Representations for Medical Report Generation29 Dec 2025
- 2025Radiology Report Generation with Layer-Wise Anatomical Attention18 Dec 2025
- 2025MRG-R1: Reinforcement Learning for Clinically Aligned Medical Report Generation18 Dec 2025
- 2025Automated Structured Radiology Report Generation with Rich Clinical Context1 Oct 2025
- 2025CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding27 Sep 2025
- 2025EditGRPO: Reinforcement Learning with Post-Rollout Edits for Clinically Accurate Chest X-Ray Report Generation26 Sep 2025
- 2025Random Direct Preference Optimization for Radiography Report Generation19 Sep 2025
- 2025Lesion-Aware Visual-Language Fusion for Automated Image Captioning of Ulcerative Colitis Endoscopic Examinations3 Sep 2025
- 2025Improving Performance, Robustness, and Fairness of Radiographic AI Models with Finely-Controllable Synthetic Data22 Aug 2025
- 2025Eyes on the Image: Gaze Supervised Multimodal Learning for Chest X-ray Diagnosis and Report Generation18 Aug 2025
- 2025A Chain of Diagnosis Framework for Accurate and Explainable Radiology Report Generation13 Aug 2025
- 2025CT-GRAPH: Hierarchical Graph Attention Network for Anatomy-Guided CT Report Generation7 Aug 2025
- 2025Semantically Informed Salient Regions Guided Radiology Report Generation15 Jul 2025
- 2025Improving Medical Visual Representation Learning with Pathological-level Cross-Modal Alignment and Correlation Exploration12 Jun 2025
- 2025LLaMA-XR: A Novel Framework for Radiology Report Generation using LLaMA and QLoRA Fine Tuning29 May 2025
- 2025Privacy-Preserving Chest X-ray Report Generation via Multimodal Federated Learning with ViT and GPT-227 May 2025
- 2025MicarVLMoE: A Modern Gated Cross-Aligned Vision-Language Mixture of Experts Model for Medical Image Captioning and Report Generation29 Apr 2025
- 2025DualPrompt-MedCap: A Dual-Prompt Enhanced Approach for Medical Image Captioning13 Apr 2025
- 2025MedRep: Medical Concept Representation for General Electronic Health Record Foundation Models11 Apr 2025
- 2025MedM-VL: What Makes a Good Medical LVLM?6 Apr 2025
- 2025Med-R2: Perception and Reflection-driven Complex Reasoning for Medical Report Generation2 Apr 2025
- 2025Abn-BLIP: Abnormality-aligned Bootstrapping Language-Image Pre-training for Pulmonary Embolism Diagnosis and Report Generation from CTPA3 Mar 2025
- 2024Integrating MedCLIP and Cross-Modal Fusion for Automatic Radiology Report Generation10 Dec 2024
- 2024MedAutoCorrect: Image-Conditioned Autocorrection in Medical Reporting4 Dec 2024
- 2024Libra: Leveraging Temporal Images for Biomedical Radiology Analysis28 Nov 2024
- 2024A Survey of Medical Vision-and-Language Applications and Their Techniques19 Nov 2024
- 2024Anatomy-Guided Radiology Report Generation with Pathology-Aware Regional Prompts16 Nov 2024
- 2024Cyclic Vision-Language Manipulator: Towards Reliable and Fine-Grained Image Interpretation for Automated Report Generation8 Nov 2024
- 2024Designing a Robust Radiology Report Generation System2 Nov 2024
- 2024Image-aware Evaluation of Generated Medical Reports22 Oct 2024
- 2024Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks3 Oct 2024
- 2024Large Language Models in Drug Discovery and Development: From Disease Mechanisms to Clinical Trials6 Sep 2024
- 2024FODA-PG for Enhanced Medical Imaging Narrative Generation: Adaptive Differentiation of Normal and Abnormal Attributes6 Sep 2024
- 2024CT-AGRG: Automated Abnormality-Guided Report Generation from 3D Chest CT Volumes21 Aug 2024
50 newest of 138 All 138 (JSON)
- 2021Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Trainingcited by 96
- 2023MAIRA-1: A specialised large multimodal model for radiology report generationcited by 72
- 2024Towards a Holistic Framework for Multimodal Large Language Models in Three-dimensional Brain CT Report Generationcited by 30
- 2025CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decodingcited by 4
- 2023Effectively Fine-tune to Improve Large Multimodal Models for Radiology Report Generationcited by 3
- 2024TiBiX: Leveraging Temporal Information for Bidirectional X-ray and Report Generationcited by 3
- 2025Eyes on the Image: Gaze Supervised Multimodal Learning for Chest X-ray Diagnosis and Report Generationcited by 1
- 2025DualPrompt-MedCap: A Dual-Prompt Enhanced Approach for Medical Image Captioningcited by 0
- 2025CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding27 Sep 2025
- 2025Eyes on the Image: Gaze Supervised Multimodal Learning for Chest X-ray Diagnosis and Report Generation18 Aug 2025
- 2025DualPrompt-MedCap: A Dual-Prompt Enhanced Approach for Medical Image Captioning13 Apr 2025
- 2024Towards a Holistic Framework for Multimodal Large Language Models in Three-dimensional Brain CT Report Generation2 Jul 2024
- 2024TiBiX: Leveraging Temporal Information for Bidirectional X-ray and Report Generation20 Mar 2024
- 2023Effectively Fine-tune to Improve Large Multimodal Models for Radiology Report Generation3 Dec 2023
- 2023MAIRA-1: A specialised large multimodal model for radiology report generation22 Nov 2023
- 2021Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training24 May 2021
- 2025EditGRPO: Reinforcement Learning with Post-Rollout Edits for Clinically Accurate Chest X-Ray Report Generationcited by 3
- 2026SDR: Set-Distance Rewards for Radiology Report Generationcited by 2
- 2025Med-R2: Perception and Reflection-driven Complex Reasoning for Medical Report Generationcited by 1
- 2026AFDBench: A Reasoning-First AI Scientist for NationalWeather Service Forecast Discussionscited by 0
- 2026AFDBench: A Reasoning-First AI Scientist for NationalWeather Service Forecast Discussions25 Aug 2026
- 2026SDR: Set-Distance Rewards for Radiology Report Generation30 May 2026
- 2025EditGRPO: Reinforcement Learning with Post-Rollout Edits for Clinically Accurate Chest X-Ray Report Generation26 Sep 2025
- 2025Med-R2: Perception and Reflection-driven Complex Reasoning for Medical Report Generation2 Apr 2025
- 2022Making the Most of Text Semantics to Improve Biomedical Vision--Language Processingcited by 336
- 2023Towards Generalist Biomedical AIcited by 286
- 2022Cross-modal Memory Networks for Radiology Report Generationcited by 183
- 2023Conformal Language Modelingcited by 163
- 2024MAIRA-2: Grounded Radiology Report Generationcited by 140
- 2023Interactive and Explainable Region-guided Radiology Report Generationcited by 139
- 2021TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generationcited by 118
- 2023ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using Large Language Modelscited by 116
- 2022Improving Chest X-Ray Report Generation by Leveraging Warm Startingcited by 93
- 2021Chest ImaGenome Dataset for Clinical Reasoningcited by 89
- 2022Improving the Factual Correctness of Radiology Report Generation with Semantic Rewardscited by 82
- 2022Competence-based Multimodal Curriculum Learning for Medical Report Generationcited by 74
12 most cited of 122 All 122 (JSON)
- 2026The Diagnosis a Reporter Leaves Unspoken: Surfacing Frozen Tumor Features for Brain-Tumor MRI Reporting2 Sep 2026
- 2026Example-based Robust Abnormality Detection with Minimal Annotations using Exemplar Med-DETR25 Aug 2026
- 2026MIRROR: Multimodal Intelligent Radiology Reasoning and Observation Reporter17 Aug 2026
- 2026Transition-Aware best-of-N sampling for Longitudinal Chest X-ray Reports23 Jun 2026
- 2026RadOT-Eval: Auditable Structured-Evidence Transport for Radiology Report Evaluation7 Jun 2026
- 2026RL-ACRGNet: Reinforcement Learning-Based Chest Radiology Report Generation Network1 Jun 2026
- 2026CCS: Clinical Consensus Selection for Radiology Report Generation28 May 2026
- 2026Graph-Augmented Topological Internalization with Dual-Stream Classifiers for Medical Report Generation4 May 2026
- 2026CXRMate-2: Structured Multimodal Temporal Embeddings and Tractable Reinforcement Learning for Clinically Acceptable Chest X-ray Radiology Report Generation21 Apr 2026
- 2026Automated Histopathology Report Generation via Pyramidal Feature Extraction and the UNI Foundation Model18 Feb 2026
- 2026BTReport: A Framework for Brain Tumor Radiology Report Generation with Clinically Relevant Features17 Feb 2026
- 2026Scaling medical imaging report generation with multimodal reinforcement learning23 Jan 2026
12 newest of 122 All 122 (JSON)