MIT's xvr matches surgical X-rays to 3D scans in seconds with sub-millimeter precision
MacrinePhD · x · 2026-09-20
Researchers at MIT CSAIL and Harvard have unveiled xvr, an AI system that aligns live 2D surgical X-rays with preoperative 3D scans (MRI/CT) to guide minimally invasive surgery.
- Speed and precision: Registration takes seconds with sub-millimeter accuracy, and the system reportedly produces zero hallucinations
- Rapid adaptation: Personalizing to each new patient takes only about 5 minutes—no retraining required per patient or procedure
- Technical approach: The model is trained on thousands of synthetic images generated from each patient's preoperative 3D scan
- Use cases: Primarily orthopedics and neurosurgery, where X-ray-based navigation is common; the goal is safer, more precise surgery and broader access to advanced navigation
Reported by MIT News on September 16, 2026.
More from Research
- Da7em Bench: independent AI benchmark scores models on 200 real client tasks across 12 areas — airesearch12 · 2026-09-20
- Researcher Accuses Laya Author of Overstating Work as Jev-Like System — Paimaamu · 2026-09-20
- LLM vs classical ML across 8 datasets: labeled data still favors SVM and XGBoost — Ok_Juggernaut2187 · 2026-09-20
- NVIDIA paper: routing voice-agent tool calls to a text LLM lifts recall above 92% — omarsar0 · 2026-09-20
- Claude Speeds Up 30+ Open-Source Biomolecular Models 4x on Average, All Code Open-Sourced — FinanceYF5 · 2026-09-20
- Developer Visualizes Object Tracking Results on OpenStreetMap via GNSS/IMU Trajectory and Depth Estimation — rsasaki0109 · 2026-09-20