TY - JOUR A1 - Kazuhino, Koshino A1 - Werner, Rudolf A. A1 - Toriumi, Fuijo A1 - Javadi, Mehrbod S. A1 - Pomper, Martin G. A1 - Solnes, Lilja B. A1 - Verde, Franco A1 - Higuchi, Takahiro A1 - Rowe, Steven P. T1 - Generative Adversarial Networks for the Creation of Realistic Artificial Brain Magnetic Resonance Images JF - Tomography 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. KW - AI KW - Magnetresonanztomografie KW - artificial intelligence KW - magnetic resonance imaging KW - MRI KW - DCGAN KW - GAN KW - stroke KW - machine learning Y1 - 2018 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-172185 VL - 4 IS - 4 ER - TY - JOUR A1 - Lapa, Constantin A1 - Linsenmann, Thomas A1 - Lückerath, Katharina A1 - Samnick, Samuel A1 - Herrmann, Ken A1 - Stoffer, Carolin A1 - Ernestus, Ralf-Ingo A1 - Buck, Andreas K. A1 - Löhr, Mario A1 - Monoranu, Camelia-Maria T1 - Tumor-Associated Macrophages in Glioblastoma Multiforme—A Suitable Target for Somatostatin Receptor-Based Imaging and Therapy? JF - PLoS One N2 - Background Glioblastoma multiforme (GBM) is the most common primary brain tumor in adults. Tumor-associated macrophages (TAM) have been shown to promote malignant growth and to correlate with poor prognosis. [1,4,7,10-tetraazacyclododecane-NN′,N″,N′″-tetraacetic acid]-d-Phe1,Tyr3-octreotate (DOTATATE) labeled with Gallium-68 selectively binds to somatostatin receptor 2A (SSTR2A) which is specifically expressed and up-regulated in activated macrophages. On the other hand, the role of SSTR2A expression on the cell surface of glioma cells has not been fully elucidated yet. The aim of this study was to non-invasively assess SSTR2A expression of both glioma cells as well as macrophages in GBM. Methods 15 samples of patient-derived GBM were stained immunohistochemically for macrophage infiltration (CD68), proliferative activity (Ki67) as well as expression of SSTR2A. Anti-CD45 staining was performed to distinguish between resident microglia and tumor-infiltrating macrophages. In a subcohort, positron emission tomography (PET) imaging using \(^{68}Ga-DOTATATE\) was performed and the semiquantitatively evaluated tracer uptake was compared to the results of immunohistochemistry. Results The amount of microglia/macrophages ranged from <10% to >50% in the tumor samples with the vast majority being resident microglial cells. A strong SSTR2A immunostaining was observed in endothelial cells of proliferating vessels, in neurons and neuropile. Only faint immunostaining was identified on isolated microglial and tumor cells. Somatostatin receptor imaging revealed areas of increased tracer accumulation in every patient. However, retention of the tracer did not correlate with immunohistochemical staining patterns. Conclusion SSTR2A seems not to be overexpressed in GBM samples tested, neither on the cell surface of resident microglia or infiltrating macrophages, nor on the surface of tumor cells. These data suggest that somatostatin receptor directed imaging and treatment strategies are less promising in GBM. KW - glioma KW - positron emission tomography KW - glioblastoma multiforme KW - macrophages KW - somatostatin KW - microglial cells KW - immunostaining KW - magnetic resonance imaging Y1 - 2015 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-125498 VL - 10 IS - 3 ER -