@article{EisslerWernerAriasLozaetal.2021,
  author    = {Eissler, Cristoph and Werner, Rudolf A. and Arias-Loza, Paula and Nose, Naoko and Chen, Xinyu and Pomper, Martin G. and Rowe, Steven P. and Lapa, Constantin and Buck, Andreas K. and Higuchi, Takahiro},
  title     = {The number of frames on ECG-gated \(^{18}\)F-FDG small animal PET has a significant impact on LV systolic and diastolic functional parameters},
  series = {Molecular Imaging},
  volume    = {2021},
  journal   = {Molecular Imaging},
  doi       = {10.1155/2021/4629459},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-265778},
  year      = {2021},
  abstract  = {Objectives. This study is aimed at investigating the impact of frame numbers in preclinical electrocardiogram- (ECG-) gated \(^{18}\)F-fluorodeoxyglucose (\(^{18}\)F-FDG) positron emission tomography (PET) on systolic and diastolic left ventricular (LV) parameters in rats. Methods. \(^{18}\)F-FDG PET imaging using a dedicated small animal PET system with list mode data acquisition and continuous ECG recording was performed in diabetic and control rats. The list-mode data was sorted and reconstructed with different numbers of frames (4, 8, 12, and 16) per cardiac cycle into tomographic images. Using an automatic ventricular edge detection software, left ventricular (LV) functional parameters, including ejection fraction (EF), end-diastolic (EDV), and end-systolic volume (ESV), were calculated. Diastolic variables (time to peak filling (TPF), first third mean filling rate (1/3 FR), and peak filling rate (PFR)) were also assessed. Results. Significant differences in multiple parameters were observed among the reconstructions with different frames per cardiac cycle. EDV significantly increased by numbers of frames (353.8 \& PLUSMN; 57.7 mu l*, 380.8 \& PLUSMN; 57.2 mu l*, 398.0 \& PLUSMN; 63.1 mu l*, and 444.8 \& PLUSMN; 75.3 mu l at 4, 8, 12, and 16 frames, respectively; *P < 0.0001 vs. 16 frames), while systolic (EF) and diastolic (TPF, 1/3 FR and PFR) parameters were not significantly different between 12 and 16 frames. In addition, significant differences between diabetic and control animals in 1/3 FR and PFR in 16 frames per cardiac cycle were observed (P < 0.005), but not for 4, 8, and 12 frames. Conclusions. Using ECG-gated PET in rats, measurements of cardiac function are significantly affected by the frames per cardiac cycle. Therefore, if you are going to compare those functional parameters, a consistent number of frames should be used.},
  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}
}