Generative Adversarial Networks for the Creation of Realistic Artificial Brain Magnetic Resonance Images

Koshino Kazuhiro, Rudolf A. Werner, Fujio Toriumi, Mehrbod S. Javadi, Martin G. Pomper, Lilja B. Solnes, Franco Verde, Takahiro Higuchi, Steven P. Rowe

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

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.

Original languageEnglish
Pages (from-to)159-163
Number of pages5
JournalTomography (Ann Arbor, Mich.)
Volume4
Issue number4
DOIs
Publication statusPublished - Dec 1 2018
Externally publishedYes

Keywords

  • AI
  • DCGAN
  • GAN
  • MRI
  • artificial intelligence
  • machine learning
  • magnetic resonance imaging
  • stroke

Fingerprint Dive into the research topics of 'Generative Adversarial Networks for the Creation of Realistic Artificial Brain Magnetic Resonance Images'. Together they form a unique fingerprint.

  • Cite this

    Kazuhiro, K., Werner, R. A., Toriumi, F., Javadi, M. S., Pomper, M. G., Solnes, L. B., Verde, F., Higuchi, T., & Rowe, S. P. (2018). Generative Adversarial Networks for the Creation of Realistic Artificial Brain Magnetic Resonance Images. Tomography (Ann Arbor, Mich.), 4(4), 159-163. https://doi.org/10.18383/j.tom.2018.00042