Recurrent Inference Machines for Reconstructing Heterogeneous MRI Data

Magnetic Resonance Imaging (MRI) is used in a wide variety of research and clinical applications measuring soft tissue in the human body. Systems at multiple field strengths deploy several measuring sequences to produce the specific contrast for the intended purpose, including T1-, T2-, and -weighted images. The scanner measures data in the space of proton net-precession frequencies, known in MRI as k-space. Once enough samples in k-space are acquired to meet the Nyquist-criterion, the MR-image of tissue density can be computed through the inverse Fourier transform.

Source: Medical Image Analysis - January 18, 2019 Category: Radiology Authors: Kai L ønning, Patrick Putzky, Jan-Jakob Sonke, Liesbeth Reneman, Matthan W.A. Caan, Max Welling Source Type: research