Saved in:
Bibliographic Details
Main Authors: He, Dinglun, Zhang, Baoming, Wang, Xu, Hao, Yao, Yang, Deshan, Duan, Ye
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.22626
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914416689152000
author He, Dinglun
Zhang, Baoming
Wang, Xu
Hao, Yao
Yang, Deshan
Duan, Ye
author_facet He, Dinglun
Zhang, Baoming
Wang, Xu
Hao, Yao
Yang, Deshan
Duan, Ye
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_22626
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PIVM: Diffusion-Based Prior-Integrated Variation Modeling for Anatomically Precise Abdominal CT Synthesis
He, Dinglun
Zhang, Baoming
Wang, Xu
Hao, Yao
Yang, Deshan
Duan, Ye
Computer Vision and Pattern Recognition
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.
title PIVM: Diffusion-Based Prior-Integrated Variation Modeling for Anatomically Precise Abdominal CT Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.22626