Open-source xvr AI aligns live X-ray with 3D CT at submillimeter accuracy, published in Nature
Dr_Alex_Crimi · x · 2026-09-29
Researchers published xvr in Nature: a self-supervised framework combining patient-specific neural networks with gradient-based optimization to rapidly register intraoperative 2D X-ray fluoroscopy to preoperative 3D CT/MRI volumes at submillimeter accuracy, with open-source code.
- Problem it solves: intensity-based 2D/3D registration needs per-patient hyperparameter tuning, while deep learning approaches require large labeled datasets and don't generalize across anatomies.
- Key idea: self-supervision plus patient-specific networks—no manual labels, generalizes across fluoroscopy-guided procedures.
- Impact: real-time alignment of live X-ray with 3D scans for surgical navigation and surgical robotics.
Related event: Open-Source AI Achieves Sub-millimeter X-ray to 3D CT Registration(2 posts)→
More from Apps
- jiangshan-map: interactive atlas of Chinese history across 18 dynasties hits 6.5k stars — DeanChensj · 2026-11-16
- SimpleListen turns articles, newsletters and ChatGPT research into personal podcasts — haltakov · 2026-11-16
- Five case studies unpack how Google AI Overviews hit clicks and CTR in France — gaganghotra_ · 2026-11-16
- Animating AI-generated 2D game art with FLUX.2 klein: masked redraws work but remain a hack — emilrueh · 2026-11-16
- Hands-on With SolidCraft: Japan's Free Open-Source 3D CAD With AI-Conversational Modeling — burhop · 2026-11-16
- Tip: Connect AI assistant Muse to your school's Canvas to track kids' homework and grades — sytelus · 2026-11-16