@article{WernerWeichKircheretal.2018,
  author    = {Werner, Rudolf A. and Weich, Alexander and Kircher, Malte and Solnes, Lilja B. and Javadi, Mehrbod S. and Higuchi, Takahiro and Buck, Andreas K. and Pomper, Martin G. and Rowe, Steven and Lapa, Constantin},
  title     = {The theranostic promise for neuroendocrine tumors in the late 2010s - Where do we stand, where do we go?},
  series = {Theranostics},
  volume    = {8},
  journal   = {Theranostics},
  number    = {22},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-170264},
  pages     = {6088-6100},
  year      = {2018},
  abstract  = {More than 25 years after the first peptide receptor radionuclide therapy (PRRT), the concept of somatostatin receptor (SSTR)-directed imaging and therapy for neuroendocrine tumors (NET) is seeing rapidly increasing use. To maximize the full potential of its theranostic promise, efforts in recent years have expanded recommendations in current guidelines and included the evaluation of novel theranostic radiotracers for imaging and treatment of NET. Moreover, the introduction of standardized reporting framework systems may harmonize PET reading, address pitfalls in interpreting SSTR-PET/CT scans and guide the treating physician in selecting PRRT candidates. Notably, the concept of PRRT has also been applied beyond oncology, e.g. for treatment of inflammatory conditions like sarcoidosis. Future perspectives may include the efficacy evaluation of PRRT compared to other common treatment options for NET, novel strategies for closer monitoring of potential side effects, the introduction of novel radiotracers with beneficial pharmacodynamic and kinetic properties or the use of supervised machine learning approaches for outcome prediction. This article reviews how the SSTR-directed theranostic concept is currently applied and also reflects on recent developments that hold promise for the future of theranostics in this context.},
  subject      = {Positronen-Emissions-Tomografie},
  language  = {en}
}
@article{KazuhinoWernerToriumietal.2018,
  author    = {Kazuhino, Koshino and Werner, Rudolf A. and Toriumi, Fuijo and Javadi, Mehrbod S. and Pomper, Martin G. and Solnes, Lilja B. and Verde, Franco and Higuchi, Takahiro and Rowe, Steven P.},
  title     = {Generative Adversarial Networks for the Creation of Realistic Artificial Brain Magnetic Resonance Images},
  series = {Tomography},
  volume    = {4},
  journal   = {Tomography},
  number    = {4},
  doi       = {10.18383/j.tom.2018.00042},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-172185},
  pages     = {159-163},
  year      = {2018},
  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.},
  subject      = {Magnetresonanztomografie},
  language  = {en}
}