AbdomenGen: Sequential Volume-Conditioned Diffusion Framework for Abdominal Anatomy Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908964291084288 |
|---|---|
| author | Bhandari, Yubraj Dahal, Lavsen Segars, Paul Lo, Joseph Y. |
| author_facet | Bhandari, Yubraj Dahal, Lavsen Segars, Paul Lo, Joseph Y. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12969 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AbdomenGen: Sequential Volume-Conditioned Diffusion Framework for Abdominal Anatomy Generation Bhandari, Yubraj Dahal, Lavsen Segars, Paul Lo, Joseph Y. Computer Vision and Pattern Recognition 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. |
| title | AbdomenGen: Sequential Volume-Conditioned Diffusion Framework for Abdominal Anatomy Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.12969 |