Abstract #4470
Evaluation of Diffusion Spectrum Imaging Reconstruction with Trained Dictionaries use of 3T MR
Ping-Hong Yeh 1 , Namgyun Lee 2 , John Morissette 3 , Arman A. Taheri 3 , Li-Wei Kuo 4 , Fang-Cheng Yeh 5 , Erick Jorge Canales- Rodrguez 6 , Wei Lui 3 , John Ollinger 3 , Terrence Oakes 3 , Mark L. Ettenhofer 7 , and Gerard Riedy 3
1
Henry Jackson Foundation for the Advancement
of Military Medicine, Bethesda, MD, United States,
2
Korea
Basic Science Institute, Korea,
3
National
Capital Neuroimaging Consortium, Bethesda, MD, United
States,
4
National
Health Research Institutes, Taiwan,
5
Carnegie
Mellon University, PA, United States,
6
FIDMAG
Research Foundation, Germanes Hospitalaries and
CIBERSAM, Barcelona, Spain,
7
7Uniformed
Services University of the Health Sciences, MD, United
States
Recent work using Compressed Sensing (CS) reconstruction
shows promising in greatly reducing diffusion spectrum
imaging (DSI) scan time without jeopardizing critical
image information. We evaluate the performance of CS
reconstruction using dictionary-based training coupled
with the Focal Underdetermined System Solver (FOCUSS)
algorithm and L2 regularization on undersampled human
brain DSI data acquired by a clinical 3T MR scanner
within an acceptable time frame (< 20 minutes).
This abstract and the presentation materials are available to members only;
a login is required.
Join Here
