Meeting Banner
Abstract #3809

Bringing Compressed Sensing to Clinical Reality: Prototypic Setup for Evaluation in Routine Applications

Kai Tobias Block1, Robert Grimm2, Li Feng3, Ricardo Otazo1, Hersh Chandarana1, Mary Bruno1, Christian Geppert4, Daniel K. Sodickson1

1Center for Biomedical Imaging, NYU Langone Medical Center, New York, NY, United States; 2Pattern Recognition Lab, University of Erlangen-Nuremberg, Erlangen, Germany; 3Center for Biomedical Imaging, New York University Langone Medical Center, New York, NY, United States; 4Siemens Medical Systems, New York, NY, United States

Compressed sensing is a promising technique for MRI reconstruction from incomplete data, but the feasibility and reliability for clinical routine applications have not been verified. Here, we present a prototypic setup that allows evaluating a recently proposed CS approach for motion-robust dynamic T1-weighted imaging in daily patient exams. It consists of a 3D stack-of-stars GRE sequence, a fully-automatic service for raw-data transfer to a multi-core server, and a highly parallelized implementation of the reconstruction algorithm. Images are saved in DICOM format and forwarded to the PACS archive, which enables our radiologists to read the images along with the conventional exams.

Abstract PDF Presentation Video

Keywords

able achieve achieved affect agent allocations applications approaches approved architecture archive arrives available background biomedical block body breathing bringing clinical clinically coefficients community comp compressed computational computations computer computing conducted configuration configured contrast core currently daily describe developed development diagnostic dynamic enthusiasm environment established evaluate evaluated exam exams expensive export external feedback finished full grasp header helps implemented initial initiated injected injector integrated interface invest investment iterations language libraries limitations lung major make manufacturers medical memory motion mouse necessary next night nodes novel numerical operating overcome partial partition patient patients performance period potential problem product programming protocol protocols prototypic published quality radiologists read reading recently recognition reconstructed reconstruction reconstructions reduce reliability remain required requires respiration robust robustness routine runs saved scientific sensing separated server service setup share slices software solutions stack stars step steps studies substantial support system systems table tags taken technicians temporal today transport unclear usage validate workstation writing