Medical image generation is pivotal in applications like data augmentation for low-resource clinical tasks and privacy-preserving data sharing. However, developing a scalable generative backbone for medical imaging requires architectural efficiency, sufficient multi-organ data, and principled evaluation, yet current approaches leave these aspects unresolved. Therefore, we introduce MedVAR, the first autoregressive-based foundation model that adopts the next-scale prediction paradigm to enable fast and scale-up-friendly medical image synthesis. MedVAR generates images in a coarse-to-fine manner and produces structured multi-scale representations suitable for downstream use. To support hierarchical generation, we curate a harmonized dataset of around 440,000 CT and MRI images spanning six anatomical regions. Comprehensive experiments across fidelity, diversity, and scalability show that MedVAR achieves state-of-the-art generative performance and offers a promising architectural direction for future medical generative foundation models.
@article{arxiv.2602.14512,
title = {MedVAR: Towards Scalable and Efficient Medical Image Generation via Next-scale Autoregressive Prediction},
author = {Zhicheng He and Yunpeng Zhao and Junde Wu and Ziwei Niu and Zijun Li and Bohan Li and Lanfen Lin and Yueming Jin},
journal= {arXiv preprint arXiv:2602.14512},
year = {2026}
}