mlsanityData to 14 Oct 2026

DRRG: A Discrete Diffusion Framework for Radiology Report Generation

arXiv 2608.24105 ↗First posted 25 Aug 2026cs.CVcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Purpose: Automatic radiology report generation (RRG) has been widely explored to improve reporting accuracy and reduce radiologists' workload. Most existing methods rely on autoregressive (AR) frameworks that generate reports token by token and cannot revise earlier content, making them prone to error propagation and inconsistent with the iterative refinement process of radiological reporting. In contrast, discrete diffusion large language models (DLLMs) generate text through iterative denoising, naturally enabling report refinement. However, DLLMs have not been extensively investigated for RRG. In this study, we developed and evaluated a discrete diffusion framework for RRG that enables iterative refinement rather than conventional left-to-right autoregressive decoding. Materials and methods: We developed DRRG, a DLLM-based framework that formulates RRG as iterative masked-token denoising. DRRG incorporates a clinical-entities-aware complementary mask to improve token supervision coverage and emphasize clinically important entities, together with a concept-conditioning module that injects image-derived clinical concepts into visual representations. DRRG was trained and evaluated on MIMIC-CXR and CheXpert Plus. Results: On MIMIC-CXR, DRRG achieved BLEU-4 of 0.210, CheXpert-F1 of 0.549, RadGraph-F1 of 0.281, GREEN of 0.360, and RaTEScore of 0.604, outperforming the compared methods on most reported metrics, despite employing a substantially smaller LLM decoder. On CheXpert Plus, DRRG achieved the highest BLEU-4 (0.119) and CheXpert-F1 (0.347) among the compared methods. Conclusion: Discrete diffusion provides an effective alternative to autoregressive radiology report generation by enabling iterative, bidirectional report refinement. Incorporating clinically focused masking and image-derived concept conditioning improves report quality and clinical consistency.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 32 of its 48 references that are in the map. First posted on arXiv 25 Aug 2026.

Builds on

32 of 48 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,423
  3. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,188
  4. 2025Large Language Diffusion Modelscited by 912
  5. 2014Show and Tell: A Neural Image Caption Generatorcited by 879
  6. 2019MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographscited by 597
  7. 2025Dream 7B: Diffusion Large Language Modelscited by 544
  8. 2020Generating Radiology Reports via Memory-driven Transformercited by 368
  9. 2020CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERTcited by 337
  10. 2021RadGraph: Extracting Clinical Entities and Relations from Radiology Reportscited by 319
  11. 2016Image Captioning with Semantic Attentioncited by 260
  12. 2017On the Automatic Generation of Medical Imaging Reportscited by 216
20 more
  1. 2022Cross-modal Memory Networks for Radiology Report Generationcited by 185
  2. 2025LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuningcited by 148
  3. 2020When Radiology Report Generation Meets Knowledge Graphcited by 145
  4. 2023Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generationcited by 118
  5. 2023R2GenGPT: Radiology Report Generation with Frozen LLMscited by 114
  6. 2024CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formatscited by 106
  7. 2023METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokenscited by 101
  8. 2025LaViDa: A Large Diffusion Language Model for Multimodal Understandingcited by 84
  9. 2024RaTEScore: A Metric for Radiology Report Generationcited by 65
  10. 2020Show, Describe and Conclude: On Exploiting the Structure Information of Chest X-Ray Reportscited by 58
  11. 2023ORGAN: Observation-Guided Radiology Report Generation via Tree Reasoningcited by 42
  12. 2023Utilizing Longitudinal Chest X-Rays and Reports to Pre-Fill Radiology Reportscited by 35
  13. 2024CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Datasetcited by 35
  14. 2025Beyond Fixed: Training-Free Variable-Length Denoising for Diffusion Large Language Modelscited by 34
  15. 2025Diffusion LLM with Native Variable Generation Lengths: Let [EOS] Lead the Waycited by 22
  16. 2025LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical Image Understandingcited by 13
  17. 2025DART: Disease-aware Image-Text Alignment and Self-correcting Re-alignment for Trustworthy Radiology Report Generationcited by 9
  18. 2025S-RRG-Bench: Structured Radiology Report Generation with Fine-Grained Evaluation Frameworkcited by 6
  19. 2024DAMPER: A Dual-Stage Medical Report Generation Framework with Coarse-Grained MeSH Alignment and Fine-Grained Hypergraph Matchingcited by 4
  20. 2025Learnable Retrieval Enhanced Visual-Text Alignment and Fusion for Radiology Report Generationcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026AnchorDiff: Topology-Aware Masked Diffusion with Confidence-based Rewriting for Radiology Report Generation
  2. 2026Discrete Diffusion Language Models for Interactive Radiology Report Drafting
  3. 2024Automated Radiology Report Generation: A Review of Recent Advances
  4. 2024Multimodal Large Language Model driven Radiology Report Generation with Clinical Knowledge Enhancement
  5. 2025Random Direct Preference Optimization for Radiography Report Generation
  6. 2025μ2Tokenizer: Differentiable Multi-Scale Multi-Modal Tokenizer for Radiology Report Generation
  7. 2025RA-RRG: Multimodal Retrieval-Augmented Radiology Report Generation with Key Phrase Extraction
  8. 2024SERPENT-VLM : Self-Refining Radiology Report Generation Using Vision Language Models