Meeting Banner
Abstract #3522

Efficient Network for Diffusion-Weighted Image Interpolation and Accelerated Shell Sampling

Eric Y. Pierre1,2, Kieran O'Brien3, Thorsten Feiweier4, Josef Pfeuffer4, and Daniel Staeb2
1The Florey Institute of Neuroscience, Melbourne, Australia, 2MR Research Collaborations, Siemens Healthcare Pty Ltd, Bayswater, Australia, 3MR Research Collaborations, Siemens Healthcare Pty Ltd, Brisbane, Australia, 4MR Applications Predevelopment, Siemens Healthcare GmbH, Erlangen, Germany


We propose an efficient, densely connected network to synthesize unacquired DW-volumes from other acquired DW-directions and b=0 mm2/s volumes, allowing acceleration of high-angular DWI shell acquisition by skipping some DW-directions altogether.

For training, we used a high-quality dataset of 20 HCP subjects with 90 DW-directions per subject at both b=1000 mm2/s and 3000 mm2/s. 40 HCP subjects were used for validation. 30 DW-directions were selected for input to reconstruct the other 60 missing target DW-directions.

Comparison with a linear-interpolation benchmark show improved fidelity of synthesized DW-volumes and FOD maps to a gold standard acquisition, for both b-values.

This abstract and the presentation materials are available to members only; a login is required.

Join Here