# CXR-Retrieve: Compositional Text-to-Image Retrieval in Chest Radiography

arXiv: https://arxiv.org/abs/2607.27779 · HTML: https://mlsanity.com/paper/2607.27779/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [NegBio: a high-performance tool for negation and uncertainty detection in radiology reports](https://mlsanity.com/paper/1712.05898/) (2017)
- [Vision-Language Models Do Not Understand Negation](https://mlsanity.com/paper/2501.09425/) (2025)
- [COLA: A Benchmark for Compositional Text-to-image Retrieval](https://mlsanity.com/paper/2305.03689/) (2023)
- [Multimodal Image-Text Matching Improves Retrieval-based Chest X-Ray Report Generation](https://mlsanity.com/paper/2303.17579/) (2023)
- [Medical Image Retrieval using Deep Convolutional Neural Network](https://mlsanity.com/paper/1703.08472/) (2017)
- [Semi-Supervised Semantic Segmentation via Marginal Contextual Information](https://mlsanity.com/paper/2308.13900/) (2023)
- [CARES: Context-Aware Resolution Selector for VLMs](https://mlsanity.com/paper/2510.19496/) (2025)
- [Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs](https://mlsanity.com/paper/2603.16932/) (2026)

## Abstract (arXiv)

Large chest radiography archives are difficult to search because most studies are paired only with free-text reports rather than structured clinical annotations. Vision-language models offer a natural interface for text-to-image retrieval, but current biomedical models are primarily optimized for report-to-image matching rather than for satisfying short clinical search queries. This creates an objective mismatch: a model may retrieve images related to words in the query while failing to satisfy the full clinical constraint, especially for conjunctions and negations such as ``atelectasis and no pneumonia.'' We introduce CXR-Retrieve, a structured benchmark for compositional chest X-ray text-to-image retrieval. The benchmark contains 5,159 test images from the official test-split of MIMIC-CXR-JPG and 145 textual queries spanning single and conjunction findings, both positive and negative. Relevance is defined by whether a retrieved image satisfies all asserted pathology constraints, rather than by whether it matches a paired report. We further propose a label-aware contrastive fine-tuning objective for clinical retrieval. Our method attracts image-text pairs with compatible asserted pathology constraints, including shared confirmed absences, while explicitly repelling contradictory pairs. Starting from the in-domain CXR-CLIP checkpoint, our method improves Precision@5 over CXR-CLIP by 8.5 percentage points on two-pathology conjunctions and by 22.0 percentage points on negation queries. These results show that reliable chest X-ray retrieval requires training objectives that model not only which findings are mentioned, but also how they are clinically asserted.