MedVAR: Towards Scalable and Efficient Medical Image Generation via Next-scale Autoregressive Prediction

TL;DR

MedVAR is a novel autoregressive foundation model for medical image generation that enables scalable, efficient, and high-quality synthesis across multiple organs, supporting downstream clinical applications.

Contribution

It introduces MedVAR, the first autoregressive model using next-scale prediction for scalable, efficient medical image synthesis with structured multi-scale representations.

Findings

Achieves state-of-the-art generative performance.

Supports multi-organ image synthesis with high fidelity and diversity.

Demonstrates scalability and efficiency in medical image generation.

Abstract

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.