3D MedDiffusion: A 3D Medical Diffusion Model for Controllable and High-quality Medical Image Generation
This addresses the problem of suboptimal 3D medical image generation for healthcare and research, offering a universal framework, though it appears incremental as it builds on diffusion models.
The paper tackles the challenge of generating high-quality 3D medical images by introducing 3D MedDiffusion, a model that achieves superior generative quality and strong generalizability across tasks like sparse-view CT reconstruction, with results surpassing state-of-the-art methods.
The generation of medical images presents significant challenges due to their high-resolution and three-dimensional nature. Existing methods often yield suboptimal performance in generating high-quality 3D medical images, and there is currently no universal generative framework for medical imaging. In this paper, we introduce the 3D Medical Diffusion (3D MedDiffusion) model for controllable, high-quality 3D medical image generation. 3D MedDiffusion incorporates a novel, highly efficient Patch-Volume Autoencoder that compresses medical images into latent space through patch-wise encoding and recovers back into image space through volume-wise decoding. Additionally, we design a new noise estimator to capture both local details and global structure information during diffusion denoising process. 3D MedDiffusion can generate fine-detailed, high-resolution images (up to 512x512x512) and effectively adapt to various downstream tasks as it is trained on large-scale datasets covering CT and MRI modalities and different anatomical regions (from head to leg). Experimental results demonstrate that 3D MedDiffusion surpasses state-of-the-art methods in generative quality and exhibits strong generalizability across tasks such as sparse-view CT reconstruction, fast MRI reconstruction, and data augmentation.