Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.02371 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908861360766976 |
|---|---|
| author | Liu, Yingcheng Taymourtash, Athena Liu, Yang Turk, Esra Abaci Wells, William M. Joskowicz, Leo Grant, P. Ellen Golland, Polina |
| author_facet | Liu, Yingcheng Taymourtash, Athena Liu, Yang Turk, Esra Abaci Wells, William M. Joskowicz, Leo Grant, P. Ellen Golland, Polina |
| contents | Automated analysis of articulated bodies is crucial in medical imaging. Existing surface-based models often ignore internal volumetric structures and rely on deformation methods that lack anatomical consistency guarantees. To address this problem, we introduce a differentiable volumetric body model based on the Skinned Multi-Person Linear (SMPL) formulation, driven by a new Kinematic Tree-based Log-Euclidean PolyRigid (KTPolyRigid) transform. KTPolyRigid resolves Lie algebra ambiguities associated with large, non-local articulated motions, and encourages smooth, bijective volumetric mappings. Evaluated on 53 fetal MRI volumes, KTPolyRigid yields deformation fields with significantly fewer folding artifacts. Furthermore, our framework enables robust groupwise image registration and a label-efficient, template-based segmentation of fetal organs. It provides a robust foundation for standardized volumetric analysis of articulated bodies in medical imaging. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_02371 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Aligning Fetal Anatomy with Kinematic Tree Log-Euclidean PolyRigid Transforms Liu, Yingcheng Taymourtash, Athena Liu, Yang Turk, Esra Abaci Wells, William M. Joskowicz, Leo Grant, P. Ellen Golland, Polina Computer Vision and Pattern Recognition Graphics Automated analysis of articulated bodies is crucial in medical imaging. Existing surface-based models often ignore internal volumetric structures and rely on deformation methods that lack anatomical consistency guarantees. To address this problem, we introduce a differentiable volumetric body model based on the Skinned Multi-Person Linear (SMPL) formulation, driven by a new Kinematic Tree-based Log-Euclidean PolyRigid (KTPolyRigid) transform. KTPolyRigid resolves Lie algebra ambiguities associated with large, non-local articulated motions, and encourages smooth, bijective volumetric mappings. Evaluated on 53 fetal MRI volumes, KTPolyRigid yields deformation fields with significantly fewer folding artifacts. Furthermore, our framework enables robust groupwise image registration and a label-efficient, template-based segmentation of fetal organs. It provides a robust foundation for standardized volumetric analysis of articulated bodies in medical imaging. |
| title | Aligning Fetal Anatomy with Kinematic Tree Log-Euclidean PolyRigid Transforms |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2603.02371 |