mlsanityData to 7 Oct 2026

Uncovering Knowledge Gaps in Radiology Report Generation Models through Knowledge Graphs

arXiv 2408.14397 ↗First posted 26 Aug 2024cs.AI cs.CL cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Recent advancements in artificial intelligence have significantly improved the automatic generation of radiology reports. However, existing evaluation methods fail to reveal the models' understanding of radiological images and their capacity to achieve human-level granularity in descriptions. To bridge this gap, we introduce a system, named ReXKG, which extracts structured information from processed reports to construct a comprehensive radiology knowledge graph. We then propose three metrics to evaluate the similarity of nodes (ReXKG-NSC), distribution of edges (ReXKG-AMS), and coverage of subgraphs (ReXKG-SCS) across various knowledge graphs. We conduct an in-depth comparative analysis of AI-generated and human-written radiology reports, assessing the performance of both specialist and generalist models. Our study provides a deeper understanding of the capabilities and limitations of current AI models in radiology report generation, offering valuable insights for improving model performance and clinical applicability.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 27 of its 43 references that are in the map. First posted on arXiv 26 Aug 2024.

Builds on

27 of 43 references.

References · 27

  1. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  2. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  3. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  4. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
  5. 2021ImageNet-21K Pretraining for the Massescited by 607
  6. 2020CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERTcited by 329
  7. 2021RadGraph: Extracting Clinical Entities and Relations from Radiology Reportscited by 310
  8. 2018A Survey on Deep Learning for Named Entity Recognitioncited by 281
  9. 2019ScispaCy: Fast and Robust Models for Biomedical Natural Language Processingcited by 244
  10. 2023MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrievalcited by 182
  11. 2020When Radiology Report Generation Meets Knowledge Graphcited by 144
  12. 2024MAIRA-2: Grounded Radiology Report Generationcited by 140
15 more
  1. 2023Interactive and Explainable Region-guided Radiology Report Generationcited by 139
  2. 2024GREEN: Generative Radiology Report Evaluation and Error Notationcited by 124
  3. 2022Improving Chest X-Ray Report Generation by Leveraging Warm Startingcited by 93
  4. 2021Chest ImaGenome Dataset for Clinical Reasoningcited by 89
  5. 2017NegBio: a high-performance tool for negation and uncertainty detection in radiology reportscited by 79
  6. 2024A Vision-Language Foundation Model to Enhance Efficiency of Chest X-ray Interpretationcited by 79
  7. 2024RaTEScore: A Metric for Radiology Report Generationcited by 65
  8. 2024Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluationcited by 51
  9. 2017Relation Extraction : A Surveycited by 44
  10. 2024MedVersa: A Generalist Foundation Model for Medical Image Interpretationcited by 37
  11. 2020CheXpert++: Approximating the CheXpert labeler for Speed,Differentiability, and Probabilistic Outputcited by 23
  12. 2024FineRadScore: A Radiology Report Line-by-Line Evaluation Technique Generating Corrections with Severity Scorescited by 18
  13. 2023A Systematic Review of Deep Learning-based Research on Radiology Report Generationcited by 14
  14. 2023RadGraph2: Modeling Disease Progression in Radiology Reports via Hierarchical Information Extractioncited by 11
  15. 2022Knowledge Graph Construction and Its Application in Automatic Radiology Report Generation from Radiologist's Dictationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 2.

7 papers.

  1. 2024FactCheXcker: Mitigating Measurement Hallucinations in Chest X-ray Report Generation Modelscited by 11
  2. 2025R2GenKG: Hierarchical Multi-modal Knowledge Graph for LLM-based Radiology Report Generationcited by 3
  3. 2025Foundation Models in Biomedical Imaging: Turning Hype into Realitycited by 2
  4. 2026Revisiting LLM Adaptation for 3D CT Report Generation: A Study of Scaling and Diagnostic Priorscited by 1
  5. 2025Holistic Artificial Intelligence in Medicine; improved performance and explainabilitycited by 0
  6. 2025CheXPO-v2: Preference Optimization for Chest X-ray VLMs with Knowledge Graph Consistencycited by 0
  7. 2026From Image Interpretation to Clinical Reasoning: Upstream Physician-Context-Aware Multimodal Learning with Causal Reinforcement Learningcited by 0