MedGen3D: A Deep Generative Framework for Paired 3D Image and Mask Generation

TL;DR

MedGen3D introduces a novel deep generative framework that synthesizes paired 3D medical images and masks, enhancing data availability and quality for medical image segmentation tasks.

Contribution

The paper presents MedGen3D, the first framework to generate complete 3D medical images with aligned segmentation masks using a multi-condition diffusion model.

Findings

Synthetic data is diverse and faithful to real data.

Generated images and masks are accurately aligned.

Improves downstream segmentation performance.

Abstract

Acquiring and annotating sufficient labeled data is crucial in developing accurate and robust learning-based models, but obtaining such data can be challenging in many medical image segmentation tasks. One promising solution is to synthesize realistic data with ground-truth mask annotations. However, no prior studies have explored generating complete 3D volumetric images with masks. In this paper, we present MedGen3D, a deep generative framework that can generate paired 3D medical images and masks. First, we represent the 3D medical data as 2D sequences and propose the Multi-Condition Diffusion Probabilistic Model (MC-DPM) to generate multi-label mask sequences adhering to anatomical geometry. Then, we use an image sequence generator and semantic diffusion refiner conditioned on the generated mask sequences to produce realistic 3D medical images that align with the generated masks. Our proposed framework guarantees accurate alignment between synthetic images and segmentation maps. Experiments on 3D thoracic CT and brain MRI datasets show that our synthetic data is both diverse and faithful to the original data, and demonstrate the benefits for downstream segmentation tasks. We anticipate that MedGen3D's ability to synthesize paired 3D medical images and masks will prove valuable in training deep learning models for medical imaging tasks.