# Adapting Pretrained Vision-Language Foundational Models to Medical Imaging Domains

arXiv: https://arxiv.org/abs/2210.04133 · HTML: https://mlsanity.com/paper/2210.04133/

## Key facts

- Cited by 86 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 18 of its 22 references that are in the map.
- First posted on arXiv 9 Oct 2022.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)
- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission](https://mlsanity.com/paper/1904.05342/) (2019)
- [Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing](https://mlsanity.com/paper/2204.09817/) (2022)
- [Brain Imaging Generation with Latent Diffusion Models](https://mlsanity.com/paper/2209.07162/) (2022)
- [Self-Alignment Pretraining for Biomedical Entity Representations](https://mlsanity.com/paper/2010.11784/) (2020)
- [GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium](https://mlsanity.com/paper/1706.08500/) (2017)
- [TorchXRayVision: A library of chest X-ray datasets and models](https://mlsanity.com/paper/2111.00595/) (2021)
- [On the limits of cross-domain generalization in automated X-ray prediction](https://mlsanity.com/paper/2002.02497/) (2020)

## Built on by (most cited first, 30 of 86)

- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models](https://mlsanity.com/paper/2210.14896/) (2022)
- [CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection](https://mlsanity.com/paper/2301.00785/) (2023)
- [Holistic Evaluation of Text-To-Image Models](https://mlsanity.com/paper/2311.04287/) (2023)
- [Leaving Reality to Imagination: Robust Classification via Generated Datasets](https://mlsanity.com/paper/2302.02503/) (2023)
- [RoentGen: Vision-Language Foundation Model for Chest X-ray Generation](https://mlsanity.com/paper/2211.12737/) (2022)
- [Differentially Private Diffusion Models Generate Useful Synthetic Images](https://mlsanity.com/paper/2302.13861/) (2023)
- [CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images](https://mlsanity.com/paper/2303.14126/) (2023)
- [Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directions](https://mlsanity.com/paper/2404.03264/) (2024)
- [Large AI Models in Health Informatics: Applications, Challenges, and the Future](https://mlsanity.com/paper/2303.11568/) (2023)
- [PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation](https://mlsanity.com/paper/2307.09036/) (2023)
- [Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunity](https://mlsanity.com/paper/2305.08252/) (2023)
- [Prompt Engineering for Healthcare: Methodologies and Applications](https://mlsanity.com/paper/2304.14670/) (2023)
- [Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance](https://mlsanity.com/paper/2402.08680/) (2024)
- [Diffusion-based Data Augmentation for Skin Disease Classification: Impact Across Original Medical Datasets to Fully Synthetic Images](https://mlsanity.com/paper/2301.04802/) (2023)
- [Generation of Anonymous Chest Radiographs Using Latent Diffusion Models for Training Thoracic Abnormality Classification Systems](https://mlsanity.com/paper/2211.01323/) (2022)
- [A Pathway Towards Responsible AI Generated Content](https://mlsanity.com/paper/2303.01325/) (2023)
- [Evaluating General Purpose Vision Foundation Models for Medical Image Analysis: An Experimental Study of DINOv2 on Radiology Benchmarks](https://mlsanity.com/paper/2312.02366/) (2023)
- [Cascaded Latent Diffusion Models for High-Resolution Chest X-ray Synthesis](https://mlsanity.com/paper/2303.11224/) (2023)
- [Universal and Extensible Language-Vision Models for Organ Segmentation and Tumor Detection from Abdominal Computed Tomography](https://mlsanity.com/paper/2405.18356/) (2024)
- [Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives](https://mlsanity.com/paper/2307.16851/) (2023)
- [DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology](https://mlsanity.com/paper/2306.13384/) (2023)
- [BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeys](https://mlsanity.com/paper/2310.10765/) (2023)
- [Data-Centric Foundation Models in Computational Healthcare: A Survey](https://mlsanity.com/paper/2401.02458/) (2024)
- [Fine-Grained Image-Text Alignment in Medical Imaging Enables Explainable Cyclic Image-Report Generation](https://mlsanity.com/paper/2312.08078/) (2023)
- [Augmenting medical image classifiers with synthetic data from latent diffusion models](https://mlsanity.com/paper/2308.12453/) (2023)
- [MedVAE: Efficient Automated Interpretation of Medical Images with Large-Scale Generalizable Autoencoders](https://mlsanity.com/paper/2502.14753/) (2025)
- [Medical diffusion on a budget: Textual Inversion for medical image generation](https://mlsanity.com/paper/2303.13430/) (2023)
- [SurGen: Text-Guided Diffusion Model for Surgical Video Generation](https://mlsanity.com/paper/2408.14028/) (2024)
- [Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion](https://mlsanity.com/paper/2502.21278/) (2025)

## Abstract (arXiv)

Multi-modal foundation models are typically trained on millions of pairs of natural images and text captions, frequently obtained through web-crawling approaches. Although such models depict excellent generative capabilities, they do not typically generalize well to specific domains such as medical images that have fundamentally shifted distributions compared to natural images. Building generative models for medical images that faithfully depict clinical context may help alleviate the paucity of healthcare datasets. Thus, in this study, we seek to research and expand the representational capabilities of large pretrained foundation models to medical concepts, specifically for leveraging the Stable Diffusion model to generate domain specific images found in medical imaging. We explore the sub-components of the Stable Diffusion pipeline (the variational autoencoder, the U-Net and the text-encoder) to fine-tune the model to generate medical images. We benchmark the efficacy of these efforts using quantitative image quality metrics and qualitative radiologist-driven evaluations that accurately represent the clinical content of conditional text prompts. Our best-performing model improves upon the stable diffusion baseline and can be conditioned to insert a realistic-looking abnormality on a synthetic radiology image, while maintaining a 95% accuracy on a classifier trained to detect the abnormality.