Towards Markerless Intraoperative Tracking of Deformable Spine Tissue

TL;DR

This paper presents a novel markerless intraoperative spine tracking system using RGB-D imaging, including a new clinical dataset, a segmentation network, and a multi-task framework for deformable spine registration.

Contribution

It introduces the first real-world clinical RGB-D dataset for spine surgery and develops SpineAlign, a system for deformable tissue tracking without markers.

Findings

First clinical RGB-D dataset for spine surgery

Effective segmentation network for intraoperative scenes

Multi-task framework accurately predicts key regions for registration

Abstract

Consumer-grade RGB-D imaging for intraoperative orthopedic tissue tracking is a promising method with high translational potential. Unlike bone-mounted tracking devices, markerless tracking can reduce operating time and complexity. However, its use has been limited to cadaveric studies. This paper introduces the first real-world clinical RGB-D dataset for spine surgery and develops SpineAlign, a system for capturing deformation between preoperative and intraoperative spine states. We also present an intraoperative segmentation network trained on this data and introduce CorrespondNet, a multi-task framework for predicting key regions for registration in both intraoperative and preoperative scenes.