RadHiera: Semantic Hierarchical Reinforcement Learning for Medical Report Generation

TL;DR

RadHiera is a hierarchical reinforcement learning framework that improves radiology report generation by modeling semantic dependencies, enhancing diagnostic accuracy, and ensuring consistency between report sections, leading to more reliable clinical documentation.

Contribution

It introduces a semantic hierarchical reinforcement learning approach that explicitly models dependencies between report sections, improving accuracy and consistency in medical report generation.

Findings

RadHiera outperforms state-of-the-art methods on chest X-ray benchmarks.

It enhances diagnostic accuracy and report consistency.

The framework adapts well to ultrasound report generation.

Abstract

Vision-language models have shown promising results in radiology report generation. However, most existing methods generate reports as flat text and do not explicitly model the semantic dependency between the Findings and Impression sections, which can lead to inconsistencies between clinical observations and diagnostic conclusions. In this paper, we propose RadHiera, a semantic hierarchical reinforcement learning framework for radiology report generation. RadHiera follows the semantic organization of radiology reports by first optimizing overall report quality, then improving the diagnostic accuracy of the Impression section, and finally enforcing consistency between Findings and Impression so that diagnostic conclusions are supported by clinical evidence. Specifically, we begin with a base reward that combines linguistic quality and medical factuality to provide supervision on the whole report. On this basis, we introduce a severity-aware reward for the Impression section that places greater emphasis on errors involving clinically critical conditions, thereby reducing both missed diagnoses and overstatement. We further enforce cross-section consistency using Expert Model-derived label sets, with subset constraints and hallucination penalties to ensure that impressions remain faithful to the findings. Experiments on three public chest X-ray benchmarks show that RadHiera consistently improves diagnostic accuracy and inter-section consistency over state-of-the-art methods, while also demonstrating good adaptability to report generation in ultrasound report generation.