Rushdi Zahid Rusho1, Wahidul Alam1, Abdul Haseeb Ahmed2, Stanley J. Kruger3, Mathews Jacob2, and Sajan Goud Lingala1,3
1Roy J. Carver Department of Biomedical Engineering, The University of Iowa, Iowa City, IA, United States, 2Department of Electrical and Computer Engineering, The University of Iowa, Iowa City, IA, United States, 3Department of Radiology, The University of Iowa, Iowa City, IA, United States
1Roy J. Carver Department of Biomedical Engineering, The University of Iowa, Iowa City, IA, United States, 2Department of Electrical and Computer Engineering, The University of Iowa, Iowa City, IA, United States, 3Department of Radiology, The University of Iowa, Iowa City, IA, United States
We propose a novel high-speed speech MRI scheme that combines multi-coil acquisitions from a 16 channel airway coil, variable density spirals, and manifold regularization. We demonstrate efficient reconstruction of complex free running speech at a temporal resolution of 15 ms/frame.
Figure 5 (animation):
Comparison of manifold regularization and low rank regularization schemes
reconstructed using 3arms/frame (or time resolution of 15 ms). Shown are the
dynamic animations and temporal profile cuts from two subjects. We observe good
fidelity and under-sampling artifact robustness in the manifold scheme compared
to the low rank scheme. This is attributed to efficiently exploiting the
similarities in local or distant image frames within the dataset without any
explicit binning strategies.
Figure 2: Dynamic
images can be modeled as points on a smooth nonlinear manifold embedded in a
high dimensional ambient space. This is demonstrated in the dynamic free speech
task of serially counting numbers. Similar images are neighbors on the 2D
manifold even if they occur at different times (see red and green squares),
whereas dissimilar images are distant on the 2D manifold even if they occur
consecutively in time.
The manifold regularization thus exploits the similarity of points that are close
to each other on this manifold.