Open access
Jun 2026
Optimized Multi-Contrast Self-Supervised MRI Reconstruction Using Learned K-Space Partitioning
This work proposes a multi-contrast self-supervised multi-contrast learned partitioning method that jointly trains on multiple under-sampled contrasts without requiring fully sampled k-space data as a reference, and improves reconstruction fidelity over single-contrast self-supervised MRI reconstructions.
Brenden T. Kadota, Charles Millard, Mark Chiew
· IEEE Transactions on Biomedi... · 0 citations