Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation

Understand

Automatic radiology reporting has great clinical potential to relieve radiologists from heavy workloads and improve diagnosis interpretation.

• Recently, researchers have enhanced data-driven neural networks with medical knowledge graphs to eliminate the severe visual and textual bias in this task.
• The structures of such graphs are exploited by using the clinical dependencies formed by the disease topic tags via general knowledge and usually do not update during the training process.
• Consequently, the fixed graphs can not guarantee the most appropriate scope of knowledge and limit the effectiveness.