Clinical applications of generative artificial intelligence in radiology: image translation, synthesis, and text generation

Abstract

Generative artificial intelligence (AI) has enabled tasks in radiology, including tools for improving image quality. Recently, new hotspots have emerged, such as intra- or inter-modal image translation, task-specific image synthesis, and text generation. Advances in generative AI have facilitated the move towards low-dose, cost-effective, and high-quality radiological image acquisition. Large language models can aid radiologists by generating professional answers and facilitating patient-physician communications. However, radiologists must be aware of potential inaccuracies in the generated content and should only use such tools after rigorous validation of their performance.

Ähnliche Arbeiten