Yamin Arefeen1, Onur Beker2, Heng Yu3, Elfar Adalsteinsson4,5,6, and Berkin Bilgic5,7,8
1Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, United States, 2Department of Computer and Communication Sciences, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland, 3Department of Automation, Tsinghua University, Beijing, China, 4Massachusetts Institute of Technology, Cambridge, MA, United States, 5Harvard-MIT Health Sciences and Technology, Cambridge, MA, United States, 6Institute for Medical Engineering and Science, Cambridge, MA, United States, 7Athinoula A. Martinos Center for Biomedical Imaging, Charlestown, MA, United States, 8Department of Radiology, Harvard Medical School, Boston, MA, United States
1Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, United States, 2Department of Computer and Communication Sciences, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland, 3Department of Automation, Tsinghua University, Beijing, China, 4Massachusetts Institute of Technology, Cambridge, MA, United States, 5Harvard-MIT Health Sciences and Technology, Cambridge, MA, United States, 6Institute for Medical Engineering and Science, Cambridge, MA, United States, 7Athinoula A. Martinos Center for Biomedical Imaging, Charlestown, MA, United States, 8Department of Radiology, Harvard Medical School, Boston, MA, United States
Spark, a scan-specific model for accelerated MRI reconstruction, is extended to advanced encoding and reconstruction schemes. We show improvement in 3D imaging with integrated and external calibration data, and in multiband, wave-encoded imaging.
Figure
3: Comparison between 4 x 3 accelerated, l2-regularized GRAPPA using 3D kernels
trained on a reference scan, and an acceleration matched SPARK acquisition
(un-regularized GRAPPA-input). SPARK measured the 30 x 30 undersampled
ACS region with 2 x 2 undersampling and the exterior of kspace with 4 x 3
undersampling in the phase encode and partition directions. SPARK
exploits the same reference scan used in GRAPPA to achieve improvement at the
representative slices.
Figure 4: Comparisons between sense, sense + SPARK, wave encoding, and wave + SPARK reconstructions on a simulated multiband 5, in-plane acceleration 2, acquisition. Wave was simulated with a maximum Gy/Gz gradient amplitude of 16 $$$\frac{mT}{m}$$$ and two cycles. Complex gaussian noise was added to all simulated data. SPARK provides qualitative and quantitative rmse improvement for both the sense and wave reconstructions. Wave + SPARK achieves the best results on both the total slice group and individual slices.