This GitHub repository summarizes papers and resources related to the radiology report generation (RRG) task.
You can refer to my survey paper titled "A Systematic Review of Deep Learning-based Research on Radiology Report Generation" for more details of this topic.
If you find my survey paper helpful to your research, please cite it with the following BibTeX:
@misc{liu2023systematic,
title={A Systematic Review of Deep Learning-based Research on Radiology Report Generation},
author={Chang Liu and Yuanhe Tian and Yan Song},
year={2023},
eprint={2311.14199},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
If you have any suggestions about this repository, please feel free to start a new issue or pull requests.
🔥 [Nov. 19th] We have released our latest paper titled "StableV2V: Stablizing Shape Consistency in Video-to-Video Editing", with the correponding code, model weights, and a testing benchmark DAVIS-Edit
open-sourced. Feel free to check them out from the links!
- Recent Papers
- Update ECCV 2024 Papers
- Update ACL 2024 Papers
- Update CVPR 2024 Papers
- Update AAAI 2024 Papers
- Update PDFs and References
- Regular Maintenance of Preprint arXiv Papers and Missed Papers
- Previous Papers
- Published Papers on Conferences
- Update ACL papers
- Update EMNLP papers
- Update CVPR papers
- Update ICCV papers
- Update ECCV papers
- Update MICCAI papers
- Update AAAI papers
- Update NeurIPS papers
- Published Papers on Journals
- Update TMM papers
- Update TMI papers
- Published Papers on Conferences
- [NAACL 2019] A Survey on Biomedical Image Captioning [Paper]
- [Artif. Intell. Medicine 2020] Deep Learning in Generating Radiology Reports: A Survey [Paper]
- [Knowledge and Information Systems 2022] Diagnostic Captioning: A Survey [Paper]
- [arXiv 2023] A Systematic Review on Deep Learning-based Research on Radiology Report Generation [Paper]
- Year 2024
- ACL
- CVPR
- ECCV
- AAAI
- TMM
- From Observation to Concept: A Flexible Multi-view Paradigm for Medical Report Generation [paper]
- TMI
- Complex Organ Mask Guided Radiology Report Generation [Paper] [Code]
- Multi-Grained Radiology Report Generation With Sentence-Level Image-Language Contrastive Learning [Paper]
- Attribute Prototype-guided Iterative Scene Graph for Explainable Radiology Report Generation [Paper] [Code]
- An Organ-aware Diagnosis Framework for Radiology Report Generation [Paper]
- arXiv
- Designing a Robust Radiology Report Generation System [Paper]
- R2Gen-Mamba: A Selective State Space Model for Radiology Report Generation [Paper] [Code]
- Image-aware Evaluation of Generated Medical Reports [Paper]
- Resource-Efficient Medical Report Generation using Large Language Models [Paper]
- An X-Ray Is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report Generation [Paper]
- KARGEN: Knowledge-enhanced Automated Radiology Report Generation Using Large Language Models [Paper]
- Medical Report Generation Is A Multi-label Classification Problem [Paper]
- Year 2023
- ACL
- EACL
- EMNLP
- CVPR
- Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation [Paper] [Code]
- RGRG: Interactive and Explainable Region-guided Radiology Report Generation [Paper] [Code]
- KiUT: Knowledge-injected U-Transformer for Radiology Report Generation [Paper]
- METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens [Paper]
- ICCV
- Unify, Align and Refine: Multi-Level Semantic Alignment for Radiology Report Generation [Paper]
- MICCAI
- ICASSP
- MvCo-DoT: Multi-View Contrastive Domain Transfer Network for Medical Report Generation [Paper]
- ICIP
- Self Adaptive Global-Local Feature Enhancement for Radiology Report Generation [Paper]
- WWW
- AMI
- TMI
- Attributed Abnormality Graph Embedding for Clinically Accurate X-Ray Report Generation [Paper]
- SGT++: Improved Scene Graph-guided Transformer for Surgical Report Generation [Paper]
- Joint Embedding of Deep Visual and Semantic Features for Medical Image Report Generation [paper]
- Semi-supervised Medical Report Generation via Graph-guided Hybrid Feature Consistency [paper]
- arXiv
- LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation [Paper] [Code]
- MAIRA-1: A Specialised Large Multimodal Model for Radiology Report Generation [Paper] [Project]
- MedXChat: Bridging CXR Modalities with a Unified Multimodal Large Model [Paper]
- Pragmatic Radiology Report Generation [paper]
- RadLLM: A Comprehensive Healthcare Benchmark of Large Language Models for Radiology [Paper] [Project]
- RaDialog: A Large Vision-Language Model for Radiology Report Generation and Conversational Assistance [Paper] [Code]
- Towards Generalist Biomedical AI [Paper] [Reproduced Code]
- Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data [Paper] [Project] [Code]
- Cross-Modal Causal Intervention for Medical Report Generation [Paper] [Code]
- Medical Report Generation based on Segment-Enhanced Contrastive Representation Learning [Paper]
- Radiology Report Generation Using Transformers Conditioned with Non-imaging Data [Paper]
- Year 2022
- AACL
- Multimodal Generation of Radiology Reports using Knowledge-Grounded Extraction of Entities and Relations [Paper]
- ACL
- EMNLP
- CVPR
- Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation [Paper]
- ECCV
- Cross-Modal Prototype Driven Network for Radiology Report Generation [Paper]
- MICCAI
- RepsNet: Combining Vision with Language for Automated Medical Reports [Paper]
- A Self-guided Framework for Radiology Report Generation [Paper] [Code]
- A Medical Semantic-Assisted Transformer for Radiographic Report Generation [Paper]
- Lesion Guided Explainable Few Weak-Shot Medical Report Generation [Paper]
- TranSQ: Transformer-Based Semantic Query for Medical Report Generation [Paper] [Code]
- BMVC
- ICBB
- Clinically Coherent Radiology Report Generation with Imbalanced Chest X-rays [Paper]
- MIA
- TMI
- Automated Radiographic Report Generation Purely on Transformer: A Multicriteria Supervised Approach [Paper]
- arXiv
- AACL
- Year 2021
- ACL
- NAACL
- COLING
- JPG - Jointly Learn to Align: Automated Disease Prediction and Radiology Report Generation [Paper]
- EMNLP
- CVPR
- ICCV
- Visual-Textual Attentive Semantic Consistency for Medical Report Generation [Paper]
- MICCAI
- NeurIPS
- Auto-encoding Knowledge Graph for Unsupervised Medical Report Generation [Paper]
- Year 2020
- Year 2019
- ACL
- Show, Describe and Conclude: On Exploiting the Structure Information of Chest X-Ray Reports [Paper]
- MICCAI
- Automatic Radiology Report Generation based on Multi-view Image Fusion and Medical Concept Enrichment [Paper]
- AAAI
- Knowledge-Driven Encode, Retrieve, Paraphrase for Medical Image Report Generation [Paper]
- BMVC
- Addressing Data Bias Problems for Chest X-ray Image Report Generation [Paper]
- ACL
- Year 2018
[J. Am. Medical Informatics Assoc.] IU X-Ray: Preparing A Collection of Radiology Examinations for Distribution and Retrieval [Paper] [Dataset]
[Scientific Data] MIMIC-CXR, A De-identified Publicly Available Database of Chest Radiographs with Free-text Reports [Paper] [Dataset]
[arXiv] MIMIC-CXR-JPG, A Large Publicly Available Database of Labeled Chest Radiographs [Paper] [Dataset]
[NeurIPS 2021 Datasets & Benchmark] FFA-IR: Towards an Explainable and Reliable Medical Report Generation Benchmark [Paper] [Dataset] [GitHub]
[NeurIPS 2021 Datasets & Benchmark] RadGraph: Extracting Clinical Entities and Relations from Radiology Reports [Paper] [Dataset]
- Q: The conference sequence of this paper list?
- This paper list is organized according to the following sequence:
- Conferences
- ACL
- EACL
- NAACL
- COLING
- EMNLP
- CVPR
- ICCV
- ECCV
- MICCAI
- AAAI
- NeurIPS
- ACCV
- BMCV
- ICASSP
- ICIP
- ICBB
- WWW
- Journals
- AMI
- MIA
- TMM
- TMI
- arXiv
- Conferences
- This paper list is organized according to the following sequence:
The reference.bib
file summarizes bibtex references of up-to-date image inpainting papers, widely used datasets, and toolkits.
Based on the original references, I have made the following modifications to make their results look nice in the LaTeX
manuscripts:
- Refereces are normally constructed in the form of
author-etal-year-nickname
. Particularly, references of datasets and toolkits are directly constructed asnickname
, e.g.,imagenet
. - In each reference, all names of conferences/journals are converted into abbreviations, e.g.,
Computer Vision and Pattern Recognition -> CVPR
. - The
url
,doi
,publisher
,organization
,editor
,series
in all references are removed. - The
pages
of all references are added if they are missing. - All paper names are in title case. Besides, I have added an additional
{}
to make sure that the title case would also work well in some particular templates.
If you have other demands of reference formats, you may refer to the original references of papers by searching their names in DBLP or Google Scholar.