Multisequence 3-T Image Synthesis from 64-mT Low-Field-Strength MRI Using Generative Adversarial Networks in Multiple Sclerosis

Multisequence 3-T Image Synthesis from 64-mT Low-Field-Strength MRI Using Generative Adversarial Networks in Multiple Sclerosis

Abstract Background Portable low-field-strength (64-mT) MRI scanners show promise for increasing access to neuroimaging for clinical and research purposes; however, these devices produce lower-quality images than conventional high-field-strength scanners. Purpose To develop and evaluate a deep learning architecture to generate high-field-strength quality brain images from low-field-strength inputs using paired data from patients with multiple sc…

Can Deep Learning Enhance Low-Field MRI for Multiple Sclerosis Assessment?

In comparison to native 64-mT MRI, the deep learning generative model LowGAN offered enhanced white matter lesion conspicuity and image quality in a study involving patients with multiple sclerosis.