Evaluation of Deep learning-based reconstruction synthetic magnetic resonance imaging MAGIC

Motivation: Synthetic MRI technology has been widely used in central nervous system imaging. Deep learning (DL) reconstruction showed promise in improving image quality and simultaneously reducing scan time. Goal(s): Our goals are to explore the application value of DLreconstruction technology in enhancing the image quality of MAGIC and potential pathological interpretation. Approach: Image quality of the T1/T2/PD relaxometry maps from MAGIC DL and MAGIC were assessed, and the potential pathological interpretation were also investigated in patients. Results: MAGIC DL image provide high quality images. Asymmetry index of T1/T2/PD values were significantly higher in lesions than that in nonlesions, but regardless of deep learning reconstruction. Impact: The utilization of deep learning-based image reconstruction techniques in MAGIC image not only provide high quality images, but also underscore the potential of the MAGIC DL methodology as an alternative tool to detect lesions in pathology studies.