Landmark Detection Uncertainty as a Reliability Weight for Robust Landmark-based 2D/3D Pelvic Pose Estimation

Yehyun Suh, Brayden Schott, Chou Mo, John Ryan Martin, Daniel Moyer

Keywords: Uncertainty-Weighted Pose Estimation, Landmark-based 2D/3D Registration, Monte Carlo Dropout, Epistemic Uncertainty Modeling

Abstract: Landmark-based 2D/3D pelvis registration is vulnerable to noisy or ambiguous landmark detections in fluoroscopy, which can destabilize downstream pose estimation. We present an uncertainty-aware registration framework that models epistemic uncertainty in predicted landmarks and incorporates it directly into the Perspective-n-Point formulation. Using Monte Carlo dropout within a U-Net detector, we compute per-landmark reliability per sample using the variance of multiple stochastic forward passes. These reliability estimates guide two complementary strategies: continuous weighting, which integrates uncertainty into a weighted PnP optimization, and discrete selection, which removes the most uncertain landmarks during inference. We evaluate the framework on synthetic fluoroscopy derived from a public pelvic CT dataset. Our experiments show that uncertainty provides a principled mechanism for identifying unreliable landmarks and stabilizing pose estimation, enabling more robust 2D/3D registration and establishing a foundation for uncertainty-guided image-guided surgical workflows.

Primary Subject Area: Image Registration

Secondary Subject Area: Uncertainty Estimation

Registration Requirement: Yes

Reproducibility: https://github.com/yehyunsuh/Landmark-based-2D-3D-Registration-Uncertainty

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 132