FleXray enables whole-body anatomy segmentation in X-ray images
FleXray: Universal Clinical X-ray Segmentation
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
X-rays are very common in medicine but hard to analyze precisely because they show all body parts superimposed in one flat image. The authors created FleXray, a computer program that can identify and label many different body parts in any X-ray picture. They trained FleXray using computer-generated X-rays made from 3D CT scans, so it did not need lots of manual labeling. This approach helps doctors measure things in X-rays more accurately and supports new uses like guiding procedures or detecting diseases more easily.
What this means in practice
- •For radiology departments: Automate measurement and assessment of anatomical features in X-rays for standardized disease grading and morphometric analysis.
- •For interventional radiologists: Provide robust anatomical navigation cues during X-ray-guided interventions by segmenting key structures in real-time images.
Authors
Victor Ion Butoi, Vivek Gopalakrishnan, John V. Guttag, Adrian V. Dalca, Neel Dey
Abstract
X-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. As a result, labeling X-ray databases for training general-purpose segmentation systems is impractical, leaving morphometric and functional X-ray analysis confined to narrow anatomical regions and applications. To this end, we present FleXray, a generalist model for anatomical segmentation across the entire body in clinical X-rays. Instead of curating large, manually annotated X-ray datasets, we build a scalable, physics-based generative X-ray data engine. Using existing 3D whole-body CT segmentation datasets and generative image-editing models, we simulate fully-annotated 2D X-rays with diverse appearances, physiological properties, and imaging geometries. Trained on these simulations, FleXray accurately segments 60 anatomical structures across unseen research datasets and in-the-wild X-rays. We further show that FleXray makes X-rays directly amenable to quantitative analysis, enabling automated measurements for disease grading, robust navigation during X-ray-guided interventions, and data-efficient learning of pathological targets. We release the model, code, a full-body X-ray segmentation dataset, and a local, easy-to-use browser-based tool at https://flexray.csail.mit.edu .