1781
View Abstract / View Presentation
Enhancing the Reconstruction quality of Physics-Guided Deep Learning via Holdout Multi-Masking
Burhaneddin Yaman1,2, Seyed Amir Hossein Hosseini1,2, Steen Moeller2, and Mehmet Akçakaya1,2
1University of Minnesota, Minneapolis, MN, United States, 2Center for Magnetic Resonance Research, Minneapolis, MN, United States
Using a holdout multi-masking approach in the data consistency (DC) units of physics-guided deep learning networks during supervised training improves upon conventional supervised training, which uses all acquired points for DC, with a reduction of aliasing and banding artifacts.
Figure 2. Reconstruction results for a representative test slice using CG-SENSE, proposed multi-mask and conventional supervised PG-DL methods. CG-SENSE suffers from noise amplification and significant residual artifacts (red arrows). Conventional supervised PG-DL approach suppresses artifacts further compared to CG-SENSE, but it still exhibits residual artifacts (red arrows) as well. Proposed multi-mask supervised PG-DL approach outperforms conventional PG-DL approach by successfully removing the residual artifacts. Difference images align with the observations.
Figure 4. Reconstruction results for conventional and proposed multi-mask supervised PG-DL. Conventional supervised PG-DL suffers from banding artifacts shown with yellow arrows. Proposed multi-mask supervised PG-DL improves reconstruction quality by significantly suppressing these banding artifacts.