Scaling Generative Foundation Models for Chest Radiography with Rectified Flow Transformers
Quick Answer
This paper shows that A new generative foundation model for chest radiograph synthesis, with over 1.3B parameters, has been developed to enhance clinical utility and generalization across diverse patient demographics.
Quick Take
Trained on 1.2M radiographs and 1.6T tokens, it achieves high-fidelity image synthesis indistinguishable from real radiographs, significantly advancing the state of the art.
Key Points
- Model trained from scratch with over 1.3 billion parameters.
- Utilizes a dataset of 1.2 million radiographs and expert metadata.
- Supports controllable generation across various demographics and pathologies.
- Achieves state-of-the-art fidelity in radiograph synthesis.
- Indistinguishable images from real radiographs to clinical experts.
Paper Resources
Source Excerpt
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. Therefo
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.