# MIT's open-weight FleXray segments 60 anatomical structures in X-rays after training only on synthetic images rendered from CT scans

The team skipped manual X-ray annotation and used a physics-based engine to generate fully labeled 2D X-rays from existing 3D whole-body segmentations.

- Published: 2026-10-08T06:25:29.519Z
- Canonical: https://polylog.news/ai/2026-10-08/mit-s-open-weight-flexray-segments-60-anatomical-structures
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [arXiv](https://arxiv.org/pdf/2609.26756), [FleXray project (MIT CSAIL)](https://flexray.csail.mit.edu/)

MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL), working with Massachusetts General Hospital and Harvard Medical School, has released FleXray. It is a generalist model that segments 60 anatomical structures, from ribs…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-08/mit-s-open-weight-flexray-segments-60-anatomical-structures (subscription information: https://polylog.news/pricing).