Jump to content

18468802. MODEL-BASED RECONSTRUCTION FOR GRASP MRI (Siemens Healthineers AG)

From WikiPatents

MODEL-BASED RECONSTRUCTION FOR GRASP MRI

Organization Name

Siemens Healthineers AG

Inventor(s)

Mahmoud Mostapha of Princeton NJ US

Simon Arberet of Princeton NJ US

Marcel Dominik Nickel of Herzogenaurach DE

Mariappan S. Nadar of Plainsboro NJ US

MODEL-BASED RECONSTRUCTION FOR GRASP MRI

This abstract first appeared for US patent application 18468802 titled 'MODEL-BASED RECONSTRUCTION FOR GRASP MRI

Original Abstract Submitted

Systems and methods for a deep learning reconstruction network with computationally light and efficient CNN architecture and a training strategy tailored to image reconstruction of dynamic multi-coil GRASP MRI. The configuration of the size of the network used in training time may be adjusted, which allows for higher accelerations and different hardware constraints.