Philippe CIUCIU (PARIETAL - Inria/CEA/Université Paris-Saclay) will give a talk at NeuroSpin on December 14th.

Short abstract:

Reducing acquisition time is a major challenge in high-resolution MRI that has been successfully addressed by the Compressed Sensing (CS) theory. Until the present, most of Fourier encoding schemes consist in downsampling existing k-space trajectories. Recently, we have overcome this issue by proposing the Spreading Projection Algorithm for Rapid K-space sampLING (SPARKLING) for T2* 2D non-Cartesian imaging and extended this approach to 3D imaging using the usual stacking strategy of 2D SPARKLING (SoS) sampling patterns. In this talk, I will present recent advancements based on a globally optimized 3D SPARKLING extension and will show how this version outperforms the SoS strategy both on phantom and in vivo human brain data collected at 3 Tesla. Additionally will discuss some important computational aspects for 3D MRI reconstruction in the standard variational setting. Discussion will follow in which, the CEA’s own deep-learning architecture, called XPDNet, will be introduced for 2D multi-coil MR image reconstruction. Summary of the last results on the fastMRI challenge will be showcased. Lastly, I will illustrate XPDNet’s transfer learning capacity on 7T NeuroSpin T2 images and demonstrate how it can easily handle non-Cartesian data.