MIT Releases FleXray, an Open X-ray Foundation Model Segmenting 60 Anatomical Structures
rishabh16_ · x · 2026-09-24
Researchers from MIT CSAIL, MGH, and Harvard Medical School (Victor Ion Butoi et al.) released FleXray, a universal foundation model for clinical X-ray anatomy segmentation.
- Trained on physics-based CT-to-DRR projections, real radiographs, and generative-model-enhanced DRRs.
- Predicts 60 anatomical structures across body regions, views, and acquisition settings, outperforming existing generalist baselines on diverse real X-ray datasets.
- Fully open: paper, code, weights on Hugging Face, training data, tutorial, plus an MCP connector.
- Browser demo runs entirely on-device via WebGPU/WebAssembly; ensemble of five models with 16-sample test-time augmentation.
- Explicitly a research demo, not a medical device.
Related event: MIT releases FleXray, open X-ray anatomical segmentation model(2 posts)→
More from Research
- Neural Spectral Capacity: a training-free architecture score that beats #Params and prunes LLaMA-7B 5900x faster — CityU-HongKong · 2026-09-25
- HRI 2027 Adds Archival Industry White Paper Track for Real-World Robot Deployments — petitegeek · 2026-09-25
- Study: Reasoning hurts 15.7% of multimodal embeddings; training-free SURE router fixes it — _reachsumit · 2026-09-25
- Google scales learned cross-task relationships in YouTube's production recommender — _reachsumit · 2026-09-25
- ByteDance's OneTrans-V2 unifies retrieval, pre-rank and fine-rank, lifting GMV 9.74% — _reachsumit · 2026-09-25
- Training-free Seek framework beats BM25 by 82% on BRIGHT via self-evaluative iteration — _reachsumit · 2026-09-25