Multiparametric Magnetic Resonance Image Synthesis using Generative Adversarial Networks

Haarburger, Christoph; Horst, Nicolas; Truhn, Daniel; Broeckmann, Mirjam; Schrading, Simone; Kuhl, Christiane; Merhof, Dorit

Multiparametric Magnetic Resonance Image Synthesis using Generative Adversarial Networks

Files

011-015.pdf (681.37 KB)

Date

2019

Authors

Haarburger, Christoph
Horst, Nicolas
Truhn, Daniel
Broeckmann, Mirjam
Schrading, Simone
Kuhl, Christiane
Merhof, Dorit

Publisher

The Eurographics Association

Abstract

Generative 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.

        @inproceedings{10.2312:vcbm.20191226
,
booktitle = {Eurographics Workshop on Visual Computing for Biology and Medicine
},
editor = {Kozlíková, Barbora and Linsen, Lars and Vázquez, Pere-Pau and Lawonn, Kai and Raidou, Renata Georgia
},
title = {{Multiparametric Magnetic Resonance Image Synthesis using Generative Adversarial Networks
}},
author = {Haarburger, Christoph and 
Horst, Nicolas and 
Truhn, Daniel and 
Broeckmann, Mirjam and 
Schrading, Simone and 
Kuhl, Christiane and 
Merhof, Dorit
},
year = {2019
},
publisher = {The Eurographics Association
},
ISSN = {2070-5786
},
ISBN = {978-3-03868-081-9
},
DOI = {10.2312/vcbm.20191226
}
}