TY - JOUR
T1 - Generative Adversarial Networks for the Creation of Realistic Artificial Brain Magnetic Resonance Images
AU - Kazuhiro, Koshino
AU - Werner, Rudolf A.
AU - Toriumi, Fujio
AU - Javadi, Mehrbod S.
AU - Pomper, Martin G.
AU - Solnes, Lilja B.
AU - Verde, Franco
AU - Higuchi, Takahiro
AU - Rowe, Steven P.
PY - 2018/12/1
Y1 - 2018/12/1
N2 - Even as medical data sets become more publicly accessible, most are restricted to specific medical conditions. Thus, data collection for machine learning approaches remains challenging, and synthetic data augmentation, such as generative adversarial networks (GAN), may overcome this hurdle. In the present quality control study, deep convolutional GAN (DCGAN)-based human brain magnetic resonance (MR) images were validated by blinded radiologists. In total, 96 T1-weighted brain images from 30 healthy individuals and 33 patients with cerebrovascular accident were included. A training data set was generated from the T1-weighted images and DCGAN was applied to generate additional artificial brain images. The likelihood that images were DCGAN-created versus acquired was evaluated by 5 radiologists (2 neuroradiologists [NRs], vs 3 non-neuroradiologists [NNRs]) in a binary fashion to identify real vs created images. Images were selected randomly from the data set (variation of created images, 40%-60%). None of the investigated images was rated as unknown. Of the created images, the NRs rated 45% and 71% as real magnetic resonance imaging images (NNRs, 24%, 40%, and 44%). In contradistinction, 44% and 70% of the real images were rated as generated images by NRs (NNRs, 10%, 17%, and 27%). The accuracy for the NRs was 0.55 and 0.30 (NNRs, 0.83, 0.72, and 0.64). DCGAN-created brain MR images are similar enough to acquired MR images so as to be indistinguishable in some cases. Such an artificial intelligence algorithm may contribute to synthetic data augmentation for "data-hungry" technologies, such as supervised machine learning approaches, in various clinical applications.
AB - Even as medical data sets become more publicly accessible, most are restricted to specific medical conditions. Thus, data collection for machine learning approaches remains challenging, and synthetic data augmentation, such as generative adversarial networks (GAN), may overcome this hurdle. In the present quality control study, deep convolutional GAN (DCGAN)-based human brain magnetic resonance (MR) images were validated by blinded radiologists. In total, 96 T1-weighted brain images from 30 healthy individuals and 33 patients with cerebrovascular accident were included. A training data set was generated from the T1-weighted images and DCGAN was applied to generate additional artificial brain images. The likelihood that images were DCGAN-created versus acquired was evaluated by 5 radiologists (2 neuroradiologists [NRs], vs 3 non-neuroradiologists [NNRs]) in a binary fashion to identify real vs created images. Images were selected randomly from the data set (variation of created images, 40%-60%). None of the investigated images was rated as unknown. Of the created images, the NRs rated 45% and 71% as real magnetic resonance imaging images (NNRs, 24%, 40%, and 44%). In contradistinction, 44% and 70% of the real images were rated as generated images by NRs (NNRs, 10%, 17%, and 27%). The accuracy for the NRs was 0.55 and 0.30 (NNRs, 0.83, 0.72, and 0.64). DCGAN-created brain MR images are similar enough to acquired MR images so as to be indistinguishable in some cases. Such an artificial intelligence algorithm may contribute to synthetic data augmentation for "data-hungry" technologies, such as supervised machine learning approaches, in various clinical applications.
KW - AI
KW - DCGAN
KW - GAN
KW - MRI
KW - artificial intelligence
KW - machine learning
KW - magnetic resonance imaging
KW - stroke
UR - http://www.scopus.com/inward/record.url?scp=85078504503&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85078504503&partnerID=8YFLogxK
U2 - 10.18383/j.tom.2018.00042
DO - 10.18383/j.tom.2018.00042
M3 - Article
C2 - 30588501
AN - SCOPUS:85078504503
SN - 2379-1381
VL - 4
SP - 159
EP - 163
JO - Tomography (Ann Arbor, Mich.)
JF - Tomography (Ann Arbor, Mich.)
IS - 4
ER -