OnPoint AR Spine System Records 1.1 mm Error in Cadaver Study
OnPoint Surgical said in a press release that the Journal of Spine Surgery published a peer reviewed study of its augmented reality navigation system. The cadaver study reported a mean positional error of 1.1 mm and a mean angular error of 1.3 degrees for pedicle screw placement.
Three experienced spine surgeons placed 80 screws across five specimens, including osteoporotic anatomy. The procedures covered the thoracic and lumbosacral spine using open and minimally invasive techniques. Postoperative CT scans were compared with planned trajectories, while a blinded musculoskeletal radiologist independently graded placement accuracy.
All 80 screws were classified as accurately placed, with no medial or inferior breaches. The researchers reported that positional and angular errors were two to five times smaller than figures previously reported for major navigation and robotic systems. The findings are limited to cadaveric specimens and do not provide clinical outcome data.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Life AI Weekly or Daily AI Brief.
Also, consider following us on social media:
More from Life Sciences
Oct 13 Suvoda Expands Sofia to All New RTSM and eCOA Trials Oct 13 HealthpointCapital Invests in Surgical Software Company Ospitek Oct 13 Prologue Medicines names Stephen Harrison chief scientific officer Oct 13 symplr Survey Finds Nearly Half of Hospital Operations Remain Manual Oct 13 MediRoutes Launches Predictive ETAs for Medical TransportLife AI Weekly
Weekly coverage of AI applications in healthcare, drug development, biotechnology research, and genomics breakthroughs.
Whitepaper
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Tensordyne
This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.
Read moreYou may also like
CMS Creates Procedure Code for Computer Aided Neuraxial Guidance
Proprioceptive AI Details Model Interpretability Roadmap
NYU Langone Tests AI Tool to Fill Radiology Training Gaps
HealthpointCapital Invests in Surgical Software Company Ospitek
DentScribe Releases Benchmark for AI Dental Notes
Daily AI Brief: the AI news that matters, in your inbox.