A Generative Foundation Model for Chest Radiography

The scarcity of well-annotated, diverse medical images is a major hurdle for developing reliable artificial intelligence (AI) models in health care. Substantial technical advances have been made in generative foundation models for natural images.

In this article we develop ChexGen, a generative vision-language foundation model that introduces a unified framework for text-, mask-, and bounding box-guided synthesis of chest radiographs. Built on the latent diffusion transformer architecture, ChexGen was pretrained on the largest curated chest x-ray dataset to date, consisting of 960,000 radiograph-report pairs.

ChexGen achieves accurate synthesis of radiographs through expert evaluations and quantitative metrics. We demonstrate the utility of ChexGen for training data augmentation and supervised pretraining, which led to performance improvements across disease classification, detection, and segmentation tasks using a small fraction of training data. Furthermore, the model enables the creation of diverse patient cohorts that enhance model fairness by detecting and mitigating demographic biases.

The study supports the transformative role of generative foundation models in building more accurate, data-efficient, and equitable medical AI systems.