Meeting Banner
Abstract #1775

Feasibility of a quasi-volumetric synthetic MRI of the brain using 2D slice-interleaved MDME acquisition with deep learned reconstruction

Ho-Joon Lee1, Yeonah Kang1, Marc Lebel2, Min Soo Park3, and Joonsung Lee3
1Department of Radiology, Haeundae Paik Hospital, Busan, Republic of Korea, 2MR Collaboration and Development, GE Healthcare, Calagary, AB, Canada, 3GE Healthcare Korea, Seoul, Republic of Korea

Sequences that allow volumetric parametric maps are being developed but when these techniques will be available clinically is uncertain. MDME sequence is a robust method, allowing rapid acquisition of T1, T2 relaxation times, PD from which one can generate synthetic multi-contrast images. However, acquisition at thin slices is challenging. With a deep learned reconstruction method, we demonstrate that interleaved thin slice acquisition of MDME, can produce quasi-volumetric synthetic MRI at an isotropic resolution. Limitations include motion misregistrations between acquisitions, parallel imaging/partial volume/pulsation related artifacts, which we believe can be overcome with technical development.

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

Join Here