Openly accessible

Medical image synthesis using generative adversarial networks: towards photo-realistic image synthesis

Attia, Mohamed Hassan 2018, Medical image synthesis using generative adversarial networks: towards photo-realistic image synthesis, Ph.D. thesis, Institute for Intelligent Systems Research and Innovation, Deakin University.

Attached Files
Name Description MIMEType Size Downloads
attia-medicalimage-2019.pdf Connect to thesis application/pdf 51.10MB 13

Title Medical image synthesis using generative adversarial networks: towards photo-realistic image synthesis
Author Attia, Mohamed Hassan
Institution Deakin University
School Institute for Intelligent Systems Research and Innovation
Faculty Deputy Vice-Chancellor Research Group
Degree type Research doctorate
Degree name Ph.D.
Thesis advisor Hossny MohammedORCID iD for Hossny Mohammed orcid.org/0000-0002-1593-6296
Date submitted 2018-09
Summary This proposed work addresses the photo-realism for synthetic images. We introduced a modified generative adversarial network: StencilGAN. It is a perceptually-aware generative adversarial network that synthesizes images based on overlaid labelled masks. This technique can be a prominent solution for the scarcity of the resources in the healthcare sector.
Language eng
Indigenous content off
Field of Research 080106 Image Processing
080103 Computer Graphics
Socio Economic Objective 970101 Expanding Knowledge in the Mathematical Sciences
Description of original 193 p.
Copyright notice ┬ęThe author
Free to Read? Yes
Persistent URL http://hdl.handle.net/10536/DRO/DU:30131733

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 13 Abstract Views, 15 File Downloads  -  Detailed Statistics
Created: Fri, 15 Nov 2019, 15:49:37 EST by Penny Mcevoy

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.