PIVM: Diffusion-Based Prior-Integrated Variation Modeling for Anatomically Precise Abdominal CT Synthesis
This work addresses data scarcity for medical imaging researchers and practitioners, offering a domain-specific solution for generating synthetic abdominal CT images to aid in segmentation and diagnostic model development.
The authors tackled the problem of limited abdominal CT data due to high annotation costs and privacy constraints by developing PIVM, a diffusion-based method for synthesizing anatomically precise CT images, which predicts voxel-wise intensity variations relative to organ-specific priors to ensure spatial alignment and realistic organ boundaries.
Abdominal CT data are limited by high annotation costs and privacy constraints, which hinder the development of robust segmentation and diagnostic models. We present a Prior-Integrated Variation Modeling (PIVM) framework, a diffusion-based method for anatomically accurate CT image synthesis. Instead of generating full images from noise, PIVM predicts voxel-wise intensity variations relative to organ-specific intensity priors derived from segmentation labels. These priors and labels jointly guide the diffusion process, ensuring spatial alignment and realistic organ boundaries. Unlike latent-space diffusion models, our approach operates directly in image space while preserving the full Hounsfield Unit (HU) range, capturing fine anatomical textures without smoothing. Source code is available at https://github.com/BZNR3/PIVM.