# Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation

arXiv: https://arxiv.org/abs/2109.12242 · HTML: https://mlsanity.com/paper/2109.12242/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 33 references that are in the map.
- First posted on arXiv 25 Sep 2021.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)
- [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)
- [On the Automatic Generation of Medical Imaging Reports](https://mlsanity.com/paper/1711.08195/) (2017)
- [Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation](https://mlsanity.com/paper/1805.08298/) (2018)
- [Clinically Accurate Chest X-Ray Report Generation](https://mlsanity.com/paper/1904.02633/) (2019)
- [Knowledge-driven Encode, Retrieve, Paraphrase for Medical Image Report Generation](https://mlsanity.com/paper/1903.10122/) (2019)
- [Show, Describe and Conclude: On Exploiting the Structure Information of Chest X-Ray Reports](https://mlsanity.com/paper/2004.12274/) (2020)
- [Contrastive Learning with Adversarial Perturbations for Conditional Text Generation](https://mlsanity.com/paper/2012.07280/) (2020)
- [Contrastive Learning for Image Captioning](https://mlsanity.com/paper/1710.02534/) (2017)
- [Learning Visual-Semantic Embeddings for Reporting Abnormal Findings on Chest X-rays](https://mlsanity.com/paper/2010.02467/) (2020)
- [Addressing Data Bias Problems for Chest X-ray Image Report Generation](https://mlsanity.com/paper/1908.02123/) (2019)
- [Large Margin Neural Language Model](https://mlsanity.com/paper/1808.08987/) (2018)
- [Contrastive Unsupervised Word Alignment with Non-Local Features](https://mlsanity.com/paper/1410.2082/) (2014)

## Built on by (most cited first, 30 of 41)

- [Transformers in Medical Imaging: A Survey](https://mlsanity.com/paper/2201.09873/) (2022)
- [Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation](https://mlsanity.com/paper/2303.10323/) (2023)
- [PromptMRG: Diagnosis-Driven Prompts for Medical Report Generation](https://mlsanity.com/paper/2308.12604/) (2023)
- [Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Review](https://mlsanity.com/paper/2301.03505/) (2023)
- [Automated Radiology Report Generation: A Review of Recent Advances](https://mlsanity.com/paper/2405.10842/) (2024)
- [Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models](https://mlsanity.com/paper/2310.03182/) (2023)
- [Multimodal Image-Text Matching Improves Retrieval-based Chest X-Ray Report Generation](https://mlsanity.com/paper/2303.17579/) (2023)
- [CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Dataset](https://mlsanity.com/paper/2410.00379/) (2024)
- [Personalized Showcases: Generating Multi-Modal Explanations for Recommendations](https://mlsanity.com/paper/2207.00422/) (2022)
- [Visualize Before You Write: Imagination-Guided Open-Ended Text Generation](https://mlsanity.com/paper/2210.03765/) (2022)
- [Longitudinal Data and a Semantic Similarity Reward for Chest X-Ray Report Generation](https://mlsanity.com/paper/2307.09758/) (2023)
- [MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation](https://mlsanity.com/paper/2310.14088/) (2023)
- [ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data](https://mlsanity.com/paper/2310.05242/) (2023)
- [A Systematic Review of Deep Learning-based Research on Radiology Report Generation](https://mlsanity.com/paper/2311.14199/) (2023)
- [Boosting Vision Semantic Density with Anatomy Normality Modeling for Medical Vision-language Pre-training](https://mlsanity.com/paper/2508.03742/) (2025)
- [LLM-RG4: Flexible and Factual Radiology Report Generation across Diverse Input Contexts](https://mlsanity.com/paper/2412.12001/) (2024)
- [Consensus, dissensus and synergy between clinicians and specialist foundation models in radiology report generation](https://mlsanity.com/paper/2311.18260/) (2023)
- [X-ray Made Simple: Lay Radiology Report Generation and Robust Evaluation](https://mlsanity.com/paper/2406.17911/) (2024)
- [A Chain of Diagnosis Framework for Accurate and Explainable Radiology Report Generation](https://mlsanity.com/paper/2508.09566/) (2025)
- [FlexR: Few-shot Classification with Language Embeddings for Structured Reporting of Chest X-rays](https://mlsanity.com/paper/2203.15723/) (2022)
- [A Disease-Aware Dual-Stage Framework for Chest X-ray Report Generation](https://mlsanity.com/paper/2511.12259/) (2025)
- [Domain-adapted large language models for classifying nuclear medicine reports](https://mlsanity.com/paper/2303.01258/) (2023)
- [LLM-driven Medical Report Generation via Communication-efficient Heterogeneous Federated Learning](https://mlsanity.com/paper/2506.17562/) (2025)
- [R2GenKG: Hierarchical Multi-modal Knowledge Graph for LLM-based Radiology Report Generation](https://mlsanity.com/paper/2508.03426/) (2025)
- [Natural Language Generation in Healthcare: A Review of Methods and Applications](https://mlsanity.com/paper/2505.04073/) (2025)
- [Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation](https://mlsanity.com/paper/2509.25963/) (2025)
- [Label Structure Preserving Contrastive Embedding for Multi-Label Learning with Missing Labels](https://mlsanity.com/paper/2209.01314/) (2022)
- [Contrastive Learning enhanced Author-Style Headline Generation](https://mlsanity.com/paper/2211.03305/) (2022)
- [MvCo-DoT:Multi-View Contrastive Domain Transfer Network for Medical Report Generation](https://mlsanity.com/paper/2304.07465/) (2023)
- ["Nothing Abnormal": Disambiguating Medical Reports via Contrastive Knowledge Infusion](https://mlsanity.com/paper/2305.08300/) (2023)

## Abstract (arXiv)

Radiology report generation aims at generating descriptive text from radiology images automatically, which may present an opportunity to improve radiology reporting and interpretation. A typical setting consists of training encoder-decoder models on image-report pairs with a cross entropy loss, which struggles to generate informative sentences for clinical diagnoses since normal findings dominate the datasets. To tackle this challenge and encourage more clinically-accurate text outputs, we propose a novel weakly supervised contrastive loss for medical report generation. Experimental results demonstrate that our method benefits from contrasting target reports with incorrect but semantically-close ones. It outperforms previous work on both clinical correctness and text generation metrics for two public benchmarks.