Scaling medical imaging report generation with multimodal reinforcement learning
In the authors' words
Abstract In medical imaging report generation, supervised fine-tuning can overfit to superficial patterns and generalize poorly across institutions. We introduce Universal Report Generation (UNIRG), which adopts reinforcement learning to directly optimize clinically meaningful quality criteria. With this framework, we developed UNIRG-CXR, an 8-billion-parameter vision–language model trained on four public datasets (MIMIC-CXR, CheXpert Plus, ReXGradient-160k and IU-Xray) by supervised fine-tuning followed by reinforcement learning (group-relative policy optimization) against a composite lexical, semantic and clinical-error reward. We evaluated held-out test sets and an external proprietary dataset, with RadCliQ as primary metric and expert radiologist validation. Here we show that our method improves report quality and generalization: UNIRG-CXR surpasses prior models on the ReXrank benchmark across four datasets and two generation settings, exceeding the previous best score by over 50% on two test sets, and produces fewer clinically significant errors while maintaining performance on unseen data sources and across demographic subgroups.
In plain words AI summary
The authors created UNIRG, a system that uses reinforcement learning to improve medical imaging reports. They built UNIRG-CXR, an 8-billion-parameter model trained on four public datasets using supervised fine-tuning followed by reinforcement learning. The model beat previous best scores by over 50% on two test sets in the ReXrank benchmark. It also made fewer clinically significant errors and maintained performance on unseen data and across demographic groups.
Written by Kimi K2.5 using only the abstract above. Jev checked that every sentence is supported by the abstract sentences it cites, and removed any that were not. Point at a sentence to highlight its source.
Appeared: Saturday, November 14. Nature Communications. Peer-reviewed journal.