FleXray: Universal Clinical X-ray Segmentation
MIT CSAIL releases FleXray, a model that segments 60 anatomical structures in clinical X-rays.
FleXray is a generalist model for anatomical segmentation across the body in clinical X-rays, trained without large manually labeled X-ray sets. A physics-based engine uses existing 3D whole-body CT segmentations and generative image editing to simulate fully annotated 2D X-rays with varied appearance, physiology, and geometry. Trained on those simulations, it segments 60 anatomical structures on unseen research datasets and real-world X-rays. The authors release the model, code, a full-body segmentation dataset, and a local browser tool.
- A physics-based engine simulates annotated X-rays from whole-body CT.
- FleXray segments 60 structures on unseen and real-world radiographs.
- Supports disease grading, intervention navigation, and pathology learning.
- Model, code, dataset, and a browser tool are publicly released.
From the original article
1 min read at arxiv.orgX-ray is medicine's most widely used imaging modality, yet remains among its least quantitative. Unlike volumetric modalities like CT or MRI, X-ray collapses 3D anatomy into a 2D projection, causing structures to overlap and anatomical boundaries to be ambiguous, even to experts.
By Victor Ion Butoi · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.