# MIT Group Trains a Whole-Body X-ray Segmenter on Synthetic Radiographs Rendered From CT Scans

FleXray predicts 60 anatomical structures on real clinical X-rays after training on physics-simulated projections, with code released under a permissive license.

- Published: 2026-09-26T06:26:42.860Z
- Canonical: https://polylog.news/ai/2026-09-26/mit-group-trains-a-whole-body-x-ray-segmenter-on-synthetic-r
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [arXiv](https://arxiv.org/abs/2609.26756)

A team from MIT has published FleXray, a generalist segmentation model that predicts 60 anatomical structures across the whole body in clinical radiographs. The paper, by Victor Ion Butoi, Vivek Gopalakrishnan, John V. Guttag, Adrian V. Dal…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-26/mit-group-trains-a-whole-body-x-ray-segmenter-on-synthetic-r (subscription information: https://polylog.news/pricing).