mlsanityData to 7 Oct 2026

Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation

arXiv 2303.10323 ↗First posted 18 Mar 2023cs.CVcited by 114

Not on the map. Why?

Abstract (arXiv)

Automatic radiology reporting has great clinical potential to relieve radiologists from heavy workloads and improve diagnosis interpretation. Recently, researchers have enhanced data-driven neural networks with medical knowledge graphs to eliminate the severe visual and textual bias in this task. The structures of such graphs are exploited by using the clinical dependencies formed by the disease topic tags via general knowledge and usually do not update during the training process. Consequently, the fixed graphs can not guarantee the most appropriate scope of knowledge and limit the effectiveness. To address the limitation, we propose a knowledge graph with Dynamic structure and nodes to facilitate medical report generation with Contrastive Learning, named DCL. In detail, the fundamental structure of our graph is pre-constructed from general knowledge. Then we explore specific knowledge extracted from the retrieved reports to add additional nodes or redefine their relations in a bottom-up manner. Each image feature is integrated with its very own updated graph before being fed into the decoder module for report generation. Finally, this paper introduces Image-Report Contrastive and Image-Report Matching losses to better represent visual features and textual information. Evaluated on IU-Xray and MIMIC-CXR datasets, our DCL outperforms previous state-of-the-art models on these two benchmarks.

Key facts. Cited by 114 papers in the map (data through 7 Oct 2026). Builds on 34 of its 52 references that are in the map. First posted on arXiv 18 Mar 2023.

Builds on

34 of 52 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2016Layer Normalizationcited by 5,579
  7. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  8. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,027
  9. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,612
  10. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  11. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,404
  12. 2017Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answeringcited by 1,310
22 more
  1. 2020Contrastive Learning of Medical Visual Representations from Paired Images and Textcited by 636
  2. 2019MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographscited by 590
  3. 2020Generating Radiology Reports via Memory-driven Transformercited by 363
  4. 2021RadGraph: Extracting Clinical Entities and Relations from Radiology Reportscited by 310
  5. 2019K-BERT: Enabling Language Representation with Knowledge Graphcited by 303
  6. 2018A Comprehensive Survey of Deep Learning for Image Captioningcited by 213
  7. 2022Cross-modal Memory Networks for Radiology Report Generationcited by 183
  8. 2021Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generationcited by 160
  9. 2020When Radiology Report Generation Meets Knowledge Graphcited by 144
  10. 2018Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generationcited by 141
  11. 2019Knowledge-driven Encode, Retrieve, Paraphrase for Medical Image Report Generationcited by 101
  12. 2022Competence-based Multimodal Curriculum Learning for Medical Report Generationcited by 74
  13. 2021Contrastive Attention for Automatic Chest X-ray Report Generationcited by 71
  14. 2021Knowledge Matters: Radiology Report Generation with General and Specific Knowledgecited by 68
  15. 2022Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discriminationcited by 67
  16. 2016Learning to Read Chest X-Rays: Recurrent Neural Cascade Model for Automated Image Annotationcited by 59
  17. 2021Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generationcited by 47
  18. 2021Progressive Transformer-Based Generation of Radiology Reportscited by 43
  19. 2021Weakly Supervised Contrastive Learning for Chest X-Ray Report Generationcited by 39
  20. 2020Auxiliary Signal-Guided Knowledge Encoder-Decoder for Medical Report Generationcited by 35
  21. 2022Cross-modal Clinical Graph Transformer for Ophthalmic Report Generationcited by 24
  22. 2022Representative Image Feature Extraction via Contrastive Learning Pretraining for Chest X-ray Report Generationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 15; 2024: 40; 2025: 36; 2026: 23.

114 papers.

Sort:

By area:

  1. 2024MAIRA-2: Grounded Radiology Report Generationcited by 140
  2. 2024GREEN: Generative Radiology Report Evaluation and Error Notationcited by 124
  3. 2023R2GenGPT: Radiology Report Generation with Frozen LLMscited by 111
  4. 2024CT2Rep: Automated Radiology Report Generation for 3D Medical Imagingcited by 96
  5. 2023PromptMRG: Diagnosis-Driven Prompts for Medical Report Generationcited by 92
  6. 2024State Space Model for New-Generation Network Alternative to Transformers: A Surveycited by 59
  7. 2024VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledgecited by 50
  8. 2025Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report Generationcited by 39
  9. 2023A Systematic Evaluation of GPT-4V's Multimodal Capability for Medical Image Analysiscited by 37
  10. 2024CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Datasetcited by 33
  11. 2024HERGen: Elevating Radiology Report Generation with Longitudinal Datacited by 32
  12. 2024Libra: Leveraging Temporal Images for Biomedical Radiology Analysiscited by 29
38 more
  1. 2024Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Modelscited by 24
  2. 2024AutoRG-Brain: Grounded Report Generation for Brain MRIcited by 23
  3. 2023RECAP: Towards Precise Radiology Report Generation via Dynamic Disease Progression Reasoningcited by 22
  4. 2023Complex Organ Mask Guided Radiology Report Generationcited by 22
  5. 2023Self-supervised Cross-view Representation Reconstruction for Change Captioningcited by 20
  6. 2024Has Multimodal Learning Delivered Universal Intelligence in Healthcare? A Comprehensive Surveycited by 20
  7. 2024ChEX: Interactive Localization and Region Description in Chest X-rayscited by 18
  8. 2024Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlookscited by 18
  9. 2024Multimodal Large Language Model driven Radiology Report Generation with Clinical Knowledge Enhancementcited by 16
  10. 2024M4CXR: Exploring Multi-task Potentials of Multi-modal Large Language Models for Chest X-ray Interpretationcited by 16
  11. 2023A Systematic Review of Deep Learning-based Research on Radiology Report Generationcited by 14
  12. 2024Structural Entities Extraction and Patient Indications Incorporation for Chest X-ray Report Generationcited by 14
  13. 2024Memorization in deep learning: A surveycited by 14
  14. 2023RadGraph2: Modeling Disease Progression in Radiology Reports via Hierarchical Information Extractioncited by 11
  15. 2024Memory-based Cross-modal Semantic Alignment Network for Radiology Report Generationcited by 11
  16. 2024R2GenCSR: Mining Contextual and Residual Information for LLMs-based Radiology Report Generationcited by 11
  17. 2024A Survey of Medical Vision-and-Language Applications and Their Techniquescited by 11
  18. 2025Activating Associative Disease-Aware Vision Token Memory for LLM-Based X-ray Report Generationcited by 11
  19. 2025MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representationscited by 11
  20. 2025RADAR: Enhancing Radiology Report Generation with Supplementary Knowledge Injectioncited by 11
  21. 2024CheX-GPT: Harnessing Large Language Models for Enhanced Chest X-ray Report Labelingcited by 10
  22. 2024Factual Serialization Enhancement: A Key Innovation for Chest X-ray Report Generationcited by 10
  23. 2023Customizing General-Purpose Foundation Models for Medical Report Generationcited by 9
  24. 2024HC-LLM: Historical-Constrained Large Language Models for Radiology Report Generationcited by 9
  25. 2025DART: Disease-aware Image-Text Alignment and Self-correcting Re-alignment for Trustworthy Radiology Report Generationcited by 9
  26. 2025PriorRG: Prior-Guided Contrastive Pre-training and Coarse-to-Fine Decoding for Chest X-ray Report Generationcited by 9
  27. 2024Contrastive Learning with Counterfactual Explanations for Radiology Report Generationcited by 8
  28. 2024Pre-training on High Definition X-ray Images: An Experimental Studycited by 7
  29. 2025DDaTR: Dynamic Difference-aware Temporal Residual Network for Longitudinal Radiology Report Generationcited by 7
  30. 2024A Survey of Deep Learning-based Radiology Report Generation Using Multimodal Datacited by 6
  31. 2024Distractors-Immune Representation Learning with Cross-modal Contrastive Regularization for Change Captioningcited by 6
  32. 2025A Chain of Diagnosis Framework for Accurate and Explainable Radiology Report Generationcited by 6
  33. 2024Topicwise Separable Sentence Retrieval for Medical Report Generationcited by 5
  34. 2025CheXPO: Preference Optimization for Chest X-ray VLMs with Counterfactual Rationalecited by 5
  35. 2025Visual Alignment of Medical Vision-Language Models for Grounded Radiology Report Generationcited by 5
  36. 2026XrayClaw: Cooperative-Competitive Multi-Agent Alignment for Trustworthy Chest X-ray Diagnosiscited by 5
  37. 2023Act Like a Radiologist: Radiology Report Generation across Anatomical Regionscited by 4
  38. 2024EVOKE: Elevating Chest X-ray Report Generation via Multi-View Contrastive Learning and Patient-Specific Knowledgecited by 4

50 most cited of 114 All 114 (JSON)