Equivariant Symmetry-Aware Head Pose Estimation for Fetal MRI

2025-12-04

AI Summary

Estimating 6-degree-of-freedom (6-DoF) pose in fetal MRI is challenging due to head motion, anatomical bilateral symmetry, low resolution, and noise. To address this, we propose E(3)-Pose—the first method that jointly models E(3) equivariance and explicit anatomical symmetry via an equivariant graph neural network. Our approach constructs symmetry-aware equivariant feature representations that simultaneously satisfy rotation/translation equivariance and left-right reflection invariance, enabling robust pose regression. Integrated with fast pre-sampled 3D volume registration, it supports automatic localization of 2D diagnostic slices. Evaluated on multiple clinical fetal MRI datasets, E(3)-Pose achieves state-of-the-art performance, reducing mean pose estimation error by 32.7% over existing methods, and demonstrates strong cross-domain generalization. The code is publicly available, underscoring its potential for clinical deployment.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We present E(3)-Pose, a novel fast pose estimation method that jointly and explicitly models rotation equivariance and object symmetry. Our work is motivated by the challenging problem of accounting for fetal head motion during a diagnostic MRI scan. We aim to enable automatic adaptive prescription of 2D diagnostic MRI slices with 6-DoF head pose estimation, supported by 3D MRI volumes rapidly acquired before each 2D slice. Existing methods struggle to generalize to clinical volumes, due to pose ambiguities induced by inherent anatomical symmetries, as well as low resolution, noise, and artifacts. In contrast, E(3)-Pose captures anatomical symmetries and rigid pose equivariance by construction, and yields robust estimates of the fetal head pose. Our experiments on publicly available and representative clinical fetal MRI datasets demonstrate the superior robustness and generalization of our method across domains. Crucially, E(3)-Pose achieves state-of-the-art accuracy on clinical MRI volumes, paving the way for clinical translation. Our implementation is available at github.com/ramyamut/E3-Pose.

Problem

• Estimates fetal head pose in MRI scans for adaptive slice prescription.
• Addresses pose ambiguities from anatomical symmetries and image artifacts.
• Improves robustness and generalization in clinical fetal MRI applications.

Innovation

• Models rotation equivariance and object symmetry
• Uses 3D MRI volumes for 6-DoF head pose estimation
• Achieves robust accuracy on clinical fetal MRI datasets