Multiparametric Magnetic Resonance Image Synthesis using Generative Adversarial Networks

Simple item page
dc.contributor.authorHaarburger, Christophen_US
dc.contributor.authorHorst, Nicolasen_US
dc.contributor.authorTruhn, Danielen_US
dc.contributor.authorBroeckmann, Mirjamen_US
dc.contributor.authorSchrading, Simoneen_US
dc.contributor.authorKuhl, Christianeen_US
dc.contributor.authorMerhof, Doriten_US
dc.contributor.editorKozlíková, Barbora and Linsen, Lars and Vázquez, Pere-Pau and Lawonn, Kai and Raidou, Renata Georgiaen_US
dc.date.accessioned2019-09-03T13:49:01Z
dc.date.available2019-09-03T13:49:01Z
dc.date.issued2019
dc.description.abstractGenerative adversarial networks have been shown to alleviate the problem of limited training data for supervised learning problems in medical image computing. However, most generative models for medical images focus on image-to-image translation rather than de novo image synthesis. In many clinical applications, image acquisition is multiparametric, i.e. includes contrast-enchanced or diffusion-weighted imaging. We present a generative adversarial network that synthesizes a sequence of temporally consistent contrast-enhanced breast MR image patches. Performance is evaluated quantitatively using the Fréchet Inception Distance, achieving a minimum FID of 21.03. Moreover, a qualitative human reader test shows that even a radiologist cannot differentiate between real and fake images easily.en_US
dc.description.sectionheadersVisual Computing for MRI-based Data
dc.description.seriesinformationEurographics Workshop on Visual Computing for Biology and Medicine
dc.identifier.doi10.2312/vcbm.20191226
dc.identifier.isbn978-3-03868-081-9
dc.identifier.issn2070-5786
dc.identifier.pages11-15
dc.identifier.urihttps://doi.org/10.2312/vcbm.20191226
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/vcbm20191226
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectModeling methodologies
dc.titleMultiparametric Magnetic Resonance Image Synthesis using Generative Adversarial Networksen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
011-015.pdf
Size:
681.37 KB
Format:
Adobe Portable Document Format
Download
Collections
VCBM 19: Eurographics Workshop on Visual Computing for Biology and Medicine