Synthesis of diagnostic quality cancer pathology images by generative adversarial networks.

Deep learning-based computer vision methods have recently made remarkable breakthroughs in the analysis and classification of cancer pathology images. However, there has been relatively little investigation of the utility of deep neural networks to synthesize medical images. In this study, we evaluated the efficacy of generative adversarial networks to synthesize high-resolution pathology images of 10 histological types of cancer, including five cancer types from The Cancer Genome Atlas and the five major histological subtypes of ovarian carcinoma. The quality of these images was assessed using a comprehensive survey of board-certified pathologists (n = 9) and pathology trainees (n = 6). Our results show that the real and synthetic images are classified by histotype with comparable accuracies and the synthetic images are visually indistinguishable from real images. Furthermore, we trained deep convolutional neural networks to diagnose the different cancer types and determined that the synthetic images perform as well as additional real images when used to supplement a small training set. These findings have important applications in proficiency testing of medical practitioners and quality assurance in clinical laboratories. Furthermore, training of computer-aided diagnostic systems can benefit from synthetic images where labeled datasets are limited (e.g. rare cancers). We have created a publicly available website where clinicians and researchers can attempt questions from the image survey (http://gan.aimlab.ca/). © 2020 Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.

Proteomics, oxidative stress and male infertility.

Oxidative stress has been established as one of the main causes of male infertility and has been implicated in many diseases associated with infertile men. It results from high concentrations of free radicals and suppressed antioxidant potential, which may alter protein expression in seminal plasma and/or spermatozoa. In recent years, proteomic analyses have been performed to characterize the protein profiles of seminal ejaculate from men with different clinical conditions, such as high oxidative stress. The aim of the present review is to summarize current findings on proteomic studies performed in men with high oxidative stress compared with those with physiological concentrations of free radicals, to better understand the aetiology of oxidative stress-induced male infertility. Each of these studies has suggested candidate biomarkers of oxidative stress, among them are DJ-1, PIP, lactotransferrin and peroxiredoxin. Changes in protein concentrations in seminal plasma samples with oxidative stress conditions were related to stress responses and to regulatory pathways, while alterations in sperm proteins were mostly associated to metabolic responses (carbohydrate metabolism) and stress responses. Future studies should include assessment of post-translational modifications in the spermatozoa as well as in seminal plasma proteomes of men diagnosed with idiopathic infertility. Oxidative stress, which occurs due to a state of imbalance between free radicals and antioxidants, has been implicated in most cases of male infertility. Cells that are in a state of oxidative stress are more likely to have altered protein expression. The aim of this review is to better understand the causes of oxidative stress-induced male infertility. To achieve this, we assessed proteomic studies performed on the seminal plasma and spermatozoa of men with high levels of oxidative stress due to various clinical conditions and compared them with men who had physiological concentrations of free radicals. A variety of sperm and seminal plasma proteins were found to be expressed either in abundance (over-expressed) or in a lesser amount (underexpressed), while other proteins were found to be unique either to men with oxidative stress or to men with a balanced ratio of antioxidants/free radicals. Each study included in this review suggested several proteins that could possibly act as biomarkers of oxidative stress-induced male infertility, such as protein DJ-1, PIP, lactotransferrin and peroxiredoxin. Pathway analysis performed in these studies revealed that the changes in seminal plasma proteins in men with oxidative stress could be attributed to stress responses and regulatory pathways, while changes in sperm proteins were linked to stress responses and metabolic responses. Subsequent studies could look into post-translational modifications in the protein profile of men with idiopathic infertility. We hope that the information in this review will contribute to a better understanding of the main causes of idiopathic male infertility.