Deep Resolve Swift Brain is an ultra-fast brain protocol leveraging the fastest available imaging sequence, EPI, together with a Deep Learning Reconstruction to push acceleration to the edge. The protocol consists of five contrasts: T1, T2, T2*, T2 dark-fluid, and diffusion. While T1 is based on a fast GRE imaging sequence, the remaining contrasts are multi-shot EPI-based. Multi-shot EPI together with a new static field correction minimizes geometric distortions that are intrinsic to EPI imaging. Within this multi-shot EPI approach, T2 and T2* are acquired simultaneously by a Siemens Healthineers exclusive EPI-implementation, further accelerating this protocol. Multi-shot EPI-based T2 dark-fluid reduces imaging times substantially compared to standard TSE imaging and offers true FLAIR contrast due to magnetization transfer preparation. Highest image quality is ensured by a Deep Learning Reconstruction to push the limits of parallel imaging acceleration. The unique combination of multi-shot EPI imaging and Deep Learning Reconstruction enables net scan times of less than two minutes. The total table time including prescans and adjustments can be less than five minutes with this protocol.
Ultrafast Brain Imaging with Deep-Learning
Multi-Shot EPI: Technical Implementation
Bryan Clifford, et al. (Siemens Medical Solutions USA, Boston, MA, USA)
Ultrafast Brain Imaging with Deep Learning Multi-Shot EPI: Preliminary Clinical Evaluation
John Conklin, et al. (Department of Radiology, Massachusetts General Hospital, Boston, MA, USA)