Markerless spinal tracking validated using routine intraoperative X-rays
Bridging the Markerless Tracking Validation Gap: Intraoperative X-ray Workflow Integration
Computer Vision and Pattern Recognition
Summary
Tracking the spine during surgery without attaching markers to bones is safer but hard to check for accuracy. The authors created a method that uses regular X-ray images taken during surgery to find the exact position of each vertebra and matches this to data from a special camera. This approach doesn't require extra equipment, changes to surgery, or additional X-rays. They tested it on animal bones and surgical data, showing it works reliably to measure how well markerless tracking methods perform.
What this means in practice
- •For surgical navigation teams: Use intraoperative X-rays already taken during spine surgery to validate and improve markerless tracking of vertebra positions without extra steps or radiation.
- •For medical device companies: Develop markerless tracking technologies for spine surgery with a built-in standard for accuracy verification based on routine imaging during operations.$Commercial implications: Enables companies to produce tracking systems with clinically validated accuracy using existing surgical imaging workflows.
Authors
Connor Daly, Salvatore Russo, Jinendra Ekanayake, Daniel S. Elson, Ferdinando Rodriguez y Baena
Abstract
Markerless intraoperative tracking of spinal anatomy via RGB-D sensors is a promising alternative to invasive bone-anchored fiducials, yet no existing clinical dataset provides independent subsurface ground truth for validating these methods. We address this gap with a clinically viable pipeline that derives per-vertebra 6-DoF pose from routine intraoperative C-arm fluoroscopy, co-registered to the RGB-D camera frame through a multimodal fiducial array detectable in both imaging modalities. Critically, the pipeline requires no additional radiation, instrumentation, or deviation from standard surgical workflows, relying solely on the fluoroscopic images already acquired during routine level checks. A calibrated transform chain links the vertebral pose recovered via multi-view 2D-3D CT-to-fluoroscopy registration to the RGB-D coordinate frame, enabling direct comparison of any markerless registration estimate against a subsurface reference. Ex vivo validation against optically tracked ovine vertebrae confirms end-to-end accuracy of 2.06 +- 0.29 mm and 3.35 +- 0.93 degrees, sufficient to serve as independent ground truth for methods with substantially larger errors. We demonstrate the pipeline's utility by evaluating two markerless registration strategies on clinical data spanning 11 vertebrae across 1,500 frames from three surgical sequences: the first such evaluation against an independent subsurface reference in a clinical setting. The proposed framework provides reusable infrastructure for benchmarking emerging markerless tracking methods on real surgical data.