MAISI: Medical AI for Synthetic Imaging

Pengfei Guo, Can Zhao, Dong Yang, Ziyue Xu, Vishwesh Nath +6 more
9/13/2024
eess.IVcs.AIcs.CV

No official code found. Best implementation: Project-MONAI/tutorials (2,522 stars, Apache-2.0, PyTorch, last commit 2026-04-14).

Abstract

Medical imaging analysis faces challenges such as data scarcity, high annotation costs, and privacy concerns. This paper introduces the Medical AI for Synthetic Imaging (MAISI), an innovative approach using the diffusion model to generate synthetic 3D computed tomography (CT) images to address those challenges. MAISI leverages the foundation volume compression network and the latent diffusion model to produce high-resolution CT images (up to a landmark volume dimension of 512 x 512 x 768 ) with flexible volume dimensions and voxel spacing. By incorporating ControlNet, MAISI can process organ segmentation, including 127 anatomical structures, as additional conditions and enables the generation of accurately annotated synthetic images that can be used for various downstream tasks. Our experiment results show that MAISI's capabilities in generating realistic, anatomically accurate images for diverse regions and conditions reveal its promising potential to mitigate challenges using synthetic data.

View on arXivView PDF

Code Implementations(1)

Project-MONAI/tutorialsCommunity100%
PyTorchApache-2.0

MONAI Tutorials

2,522798Shell, PythonAug 19, 20206 months agoApache-2.0
jupyter-notebookmonaimonai-tutorialsmonai-workflowspytorch

Similar Papers

MedLoRD: A Medical Low-Resource Diffusion Model for High-Resolution 3D CT Image Synthesis

87% match2025

MedDiff-FM: A Diffusion-based Foundation Model for Versatile Medical Image Applications

85% match2024

See More, Change Less: Anatomy-Aware Diffusion for Contrast Enhancement

85% match2025

LAND: Lung and Nodule Diffusion for 3D Chest CT Synthesis with Anatomical Guidance

85% match2025

MedIL: Implicit Latent Spaces for Generating Heterogeneous Medical Images at Arbitrary Resolutions

84% match2025

Diffuse-UDA: Addressing Unsupervised Domain Adaptation in Medical Image Segmentation with Appearance and Structure Aligned Diffusion Models

84% match2024

Cite this paper

@article{guo2024maisi,
  title  = {MAISI: Medical AI for Synthetic Imaging},
  author = {Pengfei Guo and Can Zhao and Dong Yang and Ziyue Xu and Vishwesh Nath and Yucheng Tang and Benjamin Simon and Mason Belue and Stephanie Harmon and Baris Turkbey and Daguang Xu},
  year   = {2024},
  eprint = {2409.11169},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2409.11169v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2409.11169.svg)](https://codeofpaper.com/paper/2409.11169)

Discussion