Scaling Generative Foundation Models for Chest Radiography with Rectified Flow Transformers
This work addresses the need for high-fidelity, controllable chest radiograph synthesis to improve dataset diversity and robustness of diagnostic AI models.
The authors introduce a 1.3B-parameter generative foundation model for chest radiograph synthesis, trained on 1.2M radiographs. The model achieves state-of-the-art fidelity, producing images indistinguishable from real ones to clinical experts.
We introduce the first generative foundation model for chest radiograph synthesis trained from scratch at the billion-parameter scale. Existing radiographic AI models often suffer from poor generalisation across patient subpopulations, institutions, and acquisition settings, resulting in limited real-world clinical utility. Controlled, high-fidelity synthesis of chest radiographs is a promising path toward diversifying clinical datasets and evaluating the robustness of diagnostic models. Therefore, we present the largest specialist generative foundation model for chest radiographs to date, with over 1.3B parameters, trained for 1.6T tokens on a curated, heterogeneous dataset comprising 1.2M radiographs and clinical expert-guided metadata. Our model supports controllable radiograph generation and editing across multiple demographic subgroups, acquisition views, and a dozen pathologies. Moreover, we significantly advance the state of the art in radiograph synthesis fidelity, producing images that are indistinguishable from real radiographs to clinical experts.