MRG-R1: Reinforcement Learning for Clinically Aligned Medical Report Generation
This work addresses the critical issue of ensuring clinical accuracy in automated medical report generation for radiology, which is incremental as it builds on existing methods by focusing on semantic correctness rather than token-level objectives.
The paper tackled the problem of generating clinically correct medical reports from images by proposing a semantic-driven reinforcement learning method that optimizes report-level rewards based on key radiological findings, achieving state-of-the-art performance with CE-F1 scores of 51.88 on IU X-Ray and 40.39 on MIMIC-CXR.
Medical report generation (MRG) aims to automatically derive radiology-style reports from medical images to aid in clinical decision-making. However, existing methods often generate text that mimics the linguistic style of radiologists but fails to guarantee clinical correctness, because they are trained on token-level objectives which focus on word-choice and sentence structure rather than actual medical accuracy. We propose a semantic-driven reinforcement learning (SRL) method for medical report generation, adopted on a large vision-language model (LVLM). SRL adopts Group Relative Policy Optimization (GRPO) to encourage clinical-correctness-guided learning beyond imitation of language style. Specifically, we optimise a report-level reward: a margin-based cosine similarity (MCCS) computed between key radiological findings extracted from generated and reference reports, thereby directly aligning clinical-label agreement and improving semantic correctness. A lightweight reasoning format constraint further guides the model to generate structured "thinking report" outputs. We evaluate Medical Report Generation with Sematic-driven Reinforment Learning (MRG-R1), on two datasets: IU X-Ray and MIMIC-CXR using clinical efficacy (CE) metrics. MRG-R1 achieves state-of-the-art performance with CE-F1 51.88 on IU X-Ray and 40.39 on MIMIC-CXR. We found that the label-semantic reinforcement is better than conventional token-level supervision. These results indicate that optimizing a clinically grounded, report-level reward rather than token overlap,meaningfully improves clinical correctness. This work is a prior to explore semantic-reinforcement in supervising medical correctness in medical Large vision-language model(Med-LVLM) training.