Alexander Lin1, Demba Ba1, and Berkin Bilgic2,3
1Harvard University, Cambridge, MA, United States, 2Department of Radiology, Massachusetts General Hospital, Martinos Center for Biomedical Imaging, Boston, MA, United States, 3Harvard Medical School, Boston, MA, United States
1Harvard University, Cambridge, MA, United States, 2Department of Radiology, Massachusetts General Hospital, Martinos Center for Biomedical Imaging, Boston, MA, United States, 3Harvard Medical School, Boston, MA, United States
We propose Bayesian accelerated Compressed Sensing (BaCS) to provide two orders of magnitude computational speed up in Bayesian CS, allowing it to run faster than sparseMRI while improving quality by exploiting joint reconstruction, and expanded its applicability to parallel imaging.
Fig4. In this single-coil, complex-valued, in vivo experiment with four contrasts, joint reconstruction with BaCS provides 2.0-fold to 1.2-fold RMSE reduction over sparseMRI for a wide range of 2D acceleration factors. It is 31x faster on the GPU, and 2.8x faster on the CPU compared to sparseMRI.
Fig5. Synergistic combination of BaCS with SENSE yields a significant, 1.4x improvement in RMSE over standard SENSE reconstruction at R=5-fold total acceleration using 32 channel data. This is made possible by the application uniform R1=2-fold undersampling with SENSE, and an additional R2=2.5-fold random undersampling on the reduced FOV coil images with joint BaCS reconstruction.