FleXray: open-weight model does zero-shot anatomical segmentation on any X-ray
rishabh16_ · x · 2026-09-25
The ionbarrel team announced FleXray, an open-source, open-weight model for zero-shot anatomical segmentation on X-rays across body regions, viewing angles, and acquisition settings. It trains on large-scale synthetic supervision generated from 3D anatomy and transfers directly to real clinical X-rays. Project page, in-browser demo (upload your own X-rays), weights, code, and paper are all available. The team argues that extracting general, quantitative anatomical information from X-rays has remained remarkably hard despite their ubiquity, and is soliciting use cases from clinicians and med students.
More from Embodied
- NYU's Steertuning Lets a Robot Learn a Chore From 5 Minutes of Human Demo — CyberRobooo · 2026-11-11
- Boston Dynamics Atlas demoed with Blender 5.3 — TomLikesRobots · 2026-11-11
- Lamport Robotics posts robot 'wake-up test' demo video — R4nsack · 2026-11-11
- Embodied AI Faces Two-Order-of-Magnitude Data Gap as Industry Heads to 10M Hours — GaryMarcus · 2026-11-11
- NVIDIA hosts CoRL 2026 meetup on scaling robot training with Isaac Lab — m_wulfmeier · 2026-11-11
- Lighthouse extends Obsidian welding foundation model to run on any robotic platform — bennash · 2026-11-11