Chest X Ray Report Generation
Chest X-ray report generation uses artificial intelligence to automatically create radiology reports from X-ray images, aiming to reduce radiologist workload and improve diagnostic efficiency. Current research focuses on leveraging large language models (LLMs) and multimodal architectures that integrate image data with patient information (e.g., vital signs, medical history) to enhance report accuracy and clinical relevance, often employing techniques like contrastive learning and retrieval augmentation to improve model performance. These advancements hold significant potential for improving healthcare by accelerating diagnosis, standardizing reporting, and potentially reducing diagnostic errors.
Papers
MedCycle: Unpaired Medical Report Generation via Cycle-Consistency
Elad Hirsch, Gefen Dawidowicz, Ayellet Tal
TiBiX: Leveraging Temporal Information for Bidirectional X-ray and Report Generation
Santosh Sanjeev, Fadillah Adamsyah Maani, Arsen Abzhanov, Vijay Ram Papineni, Ibrahim Almakky, Bartłomiej W. Papież, Mohammad Yaqub