# Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluation

arXiv: https://arxiv.org/abs/2403.08002 · HTML: https://mlsanity.com/paper/2403.08002/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 71 references that are in the map.
- First posted on arXiv 12 Mar 2024.

## Builds on (most cited first, 30 of 33)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Textbooks Are All You Need](https://mlsanity.com/paper/2306.11644/) (2023)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [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)
- [Big Self-Supervised Models Advance Medical Image Classification](https://mlsanity.com/paper/2101.05224/) (2021)
- [RadGraph: Extracting Clinical Entities and Relations from Radiology Reports](https://mlsanity.com/paper/2106.14463/) (2021)
- [PadChest: A large chest x-ray image dataset with multi-label annotated reports](https://mlsanity.com/paper/1901.07441/) (2019)
- [Towards Generalist Biomedical AI](https://mlsanity.com/paper/2307.14334/) (2023)
- [Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing](https://mlsanity.com/paper/2301.04558/) (2023)
- [Orca 2: Teaching Small Language Models How to Reason](https://mlsanity.com/paper/2311.11045/) (2023)
- [Do We Still Need Clinical Language Models?](https://mlsanity.com/paper/2302.08091/) (2023)
- [Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports](https://mlsanity.com/paper/1911.02541/) (2019)
- [Improving the Factual Correctness of Radiology Report Generation with Semantic Rewards](https://mlsanity.com/paper/2210.12186/) (2022)
- [MAIRA-1: A specialised large multimodal model for radiology report generation](https://mlsanity.com/paper/2311.13668/) (2023)
- [Cross-modal Prototype Driven Network for Radiology Report Generation](https://mlsanity.com/paper/2207.04818/) (2022)
- [MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records](https://mlsanity.com/paper/2308.14089/) (2023)
- [Improving Radiology Report Generation Systems by Removing Hallucinated References to Non-existent Priors](https://mlsanity.com/paper/2210.06340/) (2022)
- [Robust and Efficient Medical Imaging with Self-Supervision](https://mlsanity.com/paper/2205.09723/) (2022)
- [An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models](https://mlsanity.com/paper/2309.09958/) (2023)

## Built on by (most cited first, 30 of 51)

- [Capabilities of Gemini Models in Medicine](https://mlsanity.com/paper/2404.18416/) (2024)
- [MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning](https://mlsanity.com/paper/2502.19634/) (2025)
- [MAIRA-2: Grounded Radiology Report Generation](https://mlsanity.com/paper/2406.04449/) (2024)
- [Merlin: A Computed Tomography Vision-Language Foundation Model and Dataset](https://mlsanity.com/paper/2406.06512/) (2024)
- [mDPO: Conditional Preference Optimization for Multimodal Large Language Models](https://mlsanity.com/paper/2406.11839/) (2024)
- [MedImageInsight: An Open-Source Embedding Model for General Domain Medical Imaging](https://mlsanity.com/paper/2410.06542/) (2024)
- [EyecareGPT: Boosting Comprehensive Ophthalmology Understanding with Tailored Dataset, Benchmark and Model](https://mlsanity.com/paper/2504.13650/) (2025)
- [MedMO: Grounding and Understanding Multimodal Large Language Model for Medical Images](https://mlsanity.com/paper/2602.06965/) (2026)
- [EndoBench: A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysis](https://mlsanity.com/paper/2505.23601/) (2025)
- [Scaling medical imaging report generation with multimodal reinforcement learning](https://mlsanity.com/paper/2601.17151/) (2026)
- [Lunguage: A Benchmark for Structured and Sequential Chest X-ray Interpretation](https://mlsanity.com/paper/2505.21190/) (2025)
- [MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning](https://mlsanity.com/paper/2602.03320/) (2026)
- [HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents](https://mlsanity.com/paper/2606.31179/) (2026)
- [Uncovering Knowledge Gaps in Radiology Report Generation Models through Knowledge Graphs](https://mlsanity.com/paper/2408.14397/) (2024)
- [MAIRA-Seg: Enhancing Radiology Report Generation with Segmentation-Aware Multimodal Large Language Models](https://mlsanity.com/paper/2411.11362/) (2024)
- [CXRAgent: Director-Orchestrated Multi-Stage Reasoning for Chest X-Ray Interpretation](https://mlsanity.com/paper/2510.21324/) (2025)
- [CheXGenBench: A Unified Benchmark For Fidelity, Privacy and Utility of Synthetic Chest Radiographs](https://mlsanity.com/paper/2505.10496/) (2025)
- [Toward Clinically Explainable AI for Medical Diagnosis: A Foundation Model with Human-Compatible Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2509.03906/) (2025)
- [A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation](https://mlsanity.com/paper/2604.00493/) (2026)
- [CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding](https://mlsanity.com/paper/2509.23379/) (2025)
- [Enhancing Radiology Report Generation and Visual Grounding using Reinforcement Learning](https://mlsanity.com/paper/2512.10691/) (2025)
- [MedVAL: Toward Expert-Level Medical Text Validation with Language Models](https://mlsanity.com/paper/2507.03152/) (2025)
- [Clinically Grounded Agent-based Report Evaluation: An Interpretable Metric for Radiology Report Generation](https://mlsanity.com/paper/2508.02808/) (2025)
- [CWCD: Category-Wise Contrastive Decoding for Structured Medical Report Generation](https://mlsanity.com/paper/2604.10410/) (2026)
- [Foundation Models in Biomedical Imaging: Turning Hype into Reality](https://mlsanity.com/paper/2512.15808/) (2025)
- [A data- and compute-efficient chest X-ray foundation model beyond aggressive scaling](https://mlsanity.com/paper/2602.22843/) (2026)
- [An Empirical Analysis of Calibration and Selective Prediction in Multimodal Clinical Condition Classification](https://mlsanity.com/paper/2603.02719/) (2026)
- [Towards Better Aligned LLM Judges for Radiology Report Evaluation across Modalities and Anatomies](https://mlsanity.com/paper/2604.03376/) (2026)
- [Interpreting Biomedical VLMs on High-Imbalance Out-of-Distributions: An Insight into BiomedCLIP on Radiology](https://mlsanity.com/paper/2506.14136/) (2025)
- [MRD: Multi-resolution Retrieval-Detection Fusion for High-Resolution Image Understanding](https://mlsanity.com/paper/2512.02906/) (2025)

## Abstract (arXiv)

The scaling laws and extraordinary performance of large foundation models motivate the development and utilization of such models in biomedicine. However, despite early promising results on some biomedical benchmarks, there are still major challenges that need to be addressed before these models can be used in real-world clinics. Frontier general-domain models such as GPT-4V still have significant performance gaps in multimodal biomedical applications. More importantly, less-acknowledged pragmatic issues, including accessibility, model cost, and tedious manual evaluation make it hard for clinicians to use state-of-the-art large models directly on private patient data. Here, we explore training open-source small multimodal models (SMMs) to bridge competency gaps for unmet clinical needs in radiology. To maximize data efficiency, we adopt a modular approach by incorporating state-of-the-art pre-trained models for image and text modalities, and focusing on training a lightweight adapter to ground each modality to the text embedding space, as exemplified by LLaVA-Med. For training, we assemble a large dataset of over 697 thousand radiology image-text pairs. For evaluation, we propose CheXprompt, a GPT-4-based metric for factuality evaluation, and demonstrate its parity with expert evaluation. For best practice, we conduct a systematic ablation study on various choices in data engineering and multimodal training. The resulting LlaVA-Rad (7B) model attains state-of-the-art results on standard radiology tasks such as report generation and cross-modal retrieval, even outperforming much larger models such as GPT-4V and Med-PaLM M (84B). The inference of LlaVA-Rad is fast and can be performed on a single V100 GPU in private settings, offering a promising state-of-the-art tool for real-world clinical applications.