Keywords: Image acquisition: Machine learning, Image acquisition: Reconstruction, Musculoskeletal: Knee
Artificial intelligence (AI) has been advancing rapidly and has shown great potential in accelerating MR imaging. This talk will aim to explain the basic principles of fast MRI with AI-based acquisition and reconstruction for broad audience. We will review the basic deep learning (DL) components that have been widely used in the field and provide an overview of the recent advances on DL-based MRI reconstruction from accelerated acquisitions. Based on that, we will introduce state-of-the-art DL reconstruction approaches with a particular focus on musculoskeletal imaging. We will also discuss about the current limitations, challenges and opportunities for AI-based fast MRI.