Generative adversarial network: a statistical-based deep learning paradigm to improve detecting breast cancer in thermograms.

Thermography, as a harmless modality, thanks to its low equipment complexity in parallel with quick and cheap access, has been able to come up as a method with significant potential in the diagnosis of some cancers in recent years. However, the complexity of the images resulting from this method has caused the use of deep learning to interpret thermograms. A limiting factor in this process is the strong dependence of deep learning methods on the number of training data, which is a serious challenge in thermography due to the young age of this technology and the lack of available images. In this paper, an attempt is made to reduce the above challenge by utilizing the concept of statistical learning in such a way that the statistical distribution of the original data is estimated by using generative adversarial networks (i.e., GAN). Then, several fake images are reconstructed based on the estimated distribution in order to increase the training thermograms. Since the fake images are reconstructed based on similar statistics of real thermograms in each class, the effective features of each class are preserved to a significant extent in the reconstruction process. The use of this method indicates a significant improvement in the separation of healthy and cancerous thermograms compared to the benchmark method which does not use the concept of GAN in such a way that characteristics of sensitivity and accuracy are improved in ranges of 3-9% and 3-7%, respectively. In terms of specificity, although we have seen an improvement of up to 9%, in some cases, small drops of up to 2% have also been observed, which can still be justified due to the significant improvement in sensitivity and accuracy.

Comparing Serum and Salivary Levels of Vitamin D in Patients with Recurrent Aphthous Stomatitis and Healthy Individuals.

STATEMENT OF THE PROBLEM: Recurrent aphthous stomatitis (RAS) is the most prevalent ulcerative condition of the oral mucosa. Many studies have emphasized on immunologic factors as the reason of inducing RAS; however, the exact etiologic cause of RAS has not been identified yet. Vitamin D has an endocrine function and regulatory effects on the immune system. It has potential therapeutic effects on autoimmune diseases, psoriasis, and neoplasms. Vitamin D deficiency has been detected in some autoimmune diseases such as rheumatoid arteritis. PURPOSE: The aim of the present study was to compare the serum and salivary levels of vitamin D in patients with RAS and healthy individuals. MATERIALS AND METHOD: In this cross sectional study, patients with RAS, referring to the Department of Oral Medicine, Tabriz Faculty of Dentistry, were evaluated after taking medical history, clinical examinations, and completing an informed consent form. The serum and salivary vitamin D levels were compared between case (n=26) and control (n=26) groups. RESULTS: The mean serum vitamin D levels in the case and control groups were 33.0.7±12.41 and 50.89±9.30 (ng/dL), respectively, with a statistically significant difference (p<0.001). On the other hand, the mean salivary vitamin D levels in the case and control groups were 17.36± 8.01 and 20.79±6.31 (ng/dL), respectively, with no statistically significant difference (p= 0.09). In addition, the correlation between the serum and salivary levels of vitamin D was 56%, being statistically significant (p< 0.001). CONCLUSION: The serum levels of vitamin D in patients with RAS were significantly less than that in healthy individuals; however, there were no significant differences in salivary vitamin D levels between patients with RAS and healthy individuals. In addition, there was a significant and positive correlation between serum and salivary levels of vitamin D in all patients.

Effects of Zinc Oxide Nanoparticles on Performance, Egg Quality, Tissue Zinc Content, Bone Parameters, and Antioxidative Status in Laying Hens.

The objective of this study was to observe the effects of dietary supplementation with zinc oxide nanoparticles (ZnO-NPs) on performance, egg quality, tissue Zn content, bone parameters, superoxide dismutase activity (SOD), and egg malondialdehyde (MDA) content in laying hens. A total of 288 laying hens at 64 weeks of age were randomly assigned to 4 treatments, 6 replicates, with 12 birds each. Experimental diets included the based diet (without Zn supplementation), and basal diet supplemented with 40, 80, and 120 mg Zn/kg from ZnO-NPs. Feed intake and egg mass were significantly higher in the 40 and 80 ZnO-NPs groups than the other groups. The birds in the 80 ZnO-NPs group had significantly higher egg product than the 120 ZnO-NPs and control groups. Egg shell thickness and shell strength significantly increased in the 40 and 80 ZnO-NPs groups. Moreover, Haugh unit significantly improved in the groups supplemented with ZnO-NPs, compared to the control group. Bone-breaking strength was significantly greater in the 80 ZnO-NPs group than the 120 ZnO-NPs and control groups. Also, ash weight was significantly greater in the 40 and 80 ZnO-NPs groups than the control group. There were significant differences among the groups in the Zn content in plasma, tibia, liver, pancreas, and egg. Relative to the control group, ZnO-NPs supplementation significantly increased the activities of SOD in the liver, pancreas, and plasma. The MDA content in egg was significantly reduced in the groups supplemented with ZnO-NPs. In conclusion, this study demonstrates that ZnO-NPs as dietary supplementation can improve the performance of laying hens, and levels of 40 to 80 ZnO-NPs are the optimal concentrations.