eduzhai > Applied Sciences > Engineering >

Diffusion-Weighted Magnetic Resonance Brain Images Generation with Generative Adversarial Networks and Variational Autoencoders A Comparison Study

  • Save

... pages left unread,continue reading

Document pages: 20 pages

Abstract: We show that high quality, diverse and realistic-looking diffusion-weightedmagnetic resonance images can be synthesized using deep generative models.Based on professional neuroradiologists evaluations and diverse metrics withrespect to quality and diversity of the generated synthetic brain images, wepresent two networks, the Introspective Variational Autoencoder and theStyle-Based GAN, that qualify for data augmentation in the medical field, whereinformation is saved in a dispatched and inhomogeneous way and access to it isin many aspects restricted.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×