PIVM: Diffusion-Based Prior-Integrated Variation Modeling for Anatomically Precise Abdominal CT Synthesis

Dinglun He, Baoming Zhang, Xu Wang, Yao Hao, Deshan Yang +1 more
3/23/2026
cs.CV

Official code: BZNR3/PIVM (1 star, MIT, last commit 2026-03-23).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

BZNR3/PIVMOfficial100%
MIT

[ISBI '26] Diffusion-Based Prior-Integrated Variation Modeling for Anatomically Precise Abdominal CT Synthesis

10PythonMar 23, 20267 months agoMIT

Similar Papers

FOSCU: Feasibility of Synthetic MRI Generation via Duo-Diffusion Models for Enhancement of 3D U-Nets in Hepatic Segmentation

90% match2026

Prior-Guided Residual Diffusion: Calibrated and Efficient Medical Image Segmentation

87% match2025

Sketch2CT: Multimodal Diffusion for Structure-Aware 3D Medical Volume Generation

87% match2026

Generation of Heterogeneous PET Images from Uniform Organ Activity Maps Using a Pretrained Domain-Adapted Diffusion Model

86% match2026

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

86% match2024

Feature-Space Guided Diffusion for Realistic Ultrasound Image Synthesis

86% match1 repo2026

Cite this paper

@article{he2026pivm,
  title  = {PIVM: Diffusion-Based Prior-Integrated Variation Modeling for Anatomically Precise Abdominal CT Synthesis},
  author = {Dinglun He and Baoming Zhang and Xu Wang and Yao Hao and Deshan Yang and Ye Duan},
  year   = {2026},
  eprint = {2603.22626},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2603.22626v1}
}

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/2603.22626.svg)](https://codeofpaper.com/paper/2603.22626)

Discussion