Urinary bladder cancer is one of the most common urinary tract cancers. Standard diagnosis procedure can be invasive and time-consuming. For these reasons, procedure called optical biopsy is introduced. This procedure allows in-vivo evaluation of bladder mucosa without the need for biopsy. Although less invasive and faster, accuracy is often lower. For this reason, machine learning (ML) algorithms are used to increase its accuracy. The issue with ML algorithms is their sensitivity to the amount of input data. In medicine, collection can be time-consuming due to a potentially low number of patients. For these reasons, data augmentation is performed, usually through a series of geometric variations of original images. While such images improve classification performance, the number of new data points and the insight they provide is limited. These issues are a motivation for the application of novel augmentation methods. Authors demonstrate the use of Deep Convolutional Generative Adversarial Networks (DCGAN) for the generation of images. Augmented datasets used for training of commonly used Convolutional Neural Network-based (CNN) architectures (AlexNet and VGG-16) show a significcan performance increase for AlexNet, where AUCmicro reaches values up to 0.99. Average and median results of networks used in grid-search increases. These results point towards the conclusion that GAN-based augmentation has decreased the networks sensitivity to hyperparemeter change.

Herein we have demonstrated that both superoxide dismutase (SOD) mimic, cationic Mn(III) meso-tetrakis(N-n-hexylpyridinium-2-yl)porphyrin (MnTnHex-2-PyP⁵⁺), and non-SOD mimic, anionic Mn(III) meso-tetrakis(4-carboxylatophenyl)porphyrin (MnTBAP³⁻), protect against oxidative stress caused by spinal cord ischemia/reperfusion via suppression of nuclear factor kappa B (NF-κB) pro-inflammatory pathways. Earlier reports showed that Mn(III) N-alkylpyridylporphyrins were able to prevent the DNA binding of NF-κB in an aqueous system, whereas MnTBAP³⁻ was not. Here, for the first time, in a complex in vivo system—animal model of spinal cord injury—a similar impact of MnTBAP³⁻, at a dose identical to that of MnTnHex-2-PyP⁵⁺, was demonstrated in NF-κB downregulation. Rats were treated subcutaneously at 1.5 mg/kg starting at 30 min before ischemia/reperfusion, and then every 12 h afterward for either 48 h or 7 days. The anti-inflammatory effects of both Mn porphyrins (MnPs) were demonstrated in the spinal cord tissue at both 48 h and 7 days. The downregulation of NF-κB, a major pro-inflammatory signaling protein regulating astrocyte activation, was detected and found to correlate well with the suppression of astrogliosis (as glial fibrillary acidic protein) by both MnPs. The markers of oxidative stress, lipid peroxidation and protein carbonyl formation, were significantly reduced by MnPs. The favorable impact of both MnPs on motor neurons (Tarlov score and inclined plane test) was assessed. No major changes in glutathione peroxidase- and SOD-like activities were demonstrated, which implies that none of the MnPs acted as SOD mimic. Increasing amount of data on the reactivity of MnTBAP³⁻ with reactive nitrogen species (RNS) (.NO/HNO/ONOO⁻) suggests that RNS/MnTBAP³⁻-driven modification of NF-κB protein cysteines may be involved in its therapeutic effects. This differs from the therapeutic efficacy of MnTnHex-2-PyP⁵⁺ which presumably occurs via reactive oxygen species and relates to NF-κB thiol oxidation; the role of RNS cannot be excluded.