Medical Report Generation
Medical report generation (MRG) uses artificial intelligence to automatically create accurate and comprehensive clinical descriptions from medical images, aiming to alleviate radiologist workload and improve diagnostic efficiency. Current research heavily utilizes large language models (LLMs) and transformer-based architectures, often incorporating multi-modal learning, contrastive learning, and knowledge graphs to enhance report quality and address data imbalances and biases. These advancements hold significant potential for improving healthcare by accelerating diagnosis, reducing errors, and enabling more efficient use of radiologist expertise.
Papers
MiniGPT-Med: Large Language Model as a General Interface for Radiology Diagnosis
Asma Alkhaldi, Raneem Alnajim, Layan Alabdullatef, Rawan Alyahya, Jun Chen, Deyao Zhu, Ahmed Alsinan, Mohamed Elhoseiny
MedRAT: Unpaired Medical Report Generation via Auxiliary Tasks
Elad Hirsch, Gefen Dawidowicz, Ayellet Tal