# ELIXR: Towards a general purpose X-ray artificial intelligence system through alignment of large language models and radiology vision encoders

arXiv: https://arxiv.org/abs/2308.01317 · HTML: https://mlsanity.com/paper/2308.01317/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 35 references that are in the map.
- First posted on arXiv 2 Aug 2023.

## Builds on (most cited first, 12 of 12)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [Med-Flamingo: a Multimodal Medical Few-shot Learner](https://mlsanity.com/paper/2307.15189/) (2023)
- [PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering](https://mlsanity.com/paper/2305.10415/) (2023)
- [A Theoretical Analysis of NDCG Type Ranking Measures](https://mlsanity.com/paper/1304.6480/) (2013)

## Built on by (most cited first, 30 of 50)

- [Capabilities of Gemini Models in Medicine](https://mlsanity.com/paper/2404.18416/) (2024)
- [VLP: Vision Language Planning for Autonomous Driving](https://mlsanity.com/paper/2401.05577/) (2024)
- [Conversational Health Agents: A Personalized LLM-Powered Agent Framework](https://mlsanity.com/paper/2310.02374/) (2023)
- [Advancing Multimodal Medical Capabilities of Gemini](https://mlsanity.com/paper/2405.03162/) (2024)
- [Foundational Models in Medical Imaging: A Comprehensive Survey and Future Vision](https://mlsanity.com/paper/2310.18689/) (2023)
- [MAIRA-1: A specialised large multimodal model for radiology report generation](https://mlsanity.com/paper/2311.13668/) (2023)
- [FairCLIP: Harnessing Fairness in Vision-Language Learning](https://mlsanity.com/paper/2403.19949/) (2024)
- [MedImageInsight: An Open-Source Embedding Model for General Domain Medical Imaging](https://mlsanity.com/paper/2410.06542/) (2024)
- [RadGPT: Constructing 3D Image-Text Tumor Datasets](https://mlsanity.com/paper/2501.04678/) (2025)
- [The first step is the hardest: Pitfalls of Representing and Tokenizing Temporal Data for Large Language Models](https://mlsanity.com/paper/2309.06236/) (2023)
- [PathAlign: A vision-language model for whole slide images in histopathology](https://mlsanity.com/paper/2406.19578/) (2024)
- [Towards a Personal Health Large Language Model](https://mlsanity.com/paper/2406.06474/) (2024)
- [FetalCLIP: A Visual-Language Foundation Model for Fetal Ultrasound Image Analysis](https://mlsanity.com/paper/2502.14807/) (2025)
- [PeFoMed: Parameter Efficient Fine-tuning of Multimodal Large Language Models for Medical Imaging](https://mlsanity.com/paper/2401.02797/) (2024)
- [ChEX: Interactive Localization and Region Description in Chest X-rays](https://mlsanity.com/paper/2404.15770/) (2024)
- [Evaluating Large Language Models as Virtual Annotators for Time-series Physical Sensing Data](https://mlsanity.com/paper/2403.01133/) (2024)
- [Improving Medical Multi-modal Contrastive Learning with Expert Annotations](https://mlsanity.com/paper/2403.10153/) (2024)
- [Multimodal Large Language Models for Medicine: A Comprehensive Survey](https://mlsanity.com/paper/2504.21051/) (2025)
- [HeAR -- Health Acoustic Representations](https://mlsanity.com/paper/2403.02522/) (2024)
- [Learning A Multi-Task Transformer Via Unified And Customized Instruction Tuning For Chest Radiograph Interpretation](https://mlsanity.com/paper/2311.01092/) (2023)
- [Mammo-CLIP: Leveraging Contrastive Language-Image Pre-training (CLIP) for Enhanced Breast Cancer Diagnosis with Multi-view Mammography](https://mlsanity.com/paper/2404.15946/) (2024)
- [ReXErr: Synthesizing Clinically Meaningful Errors in Diagnostic Radiology Reports](https://mlsanity.com/paper/2409.10829/) (2024)
- [Large Language Models Illuminate a Progressive Pathway to Artificial Healthcare Assistant: A Review](https://mlsanity.com/paper/2311.01918/) (2023)
- [Foundation Models in Medical Imaging: A Review and Outlook](https://mlsanity.com/paper/2506.09095/) (2025)
- [Toward a Vision-Language Foundation Model for Medical Data: Multimodal Dataset and Benchmarks for Vietnamese PET/CT Report Generation](https://mlsanity.com/paper/2509.24739/) (2025)
- [MAGDA: Multi-agent guideline-driven diagnostic assistance](https://mlsanity.com/paper/2409.06351/) (2024)
- [Fair-MoE: Fairness-Oriented Mixture of Experts in Vision-Language Models](https://mlsanity.com/paper/2502.06094/) (2025)
- [A unified multi-task framework enables interpretable chest radiograph analysis](https://mlsanity.com/paper/2606.03417/) (2026)
- [MedXChat: A Unified Multimodal Large Language Model Framework towards CXRs Understanding and Generation](https://mlsanity.com/paper/2312.02233/) (2023)
- [Breast Ultrasound Report Generation using LangChain](https://mlsanity.com/paper/2312.03013/) (2023)

## Abstract (arXiv)

In this work, we present an approach, which we call Embeddings for Language/Image-aligned X-Rays, or ELIXR, that leverages a language-aligned image encoder combined or grafted onto a fixed LLM, PaLM 2, to perform a broad range of chest X-ray tasks. We train this lightweight adapter architecture using images paired with corresponding free-text radiology reports from the MIMIC-CXR dataset. ELIXR achieved state-of-the-art performance on zero-shot chest X-ray (CXR) classification (mean AUC of 0.850 across 13 findings), data-efficient CXR classification (mean AUCs of 0.893 and 0.898 across five findings (atelectasis, cardiomegaly, consolidation, pleural effusion, and pulmonary edema) for 1% (~2,200 images) and 10% (~22,000 images) training data), and semantic search (0.76 normalized discounted cumulative gain (NDCG) across nineteen queries, including perfect retrieval on twelve of them). Compared to existing data-efficient methods including supervised contrastive learning (SupCon), ELIXR required two orders of magnitude less data to reach similar performance. ELIXR also showed promise on CXR vision-language tasks, demonstrating overall accuracies of 58.7% and 62.5% on visual question answering and report quality assurance tasks, respectively. These results suggest that ELIXR is a robust and versatile approach to CXR AI.