Aligning Fetal Anatomy with Kinematic Tree Log-Euclidean PolyRigid Transforms

2026-03-02

AI Summary

Existing fetal MRI modeling approaches often neglect internal volumetric structure and struggle to maintain anatomical consistency and topological correctness under large articulated deformations. To address this, this work proposes a differentiable volumetric human model based on SMPL, incorporating a novel KTPolyRigid transformation that integrates a kinematic tree, Log-Euclidean metric, and PolyRigid framework. This formulation effectively resolves the ambiguity of Lie algebra representations under large-angle motions, ensuring that the resulting deformation fields are smooth, bijective, and biologically plausible. Evaluated on 53 fetal MRI scans, the method significantly reduces folding artifacts and enables robust inter-subject registration and template-based organ segmentation with minimal reliance on labeled data.

Technology Category

• Machine Learning: Learning with Manifolds
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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.

Problem

• articulated bodies
• volumetric structures
• anatomical consistency
• medical imaging
• deformation methods

Innovation

• KTPolyRigid
• volumetric registration
• fetal MRI
• bijective deformation
• kinematic tree