Reproduce “Grounding Radiology Reports in 3D Chest CT: Results of the ReXGrounding Challenge” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Mohammed Baharoon, Mahmoud Hussain Alabbad, Sung Eun Kim, Xiaoman Zhang, Lucas Bijnens, Zirong Chen, Jiayu Wang, Xi Ouyang and 54 more

The authors present a benchmark for grounding chest CT report findings as separate three-dimensional masks. Models must use the finding’s location and description, not just its category. On the 300-scan test set, Team 1 achieved mean Dice 0.3755. This result covers non-contrast chest CT lung and pleural findings from one source; it does not establish clinical equivalence or a solved task.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.