AUTHOR=Yoo Denis , Choi Yuni Annette , Rah C. J. , Lee Eric , Cai Jing , Min Byung Jun , Kim Eun Ho 

TITLE=Signal Enhancement of Low Magnetic Field Magnetic Resonance Image Using a Conventional- and Cyclic-Generative Adversarial Network Models With Unpaired Image Sets

JOURNAL=Frontiers in Oncology

VOLUME=Volume 11 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.660284

DOI=10.3389/fonc.2021.660284

ISSN=2234-943X

ABSTRACT=In this study, the signal enhancement ratio of low-field magnetic resonance (MR) images was investigated using a deep learning-based algorithm. Unpaired image sets (0.06T and 1.5T MR images for different patients) were used in this study following three steps. In the first step, the deformable registration of a 1.5T MR image into a 0.06T MR image was performed to ensure that the shapes of the unpaired set matched. In the second step, a cyclic-generative adversarial network (GAN) was used to generate a synthetic MR image of the original 0.06T MR image based on the deformed or original 1.5T MR image. Finally, an enhanced 0.06T MR image could be generated using the conventional GAN with the deformed or synthetic MR image. The results from the optimized flow and enhanced MR images showed significant signal enhancement of the anatomical view, especially in the nasal septum, inferior nasal choncha, nasopharyngeal fossa, and eye lens. The signal enhancement ratio, signal-to-noise ratio (SNR) and correlation factor between the original and enhanced MR images were analyzed. A combined method using conventional- and cyclic-GANs is a promising approach for generating enhanced MR images from low-magnetic-field MR.