AbdomenGen: Sequential Volume-Conditioned Diffusion Framework for Abdominal Anatomy Generation

2026-04-14

AI Summary

This study addresses the lack of controllable and clinically meaningful methods for generating abdominal anatomical structures in medical imaging. The authors propose a sequential volumetric conditional diffusion framework that synthesizes organ masks iteratively, conditioned on a body mask and previously generated organs, thereby ensuring global anatomical consistency while enabling independent control over multiple organs. A key innovation is the introduction of a Volumetric Control Scalar (VCS), which decouples organ size from overall body habitus, allowing for interpretable volume adjustment and disentangled inter-organ control. Experiments demonstrate high geometric fidelity across 11 abdominal organs—e.g., achieving a Dice score of 0.83 ± 0.05 for the liver—with the VCS stably calibrated within the range [−3, +3] and reducing the distributional distance to clinical cohorts by 73.6% compared to baseline training data.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Computational phantoms are widely used in medical imaging research, yet current systems to generate controlled, clinically meaningful anatomical variations remain limited. We present AbdomenGen, a sequential volume-conditioned diffusion framework for controllable abdominal anatomy generation. We introduce the \textbf{Volume Control Scalar (VCS)}, a standardized residual that decouples organ size from body habitus, enabling interpretable volume modulation. Organ masks are synthesized sequentially, conditioning on the body mask and previously generated structures to preserve global anatomical coherence while supporting independent, multi-organ control. Across 11 abdominal organs, the proposed framework achieves strong geometric fidelity (e.g., liver dice $0.83 \pm 0.05$), stable single-organ calibration over $[-3,+3]$ VCS, and disentangled multi-organ modulation. To showcase clinical utility with a hepatomegaly cohort selected from MERLIN, Wasserstein-based VCS selection reduces distributional distance of training data by 73.6\% . These results demonstrate calibrated, distribution-aware anatomical generation suitable for controllable abdominal phantom construction and simulation studies.

Problem

• computational phantoms
• abdominal anatomy generation
• anatomical variations
• medical imaging
• controllable generation

Innovation

• Volume Control Scalar
• sequential diffusion
• anatomical disentanglement
• controllable generation
• computational phantom