RL-ACRGNet: Reinforcement Learning-Based Chest Radiology Report Generation Network
2026-06-01 • Artificial Intelligence
Artificial IntelligenceMachine Learning
AI summaryⓘ
The authors developed a new deep learning model called RL-ACRGNet to help automate writing medical imaging reports, which doctors usually do by hand and can take a lot of time. Their method combines two types of neural networks and uses reinforcement learning to better understand detailed images and generate clearer, more accurate reports. They tested their model on two big datasets of chest X-rays and found it performed better than previous methods in producing high-quality, clinically useful descriptions. This approach could help make medical imaging interpretations faster and more consistent.
medical imagingradiology reportsdeep learningDenseNetLSTMreinforcement learningIU-Xray datasetMIMIC-CXR datasetvisual-semantic embeddingsevaluation metrics
Authors
Yogesh Kumar Meena, Saurabh Agarwal, K. V. Arya
Abstract
Medical imaging interpretation is a foundational pillar of modern clinical diagnostics, yet the manual generation of radiology reports remains a time-consuming process prone to interpretation inconsistencies. Within the field of medical AI, automating these descriptions through deep learning promises to streamline clinical workflows and standardise diagnostic output. However, accurate disease detection and precise report generation remain significant challenges due to limitations in capturing fine-grained visual features and ensuring clinical coherence. To address these issues, we propose RL-ACRGNet, an improved encoder-decoder model that integrates a pre-trained DenseNet encoder with a multilevel LSTM decoder within an off-policy reinforcement learning framework. Using a dual-network approach to refine visual-semantic embeddings through a metric-based reward mechanism, we demonstrate that RL-ACRGNet consistently outperforms state-of-the-art baselines on the IU-Xray dataset, achieving quantitative improvements in BLEU-4 (0.47%), METEOR (0.17%) and ROUGE-L (0.518). Furthermore, comprehensive evaluations on the large-scale MIMIC-CXR data set confirm the robust generalisation of the model and its ability to generate high-quality, clinically relevant reports