# Graph Enhanced Contrastive Learning for Radiology Findings Summarization

arXiv: https://arxiv.org/abs/2204.00203 · HTML: https://mlsanity.com/paper/2204.00203/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 43 references that are in the map.
- First posted on arXiv 1 Apr 2022.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [Text Summarization with Pretrained Encoders](https://mlsanity.com/paper/1908.08345/) (2019)
- [Generating Radiology Reports via Memory-driven Transformer](https://mlsanity.com/paper/2010.16056/) (2020)
- [CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT](https://mlsanity.com/paper/2004.09167/) (2020)
- [DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations](https://mlsanity.com/paper/2006.03659/) (2020)
- [When Radiology Report Generation Meets Knowledge Graph](https://mlsanity.com/paper/2002.08277/) (2020)
- [InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring](https://mlsanity.com/paper/2103.01128/) (2021)
- [Clinically Accurate Chest X-Ray Report Generation](https://mlsanity.com/paper/1904.02633/) (2019)
- [CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2109.09209/) (2021)
- [Self-Guided Contrastive Learning for BERT Sentence Representations](https://mlsanity.com/paper/2106.07345/) (2021)
- [Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports](https://mlsanity.com/paper/1911.02541/) (2019)
- [X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning](https://mlsanity.com/paper/2203.00843/) (2022)
- [Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward](https://mlsanity.com/paper/2005.01159/) (2020)
- [Learning to Summarize Radiology Findings](https://mlsanity.com/paper/1809.04698/) (2018)
- [Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning](https://mlsanity.com/paper/2105.14289/) (2021)
- [Ontology-Aware Clinical Abstractive Summarization](https://mlsanity.com/paper/1905.05818/) (2019)
- [Attend to Medical Ontologies: Content Selection for Clinical Abstractive Summarization](https://mlsanity.com/paper/2005.00163/) (2020)
- [Medical-VLBERT: Medical Visual Language BERT for COVID-19 CT Report Generation With Alternate Learning](https://mlsanity.com/paper/2108.05067/) (2021)
- [BASS: Boosting Abstractive Summarization with Unified Semantic Graph](https://mlsanity.com/paper/2105.12041/) (2021)
- [A Neural Multi-Task Learning Framework to Jointly Model Medical Named Entity Recognition and Normalization](https://mlsanity.com/paper/1812.06081/) (2018)
- [Word Graph Guided Summarization for Radiology Findings](https://mlsanity.com/paper/2112.09925/) (2021)

## Built on by (most cited first, 24 of 24)

- [An Iterative Optimizing Framework for Radiology Report Summarization with ChatGPT](https://mlsanity.com/paper/2304.08448/) (2023)
- [Exploring the Boundaries of GPT-4 in Radiology](https://mlsanity.com/paper/2310.14573/) (2023)
- [PsycoLLM: Enhancing LLM for Psychological Understanding and Evaluation](https://mlsanity.com/paper/2407.05721/) (2024)
- [Toward expanding the scope of radiology report summarization to multiple anatomies and modalities](https://mlsanity.com/paper/2211.08584/) (2022)
- [RLHF in an SFT Way: From Optimal Solution to Reward-Weighted Alignment](https://mlsanity.com/paper/2502.11026/) (2025)
- [Atoxia: Red-teaming Large Language Models with Target Toxic Answers](https://mlsanity.com/paper/2408.14853/) (2024)
- [FactReranker: Fact-guided Reranker for Faithful Radiology Report Summarization](https://mlsanity.com/paper/2303.08335/) (2023)
- [Add-One-In: Incremental Sample Selection for Large Language Models via a Choice-Based Greedy Paradigm](https://mlsanity.com/paper/2503.02359/) (2025)
- [APLOT: Robust Reward Modeling via Adaptive Preference Learning with Optimal Transport](https://mlsanity.com/paper/2510.10963/) (2025)
- [Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMs](https://mlsanity.com/paper/2409.01552/) (2024)
- [Improving Radiology Summarization with Radiograph and Anatomy Prompts](https://mlsanity.com/paper/2210.08303/) (2022)
- [A Survey for Biomedical Text Summarization: From Pre-trained to Large Language Models](https://mlsanity.com/paper/2304.08763/) (2023)
- [Aspect-oriented Consumer Health Answer Summarization](https://mlsanity.com/paper/2405.06295/) (2024)
- [Natural Language Generation in Healthcare: A Review of Methods and Applications](https://mlsanity.com/paper/2505.04073/) (2025)
- [Automatic Personalized Impression Generation for PET Reports Using Large Language Models](https://mlsanity.com/paper/2309.10066/) (2023)
- [Responsible AI Considerations in Text Summarization Research: A Review of Current Practices](https://mlsanity.com/paper/2311.11103/) (2023)
- [Coreference Graph Guidance for Mind-Map Generation](https://mlsanity.com/paper/2312.11997/) (2023)
- [KU-DMIS-MSRA at RadSum23: Pre-trained Vision-Language Model for Radiology Report Summarization](https://mlsanity.com/paper/2307.07409/) (2023)
- [Guidance in Radiology Report Summarization: An Empirical Evaluation and Error Analysis](https://mlsanity.com/paper/2307.12803/) (2023)
- [Knowledge Graph Embeddings for Multi-Lingual Structured Representations of Radiology Reports](https://mlsanity.com/paper/2309.00917/) (2023)
- [Advancing Medical Radiograph Representation Learning: A Hybrid Pre-training Paradigm with Multilevel Semantic Granularity](https://mlsanity.com/paper/2410.00448/) (2024)
- [CSTRL: Context-Driven Sequential Transfer Learning for Abstractive Radiology Report Summarization](https://mlsanity.com/paper/2503.05750/) (2025)
- [Comparative Analysis of Abstractive Summarization Models for Clinical Radiology Reports](https://mlsanity.com/paper/2506.16247/) (2025)
- [VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference](https://mlsanity.com/paper/2608.24063/) (2026)

## Abstract (arXiv)

The impression section of a radiology report summarizes the most prominent observation from the findings section and is the most important section for radiologists to communicate to physicians. Summarizing findings is time-consuming and can be prone to error for inexperienced radiologists, and thus automatic impression generation has attracted substantial attention. With the encoder-decoder framework, most previous studies explore incorporating extra knowledge (e.g., static pre-defined clinical ontologies or extra background information). Yet, they encode such knowledge by a separate encoder to treat it as an extra input to their models, which is limited in leveraging their relations with the original findings. To address the limitation, we propose a unified framework for exploiting both extra knowledge and the original findings in an integrated way so that the critical information (i.e., key words and their relations) can be extracted in an appropriate way to facilitate impression generation. In detail, for each input findings, it is encoded by a text encoder, and a graph is constructed through its entities and dependency tree. Then, a graph encoder (e.g., graph neural networks (GNNs)) is adopted to model relation information in the constructed graph. Finally, to emphasize the key words in the findings, contrastive learning is introduced to map positive samples (constructed by masking non-key words) closer and push apart negative ones (constructed by masking key words). The experimental results on OpenI and MIMIC-CXR confirm the effectiveness of our proposed method.