An Optimization-based Baseline for Rigid 2D/3D Registration Applied to Spine Surgical Navigation Using CMA-ES

TL;DR

This work addresses the problem of accurate 2D/3D registration for spine surgical navigation by proposing a coarse-to-fine framework guided by CMA-ES. The method performs coarse alignment on downsampled data using multi-scale normalized cross-correlation ($mNCC$) and refines on full-resolution data with Gradient Correlation ($GC$), operating on a moving vertebral segmentation $V$ and fixed image $I$ via pose $\theta \in SE(3)$. Validation on 15 spine CT/X-ray pairs (cervical, thoracic, lumbar) shows strong results for thoracic and lumbar regions while noting challenges in the cervical region due to anatomy, suggesting the approach as a robust optimization-based baseline to complement learning-based registration. This framework has potential clinical relevance, offering a principled, optimization-driven refinement that can be integrated with learning-based methods to improve accuracy and reliability in spine navigation.

Abstract

A robust and efficient optimization-based 2D/3D registration framework is crucial for the navigation system of orthopedic surgical robots. It can provide precise position information of surgical instruments and implants during surgery. While artificial intelligence technology has advanced rapidly in recent years, traditional optimization-based registration methods remain indispensable in the field of 2D/3D registration.he exceptional precision of this method enables it to be considered as a post-processing step of the learning-based methods, thereby offering a reliable assurance for registration. In this paper, we present a coarse-to-fine registration framework based on the CMA-ES algorithm. We conducted intensive testing of our method using data from different parts of the spine. The results shows the effectiveness of the proposed framework on real orthopedic spine surgery clinical data. This work can be viewed as an additional extension that complements the optimization-based methods employed in our previous studies.