LAPANet: Direct K-space Registration Enables Sub-5ms Motion Tracking in Cardiac MRI

A new k-space-based AI model (LAPANet) accurately estimates cardiac MRI motion from just 2 Cartesian lines/frame or 3 radial spokes/frame, achieving sub-5 ms temporal resolution. This bypasses image reconstruction and avoids undersampling artifacts, enabling real-time motion tra…

• LAPANet recovers non-rigid motion from highly undersampled k-space data (2 Cartesian lines/frame, 3 radial spokes/frame).
• It provides sub-5 ms temporal resolution, suitable for real-time and interventional MRI.
• Existing image-based and other k-space registration methods fail to maintain anatomically plausible motion under these accelerations.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.